WO2024024444A1

WO2024024444A1 - Monitoring system, learning device, monitoring method, learning method, and program

Info

Publication number: WO2024024444A1
Application number: PCT/JP2023/025136
Authority: WO
Inventors: 要原田; 信一栗原
Original assignee: 栗田工業株式会社
Priority date: 2022-07-28
Filing date: 2023-07-06
Publication date: 2024-02-01
Also published as: JP2024017788A; JP7439865B2

Abstract

This monitoring system comprises: a determination unit that determines the internal state of a solid-liquid separation tank to be diagnosed from a supernatant water image representing the supernatant water inside the solid-liquid separation tank, using a first learning model that has learned the relationship between supernatant water images, which are images representing the supernatant water inside a solid-liquid separation tank for separating waste water into solid and liquid, and the internal state of the solid-liquid separation tank, on the basis of the supernatant water images and diagnostic results based on the supernatant water images; and an output unit that outputs information identifying the internal state of the solid-liquid separation tank to be diagnosed as determined by the determination unit using the supernatant water image of the solid-liquid separation tank and the first learning model.

Description

Monitoring systems, learning devices, monitoring methods, learning methods and programs

The present invention relates to a monitoring system, a learning device, a monitoring method, a learning method, and a program.
This application claims priority to Japanese Patent Application No. 2022-120673 filed in Japan on July 28, 2022, the contents of which are incorporated herein.

Aerobic biological treatment (activated sludge), which has an aeration tank and a settling tank in wastewater treatment, is a mature treatment form, and the equipment is almost complete in terms of engineering. However, as the products, production processes, and production volumes change, the wastewater changes, and the inflow conditions (substrate, concentration, flow rate) often differ from when the equipment was designed based on the assumed water quality and volume. In addition, due to the shift to multi-product manufacturing, there are more and more fluctuations, and the number of cases in which they become larger is increasing, making plant maintenance and management more complex and difficult. In addition, in response to the review of water quality and environmental standards, there is a need for more stable treatment than ever before, and on the other hand, there is a need to reduce treatment costs, that is, to reduce electricity costs, waste costs, and chemical consumption. It is becoming. Therefore, sophisticated management is required to accurately and quickly grasp the processing status and make appropriate adjustments according to the status, but such measurement and monitoring is not easy.

Regarding technology for monitoring the status of processing, the position of the interface formed from suspended turbidity in the liquid (interface depth) is determined based on the results of emitting ultrasonic pulses perpendicularly from the liquid surface and receiving the reflected pulses. A technique for measuring is known (for example, see Patent Document 1).
Furthermore, a technique for monitoring the state inside a tank such as a solid-liquid separation tank is known (for example, see Patent Document 2). This technology consists of an A/D converter that converts the received signal into a digital signal by a sensor that sends out ultrasound or light and receives the ultrasound or light that propagated through the water containing the suspended solid layer, and an A/D converter that converts the received signal into a digital signal. a calculation unit that calculates the position of the interface in the tank based on the information, a graphic conversion unit that converts the digital signal into pixel data, a memory that stores the pixel data and the interface position data, and the pixel data stored in the memory. and a display section that displays.
Furthermore, an interface level meter that can quickly and stably switch and display image information of a plurality of time widths is known (for example, see Patent Document 3). This interface level meter uses an ultrasonic sensor, an A/D converter that converts the signal received by the ultrasonic sensor into a digital signal, and detects the position of the interface between the suspended matter layer and the supernatant water based on the digital signal. A calculation unit that performs calculations, a graphics conversion unit that converts digital signals into pixel data corresponding to a predetermined color gradation, and a storage area that acquires and stores pixel string data including a plurality of pixel data at different time intervals. a display area that displays a plurality of pixel row data stored in any one of the storage areas based on color gradation, and a display area that displays the position of the interface calculated by the calculation unit. A display section having a display section.

Furthermore, a technique for measuring the precipitation state is known (for example, see Patent Document 4). This technique includes an ultrasonic transmitting/receiving means for transmitting and receiving ultrasonic waves vertically downward from the water surface of a settling tank, and a waveform processing means for processing reflected received waves obtained by the ultrasonic transmitting/receiving means. The waveform processing means measures the amount of substances floating under the water surface and/or the concentration distribution of sediment based on changes in the intensity of the reflected received waves.
Furthermore, a technique for detecting interfaces between layers in a sludge accumulation layer is known (for example, see Patent Document 5). This technology uses a sensor that transmits ultrasonic waves or light into the liquid in a solid-liquid separation tank and receives ultrasonic waves or light that have propagated through the water, including the sludge accumulation layer, and is based on the signals from the sensor. Then, the position of the interface between the sludge accumulation layer and the supernatant water is detected, and the interface between the free sedimentation layer occupying the uppermost layer in the sludge accumulation layer and the coagulated sedimentation layer below the free sedimentation layer is detected. In this technology, the band in which the received signal intensity distribution of the sensor in the depth direction of the tank is constant at the top of the sludge accumulation layer is defined as a free settling layer, and the received signal intensity distribution is lower than that of the free settling layer. The position where the value starts to increase is defined as the interface between the free sedimentation layer and the coagulated sedimentation layer.

Japanese Patent Application Publication No. 3-274484 JP2011-047761A Japanese Patent Application Publication No. 2011-13084 Japanese Patent Application Publication No. 4-264235 Japanese Patent Application Publication No. 2011-47760

In the techniques described above, images obtained by monitoring the processing status (hereinafter referred to as "monitoring images") are interpreted by humans. People diagnose the current state of processing by interpreting monitoring images. Furthermore, the causes of the results of diagnosing the processing status were diagnosed by humans based on their experience. Furthermore, people were making decisions about how to deal with the problem. Interpreting surveillance images requires experience, and the interpretation results may vary depending on the interpreter.
The present invention has been made in view of the above circumstances, and provides a monitoring system, a learning device, a monitoring method, a learning method, and a program that can monitor the internal state of a solid-liquid separation tank for solid-liquid separation of wastewater. With the goal.

(1) One aspect of the present invention is based on a supernatant water image that is an image representing supernatant water inside a solid-liquid separation tank for solid-liquid separation of wastewater and a diagnosis result based on the supernatant water image, Using the first learning model that has learned the relationship between the supernatant water image and the internal state of the solid-liquid separation tank, solid-liquid separation is performed from the supernatant water image representing the supernatant water inside the solid-liquid separation tank that is the target of diagnosis. a determination unit that determines the internal state of the tank; and an interior of the solid-liquid separation tank determined by the determination unit using the supernatant water image of the solid-liquid separation tank that is a diagnosis target and the first learning model. The monitoring system includes an output unit that outputs information specifying the state of the monitor.
(2) One aspect of the present invention is based on a monitoring image that is an image showing the inside of a solid-liquid separation tank for solid-liquid separation of wastewater and a diagnosis result based on the monitoring image of the inside of the solid-liquid separation tank. Based on this, the first learning model that has learned the relationship between the monitoring image and the internal state of the solid-liquid separation tank is used to determine the state of the solid-liquid separation tank from the monitoring image representing the inside of the solid-liquid separation tank that is the target of diagnosis. a determination unit that determines an internal state; and a determination unit that determines an internal state of the solid-liquid separation tank determined by the determination unit using the monitoring image of the solid-liquid separation tank that is a diagnosis target and the first learning model. The monitoring system has an output unit that outputs identifying information, and the monitoring image does not include an error image that is an image at the time of a measurement failure.
(3) One aspect of the present invention is the monitoring system according to (1) above, in which the supernatant water image does not include an error image that is an image at the time of poor measurement.
(4) In the monitoring system according to (1) above, one aspect of the present invention is to provide a supernatant water image and a supernatant water image based on the supernatant water image and information specifying a cause of a diagnosis result based on the supernatant water image. The solid-liquid separation tank is determined from the supernatant water image of the solid-liquid separation tank that is the target of diagnosis using the second learning model that has learned the relationship with information that specifies the cause of the diagnosis result inside the solid-liquid separation tank. has a cause determining unit that determines information that specifies the cause of the state inside the device, and the output unit is configured to output the supernatant water image of the solid-liquid separation tank that is the object of diagnosis and the second learning model. and further outputs information specifying the cause of the state inside the solid-liquid separation tank determined by the cause determining unit using the solid-liquid separation tank.
(5) One aspect of the present invention is the monitoring system according to (1) above, in which the supernatant water image is Using the third learning model that has learned the relationship between information and information that specifies how to deal with the diagnosis results inside the solid-liquid separation tank, solid-liquid analysis is performed from the supernatant water image of the solid-liquid separation tank that is the target of diagnosis. It has a countermeasure determination section that determines information specifying a countermeasure method for the condition inside the separation tank, and the output section outputs the supernatant water image of the solid-liquid separation tank that is the object of diagnosis and the third The learning model further outputs information specifying a method for dealing with the state inside the solid-liquid separation tank determined by the method determination section.
(6) In the monitoring system according to (1) above, one aspect of the present invention provides information for specifying the supernatant water image and a change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained. Using the fourth learning model that has learned the relationship between the supernatant water image and information specifying changes in the internal state of the solid-liquid separation tank based on the a change sign deriving unit that detects a sign of a change in the state inside the solid-liquid separation tank from a clear water image, and the output unit is configured to detect the supernatant water image of the solid-liquid separation tank to be diagnosed and the fourth The learning model further outputs information that specifies a sign of a change in the state inside the solid-liquid separation tank detected by the change sign deriving unit.
(7) One aspect of the present invention is the monitoring system according to (1) above, in which the diagnosis result is based on one or both of a deposited state of solids and a suspended state of solids included in the supernatant water image. Generated based on.
(8) One aspect of the present invention is the monitoring system according to (1) above, in which the determination unit determines the solid-liquid separation tank from the supernatant water image showing the inside of the solid-liquid separation tank that is the object of diagnosis. Determine whether the internal state is normal, malfunctioning, or abnormal.
(9) In the monitoring system according to (1) above, when the determination unit determines that the state inside the solid-liquid separation tank is either malfunctioning or abnormal, the solid-liquid separation The device further includes a notification unit that notifies that the state inside the tank is either malfunction or abnormal.

(10) One aspect of the present invention provides a supernatant water image that is an image representing supernatant water inside a solid-liquid separation tank for solid-liquid separation of wastewater, and a state of the supernatant water inside the solid-liquid separation tank. The learning device includes a learning unit that generates, through learning, a first learning model representing the relationship between the supernatant water image and the internal state of the solid-liquid separation tank based on the image-based diagnosis result.
(11) One aspect of the present invention is a monitoring image that is an image showing the inside of a solid-liquid separation tank for solid-liquid separation of wastewater, and a diagnosis result based on the monitoring image of the internal state of the solid-liquid separation tank. a learning unit that generates a first learning model representing the relationship between the monitoring image and the internal state of the solid-liquid separation tank by learning based on the above, and the monitoring image is an error image that is an image at the time of a measurement failure. It is a learning device that does not include.
(12) One aspect of the present invention is the learning device according to (10) above, in which the supernatant water image does not include an error image that is an image at the time of poor measurement.
(13) One aspect of the present invention is the learning device according to (10) above, in which the learning unit performs a process based on the supernatant water image and information specifying a cause of a diagnosis result based on the supernatant water image. , a second learning model representing the relationship between the supernatant water image and information specifying the cause of the diagnosis result inside the solid-liquid separation tank is generated by learning.
(14) One aspect of the present invention is the learning device according to (10) above, in which the learning unit is based on the supernatant water image and information specifying how to deal with a diagnosis result based on the supernatant water image. Then, a third learning model representing the relationship between the supernatant water image and information specifying how to deal with the diagnosis result inside the solid-liquid separation tank is generated by learning.
(15) One aspect of the present invention is the learning device according to (10) above, in which the learning unit is configured to determine the supernatant water image and the internal state of the solid-liquid separation tank after the supernatant water image is obtained. A fourth learning model representing the relationship between the supernatant water image and the information specifying the change in the internal state of the solid-liquid separation tank is generated based on the information specifying the change.
(16) One aspect of the present invention is the learning device according to (10) above, in which the diagnosis result is one or both of a deposited state of solids and a suspended state of solids included in the supernatant water image. Generated based on.

(17) One aspect of the present invention is based on a supernatant water image that is an image representing supernatant water inside a solid-liquid separation tank for solid-liquid separation of wastewater and a diagnosis result based on the supernatant water image, Using the first learning model that has learned the relationship between the supernatant water image and the internal state of the solid-liquid separation tank, solid-liquid separation is performed from the supernatant water image representing the supernatant water inside the solid-liquid separation tank that is the target of diagnosis. the step of determining the internal state of the tank, and the inside of the solid-liquid separation tank determined in the step of determining using the supernatant water image of the solid-liquid separation tank that is a diagnosis target and the first learning model; A monitoring method executed by a monitoring system, comprising the steps of: outputting information specifying the state of the computer.

(18) One aspect of the present invention is based on a supernatant water image that is an image representing supernatant water inside a solid-liquid separation tank for solid-liquid separation of wastewater and a diagnosis result based on the supernatant water image, This is a learning method executed by a learning device, which includes a step of generating, through learning, a first learning model representing a relationship between a supernatant water image and an internal state of a solid-liquid separation tank.

(19) One aspect of the present invention is to provide a supernatant water image, which is an image representing supernatant water inside a solid-liquid separation tank for solid-liquid separation of wastewater, to a computer of a monitoring system, and a diagnosis based on the supernatant water image. Based on the results, the first learning model that has learned the relationship between the supernatant water image and the internal state of the solid-liquid separation tank is used to create a supernatant that represents the supernatant water inside the solid-liquid separation tank that is the target of diagnosis. the step of determining the internal state of the solid-liquid separation tank from the clear water image; and the step of determining the internal state of the solid-liquid separation tank using the supernatant water image of the solid-liquid separation tank that is the object of diagnosis and the first learning model. This is a program that executes the step of outputting information specifying the internal state of the solid-liquid separation tank.

(20) One aspect of the present invention is to display a supernatant water image, which is an image representing supernatant water inside a solid-liquid separation tank for solid-liquid separation of wastewater, and an inside of the solid-liquid separation tank on a computer of a learning device. This program executes a step of generating, by learning, a first learning model representing the relationship between the supernatant water image and the internal state of the solid-liquid separation tank, based on the diagnosis result based on the supernatant water image.

According to the present invention, it is possible to provide a monitoring system, a learning device, a monitoring method, a learning method, and a program that can monitor the internal state of a solid-liquid separation tank for solid-liquid separation of wastewater.

1 is a diagram showing a configuration example of a monitoring system according to an embodiment of the present invention. It is a figure showing an example of an ultrasonic sensor. 1 is a diagram illustrating an example of a data processing device of a monitoring system according to an embodiment. It is a diagram showing an example of the operation of the monitoring system according to the present embodiment. FIG. 3 is a diagram showing an example of a monitoring image. FIG. 3 is a diagram showing an example of teacher data. FIG. 2 is a diagram showing an example 1 of the operation of the monitoring system according to the present embodiment. It is a figure showing example 2 of operation of a monitoring system concerning this embodiment. It is a figure showing example 3 of operation of a monitoring system concerning this embodiment. FIG. 7 is a diagram showing another example of the data processing device according to the present embodiment. It is a figure showing the example of composition of the monitoring system concerning modification 1 of an embodiment of the present invention. FIG. 3 is a diagram showing an example of teacher data. It is a figure showing example 1 of operation of a monitoring system concerning modification 1 of an embodiment. FIG. 7 is a diagram illustrating a second example of the operation of the monitoring system according to the first modification of the embodiment. It is a figure showing an example of composition of a monitoring system concerning modification 2 of an embodiment of the present invention. FIG. 3 is a diagram showing an example of teacher data. FIG. 7 is a diagram illustrating an example 1 of operation of a monitoring system according to a second modification of the embodiment. It is a figure showing example 2 of operation of a monitoring system concerning modification 2 of an embodiment. It is a figure showing an example of composition of a monitoring system concerning modification 3 of an embodiment of the present invention. It is a figure showing example 1 of operation of a monitoring system concerning modification 3 of an embodiment. FIG. 7 is a diagram illustrating a second example of the operation of the monitoring system according to a third modification of the embodiment. It is a figure showing an example of composition of a monitoring system concerning modification 4 of an embodiment of the present invention. It is a figure showing an example of the monitoring device of the monitoring system concerning modification 4 of this embodiment. FIG. 7 is a diagram showing an example 1 of operation of a monitoring system according to a fourth modification of the embodiment. FIG. 7 is a diagram showing a second example of the operation of the monitoring system according to a fourth modification of the embodiment. This is an example of an error image. It is a figure showing example 1 of operation of a monitoring system concerning other embodiments. It is a figure showing example 2 of operation of a monitoring system concerning other embodiments. It is a figure showing example 3 of operation of a monitoring system concerning this embodiment.

The monitoring system, monitoring method, and program of this embodiment will be explained with reference to the drawings. The embodiments described below are merely examples, and the embodiments to which the present invention is applied are not limited to the following embodiments.
In addition, in all the figures for explaining the embodiment, parts having the same functions are denoted by the same reference numerals, and repeated explanations will be omitted.
Furthermore, "based on XX" as used herein means "based on at least XX", and includes cases where it is based on another element in addition to XX. Moreover, "based on XX" is not limited to the case where XX is used directly, but also includes the case where it is based on calculations or processing performed on XX. "XX" is an arbitrary element (for example, arbitrary information).

[Embodiment]
(Monitoring system)
FIG. 1 is a diagram showing a configuration example of a monitoring system according to an embodiment of the present invention. The monitoring system 100 according to this embodiment diagnoses the state of sludge accumulation in solid-liquid separation tanks such as settling tanks and thickening tanks. In this embodiment, description will be continued regarding the sewage treatment equipment 10 as an example of equipment including a solid-liquid separation tank.
(Sewage treatment equipment 10)
An example of the sewage treatment equipment 10 includes a pre-sedimentation tank 11, a concentration tank 12, a storage tank 13, a dehydrator 14, a container 15, an aeration tank 16, a post-sedimentation tank 17, a pump 18, and equipment control. A device 19 is provided.
The pre-sedimentation tank 11 is connected to the aeration tank 16 through a flow path P1. Raw water is introduced into the pre-sedimentation tank 11 . The pre-sedimentation tank 11 settles and separates initial settled sludge (drawn sludge) from introduced raw water. The water to be treated after sedimentation and separation is introduced into the aeration tank 16 via the flow path P1.
The aeration tank 16 is connected to the post-sedimentation tank 17 via a flow path P2. The aeration tank 16 performs aerobic treatment on the water to be treated introduced from the pre-sedimentation tank 11 by aerating air from an aeration pipe. The water to be treated that has been aerobically treated in the aeration tank 16 is introduced into the post-sedimentation tank 17 via the flow path P2.

The post-settling tank 17 is connected to the pump 18 through a flow path P3. Pump 18 is connected to flow path P4. The flow path P4 is branched into a flow path P5 and a flow path P6. The flow path P5 is connected to the concentration tank 12, and the flow path P6 is connected to the aeration tank 16. The post-settling tank 17 separates the water to be treated introduced from the aeration tank 16 into settled sludge (drawn sludge) and supernatant water. The supernatant water in the post-sedimentation tank 17 is discharged outside the sewage treatment facility 10 as discharge water. Further, a part of the sludge settled in the post-settling tank 17 is introduced into the thickening tank 12 as surplus sludge via the pump 18, the flow path P4, and the flow path P5. The remainder of the sludge settled in the post-settling tank 17 is returned to the aeration tank 16 as return sludge via the flow path P4 and piping P6. By controlling the pump 18 by the equipment control device 19, a predetermined amount of sludge from among the sludge precipitated in the post-settling tank 17 is introduced into the flow path P4.
Further, the pre-precipitation tank 11 is connected to the concentration tank 12 through a flow path P7. The drawn sludge is introduced into the thickening tank 12 from the pre-sedimentation tank 11 via the flow path P7. The concentration tank 12 is connected to the pre-precipitation tank 11 through a flow path P8, and connected to the storage tank 13 through a flow path P9.

In the thickening tank 12, the introduced sludge is separated by gravity into supernatant water and thickened sludge. The supernatant water is returned to the pre-sedimentation tank 11 via the flow path P8. The thickened sludge is extracted from the bottom of the thickening tank 12 and introduced into the storage tank 13 via the flow path P9.
The storage tank 13 is connected to a dehydrator 14 through a flow path P10. The storage tank 13 temporarily stores the thickened sludge introduced from the thickening tank 12. The thickened sludge stored in the thickening tank 12 is introduced into the dehydrator 14. The dehydrator 14 is connected to the container 15 by a conveyor P11. The dehydrator 14 dehydrates the thickened sludge introduced from the storage tank 13. The dehydrated cake produced by the dehydration process is introduced into the container 15 via the conveyor P11. The container 15 accommodates the dehydrated cake introduced by the dehydrator 14, and carries out the accommodated dehydrated cake.

(Monitoring system 100)
The monitoring system 100 includes an ultrasonic sensor 20, a data processing device 30, a gateway device 31, an information processing device 40, a terminal device 45, and a monitoring device 50.
The gateway device 31, the information processing device 40, the terminal device 45, and the monitoring device 50 are connected via a network NW. The network NW is a wireless or wired communication network. This network NW includes the Internet, an intranet, and the like. Specifically, the network NW is an information communication network configured by a WAN (Wide Area Network), a LAN (Local Area Network), and the like. This WAN includes, for example, a mobile phone network, a PHS (Personal Handy-phone System) network, a PSTN (Public Switched Telephone Network), a dedicated communication line network, and a VPN (Virtual Private Network). .

The ultrasonic sensor 20 transmits ultrasonic waves into water by applying a pulse voltage to an ultrasonic transducer from an ultrasonic transmitting circuit. In this embodiment, as an example, a case will be continued in which the ultrasonic sensor 20 is installed in the post-settling tank 17 and transmits ultrasonic waves into the inside of the post-settling tank. Here, the voltage [V] is converted into sound pressure [dB]. Ultrasonic waves are generated by the tiny vibrations of the vibrator. An example of a vibrator is a ceramic element. When the transducer receives a reflected wave that is reflected back from something in the water, an electromotive force is generated, and the ultrasonic receiving circuit detects the voltage.
FIG. 2 is a diagram showing an example of an ultrasonic sensor. As shown in FIG. 2, the ultrasonic sensor 20 includes an oscillation (transmission) section 21 that is a transducer 2 for transmitting, and a receiving section 22 that is a transducer for receiving. In FIG. 2, as an example, a case will be described in which the ultrasonic sensor 20 includes two vibrators, an oscillating section 21 and a receiving section 22. However, the transmitting transducer and the receiving transducer may be realized by one transducer.
The ultrasonic sensor 20 is installed at a predetermined height 27 of a post-settling tank 17 (hereinafter also referred to as a treatment tank 25) that stores a suspended matter accumulation layer 23 such as sludge and supernatant water 24 of the suspended matter accumulation layer 23. by a mechanism (not shown). Since the depth remains unchanged by installing the ultrasonic sensor 20 in the processing tank 25 for measurement, the depth is not changed. For example, when the depth of a tank is 5 m, an image database can be created by dividing 200 dots into 5 m. In this case, each pixel is 2.5 cm, and the display resolution is 2.5 cm. For example, there may be a setting item for inputting the depth when setting the measurement, and data in the depth direction may be thinned out based on this setting value. All the data may be stored so that a certain part can be enlarged, and the display may be thinned out or partially enlarged (full display) in accordance with an instruction.
The oscillator 21 provides an electric signal generated by a signal generation circuit (not shown) to the ultrasonic transducer and transmits it toward the lower surface of the processing tank 25 .

The ultrasonic waves transmitted by the oscillator 21 are reflected by the interface 26 between the suspended matter accumulation layer 23 and its supernatant water 24, the suspended matter under the interface 26, the bottom of the processing tank 25, etc. The reflected waves return one after another with a time difference (arrival time) proportional to the position (distance, depth) of the reflected object. The strength of the reflected wave is related to the properties (≈density) of the object, and this information is expressed in sound pressure (dB). The reflected wave is received by the receiving section 22. In the receiving section 22, the sound pressure causes the vibrator to vibrate, and a voltage corresponding to the strength of the vibrator is generated. Here, the sound pressure [dB] is converted into voltage [V]. The receiving section 22 outputs the received signal to the data processing device 30. The data processing device 30 receives the received signal output by the receiving section 22 and converts the received signal into image data.

FIG. 3 is a diagram showing an example of a data processing device of the monitoring system according to the present embodiment. In the example shown in FIG. 3, a case will be described in which a transmitting transducer and a receiving transducer are implemented by one transducer.
The data processing device 30 includes an ultrasound transmission/reception circuit 32, a data conversion circuit 33, a data calculation section 34, and an image data storage section 35.
The ultrasonic transmitter/receiver circuit 32 generates an electric signal for transmitting ultrasonic waves, and outputs the generated electric signal to the ultrasonic sensor 20 . The ultrasonic transmitter/receiver circuit 32 receives the electrical signal output by the ultrasonic sensor 20. The ultrasonic transmitter/receiver circuit 32 outputs the received electrical signal to the data converter circuit 33 .
The data conversion circuit 33 acquires the electrical signal output by the ultrasonic transmission/reception circuit 32. The data conversion circuit 33 amplifies the acquired electrical signal. The data conversion circuit 33 performs masking processing on the amplified electrical signal. The data conversion circuit 33 converts the amplified electrical signal into a digital signal by digitally processing the signal intensity based on the result of masking processing. For example, the data conversion circuit 33 converts the electrical signal into, for example, 256 tones based on the signal strength. The data conversion circuit 33 outputs a digital signal to the data calculation section 34.

The data calculation unit 34 acquires the digital signal output from the data conversion circuit 33. Further, the data calculation unit 34 acquires temperature data from a thermocouple (not shown) installed in the ultrasonic sensor 20. The data calculation unit 34 uses the acquired temperature data to perform correction calculations on the speed of sound traveling in water. Further, the data calculation unit 34 expresses the position (=distance) of the signal as a function of time based on the acquired digital signal. Furthermore, the data calculation unit 34 calculates a change in reflection intensity (signal intensity) over time after the ultrasonic sensor 20 transmits the ultrasonic wave, based on the acquired digital signal. The data calculation unit 34 calculates the position (=distance) of the signal as a function of time and the change in reflection intensity (signal intensity) over time after transmitting the ultrasound. , associating signal strength with location information. The data calculation unit 34 temporarily stores (stocks) signal strength and position information in association with each other.
The data calculation unit 34 calculates the position (depth) of the interface 26 between the suspended matter accumulation layer 23 and the supernatant water 24. For example, the data calculation unit 34 calculates, based on the elapsed time of the reflected intensity of ultrasonic waves after the ultrasonic sensor 20 transmits the ultrasonic waves, up to the timing when the reflected intensity suddenly increases beyond a predetermined threshold. Derive the elapsed time. The data calculation unit 34 calculates the distance to the interface 26 (the position of the interface 26) based on the derived time passage. The data calculation unit 34 outputs numerical digital data at the interface level to the image data storage unit 35.

The data calculation unit 34 outputs the stored information associating the signal strength and position information and digital data of interface level numerical values to the image data storage unit 35. Here, if the interface level cannot be determined, the data calculation section 34 may output information indicating a determination error to the image data storage section 35. The data calculation unit 34 may output to the image data storage unit 35 information that associates signal strength with position information, and information that associates digital data of numerical values at the interface level with temperature data.
FIG. 4 is a diagram illustrating an example of the operation of the monitoring system according to this embodiment. FIG. 4 shows an example of data output from the data calculation section 34 to the image data storage section 35. An example of data output from the data calculation section 34 to the image data storage section 35 is expressed as an instantaneous value. FIG. 4 shows a two-dimensional representation of the instantaneous values output from the data calculation unit 34 to the image data storage unit 35.
In the data processing device 30, the data calculation unit 34 transmits the digital signal to the monitoring device 50 via the gateway device 31. Returning to FIG. 1, the explanation will be continued.

(Monitoring device 50)
The monitoring device 50 is realized by a device such as a personal computer, a server, or an industrial computer. The monitoring device 50 includes a communication device 51, a recording device 52, an information processing unit 53, and bus lines such as an address bus and a data bus for electrically connecting each component as shown in FIG. It is equipped with BL.
The communication device 51 is realized by a communication module. The communication device 51 communicates with other devices such as the data processing device 30 and the information processing device 40 via the network NW. The communication device 51 receives the digital signal transmitted by the data processing device 30. For example, the communication device 51 receives data measured during a predetermined period of time in the past at predetermined time intervals.
Specifically, the communication device 51 receives data for the past hour once every hour. The communication device 51 also receives a monitoring image request sent by the terminal device 45 for requesting a monitoring image. Here, the monitoring image is an image showing changes in reflection intensity (reception intensity) over time after ultrasonic waves are transmitted to the solid-liquid separation tank. The communication device 51 transmits the monitoring image response output by the information processing unit 53 to the terminal device 45 in response to the received monitoring image request. The communication device 51 receives the diagnosis result notification sent by the terminal device 45 in response to the sent monitoring image response. The diagnosis result notification includes information indicating the monitoring image and information indicating the diagnosis result of the internal state of the solid-liquid separation tank.
Further, the communication device 51 receives the in-tank state information request transmitted by the information processing device 40. The communication device 51 transmits the tank state information response outputted by the information processing section 53 to the information processing device 40 . The communication device 51 acquires the status notification information output by the information processing unit 53 and transmits the acquired status notification information to the information processing device 40 .

The recording device 52 is realized by, for example, a RAM, a ROM, an HDD, a flash memory, or a hybrid storage device that is a combination of two or more of these. The recording device 52 stores a program (monitoring application) executed by the monitoring device 50. The recording device 52 also stores pixel data output from the information processing section 53.
The recording device 52 includes training data of diagnosis results that associates information indicating a supernatant water image with a diagnosis result of the interior of the solid-liquid separation tank (inside the tank) based on the supernatant water image, and data based on the training data of the diagnosis results. , a learning model of diagnosis results obtained by machine learning of the relationship between the supernatant water image and the internal state of the solid-liquid separation tank is stored. Here, the monitoring image and the supernatant water image included in the monitoring image will be explained.
FIG. 5 shows an example of a monitoring image. The data processing device 30 transmits ultrasonic waves from the ultrasonic sensor 20 downward underwater (=towards the bottom), and receives reflected waves that hit and return to objects existing within the range in which the ultrasonic waves travel. Convert reflected waves into digital signals.
The information processing unit 53 acquires the digital signal transmitted by the data processing device 30. Based on the acquired digital signal, the information processing unit 53 converts the intensity of the reflected wave into a color tone, converts the time until the reflected wave returns to a distance, provides it as position information, and matches the color tone and distance. Continuously plot the distance from the sensor (=water depth) in the vertical direction and the time course (=time series) in the horizontal direction. This continuous plot is the monitoring image. As shown in FIG. 5, images corresponding to the bottom surface of the solid-liquid separation tank, the rake, the sludge accumulation layer, the sludge interface, and the supernatant water are seen in the monitoring image. The supernatant water image is an image of supernatant water included in the monitoring image. To explain using FIG. 2, the monitoring image is the measurement result of the suspended matter deposit layer 23 and the supernatant water 24 by the ultrasonic sensor 20, whereas the supernatant water image is the measurement result of only the supernatant water 24 by the ultrasonic sensor 20. This is the result.
FIG. 6 is a diagram showing an example of teacher data. FIG. 6 shows the teaching data of the diagnosis results. The training data of the diagnosis result is data that associates a supernatant water image with a diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image. In this embodiment, as an example, one of "normal", "abnormal", and "unwell" is associated with each of the plurality of supernatant water images as a diagnostic result. In the description of FIG. 6, a monitoring image will be used for convenience. In FIG. 6, (1) is diagnosed as normal because the supernatant water has a sufficient depth. (2) is diagnosed as abnormal because the depth of the supernatant water is shallow. Case (3) is diagnosed as malfunctioning because accumulated sludge is seen floating up in the supernatant water. Returning to FIG. 1, the explanation will be continued.

The information processing unit 53 functions as, for example, a graphic generation unit 54, a current status determination unit 55, and a learning unit 56.
The graphic generator 54 acquires the digital signal received by the communication device 51. The graphic converting unit 54 converts the values of the acquired digital signals into pixel data. The graphic converting unit 54 causes the recording device 52 to store the pixel data after converting the digital signal.
The graphic generation unit 54 acquires the supernatant water image request received by the communication device 51. The graphic generation unit 54 acquires pixel data stored in the recording device 52 based on the acquired supernatant water image request. The graphic generator 54 creates an image of supernatant water included in the monitoring image based on the acquired pixel data. The graphic generation unit 54 creates a supernatant water image response that includes information indicating the created supernatant water image and is addressed to the information processing device 40 . The graphic generation unit 54 outputs the created supernatant water image response to the communication device 51.
The graphic generation unit 54 detects a sludge interface, which is an interface between supernatant water and a sludge accumulation layer, from a monitoring image, for example, and creates pixel data vertically upward from the sludge interface (in a direction where water depth becomes shallower) as a supernatant water image. The sludge interface is the interface 26 calculated by the data calculation unit 34. The graphic section 54 may set the position of the interface 26 calculated by the data calculation section 34 as the sludge interface. The graphic generation unit 54 acquires the tank internal state information request received by the communication device 51. The graphic generating unit 54 acquires pixel data stored in the recording device 52 based on the acquired tank state information request, and creates a supernatant water image based on the acquired pixel data. The graphic generation unit 54 creates an in-tank state information response that includes information indicating the created supernatant water image and is addressed to the information processing device 40 . The graphic generator 54 outputs the created tank state information response to the communication device 51.

The current state determining unit 55 acquires the pixel data stored in the recording device 52, and creates a supernatant water image based on the acquired pixel data. The current status determination unit 55 acquires the learning model of the diagnosis result stored in the recording device 52. The current state determining unit 55 determines the internal state of the solid-liquid separation tank in the created supernatant water image based on the learning model of the acquired diagnosis result. If the determination result of the internal state of the solid-liquid separation tank is poor or abnormal, the current status determination unit 55 sends the information processing device 40 containing information indicating the determination result of the internal state of the solid-liquid separation tank as a destination. Create status notification information. The current status determination unit 55 outputs the created status notification information to the communication device 51. The communication device 51 acquires the status notification information output by the current status determination unit 55 and transmits the acquired status notification information to the information processing device 40 .
When creating a supernatant water image, the current status determination unit 55 may use the measured data as is, or may include data measured over a long period of time in a limited display width by thinning out the data. good. By including data measured over a long period of time in a limited display width, changes over a longer period of time can be monitored. If it is a still image, pixel data can be picked up at any appropriate interval and switched and displayed, but in this embodiment, measurement is always performed and new data is added, so pixel data can be picked up and displayed at any appropriate interval. If pixel data is picked up at regular intervals and switched for display, there is a risk that data processing will be delayed or hindered, and if measurement becomes unstable due to image display, it would be a waste of money. Therefore, in this embodiment, several preset display time widths are prepared, and data storage areas for time widths corresponding to each of the plurality of display time widths are created. In this embodiment, an interval at which new data is added is specified, and an image database (data storage area (address)) corresponding to each of a plurality of intervals is created.

An operation to switch the display is performed on the monitoring device 50, and a display time width is selected. The current status determination unit 55 acquires data from the database corresponding to the selected time display width, and creates a supernatant water image using the acquired data. If the time display width is switched, data is acquired from the database corresponding to the selected time display width, and a supernatant water image is created using the acquired data. With this configuration, smooth switching can be performed without processing the data in the database in which the data is stored and without the time lag of creating a supernatant water image.
The learning unit 56 acquires the diagnosis result notification received by the communication device 51, and obtains information indicating a supernatant water image included in the acquired diagnosis result notification and the state of the inside of the solid-liquid separation tank (inside the tank) based on the supernatant water image. The recording device 52 stores the teacher data of the diagnosis result in association with the diagnosis result of the diagnosis result. The learning unit 56 acquires training data of the diagnosis results stored in the recording device 52. The learning unit 56 performs machine learning (supervised learning) on the supernatant water image and the diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, based on the acquired diagnostic result training data. A learning model for diagnosis results that correlates clear water images and the internal state of the solid-liquid separation tank is generated. For example, the learning unit 56 recognizes the supernatant water image using a convolutional neural network (CNN). Based on the information indicating the supernatant water image, the learning model of the diagnosis result classifies the supernatant water image as one of normal, malfunctioning, and abnormal as the internal state of the solid-liquid separation tank. The learning unit 56 causes the recording device 52 to store the generated learning model of the diagnosis result.
All or part of the information processing unit 53 is a functional unit (hereinafter referred to as a software function) realized by a processor such as a CPU (Central Processing Unit) executing a program such as a monitoring application stored in the recording device 52. ). Note that all or part of the information processing unit 53 may be realized by hardware such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), or FPGA (Field-Programmable Gate Array), or may be realized by software functions. It may also be realized by a combination of parts and hardware.

(Information processing device 40)
The information processing device 40 is realized by a device such as a personal computer, a server, or an industrial computer. An example of the information processing device 40 is installed in a monitoring center that remotely monitors the sewage treatment facility 10.
When the information processing device 40 receives the status information notification transmitted by the monitoring device 50, the information processing device 40 displays the determination result of the solid-liquid separation tank included in the received status information notification.
The information processing device 40 also requests tank internal status information addressed to the monitoring device 50, including information requesting the internal status of the tank, based on the operator's operation to acquire status information in the solid-liquid separation tank. Create. The information processing device 40 transmits the created tank state information request to the communication device 51.
The information processing device 40 receives the tank state information response sent by the monitoring device 50 in response to the tank state information request. The information processing device 40 acquires the supernatant water image included in the received tank state information response. The information processing device 40 displays the acquired supernatant water image.

(Terminal device 45)
The terminal device 45 is realized by a device such as a personal computer, a server, or an industrial computer. An example of the terminal device 45 is installed in a monitoring center that monitors the sewage treatment facility 10.
When diagnosing the internal state of the solid-liquid separation tank, the user operates the terminal device 45 to create a supernatant water image request addressed to the monitoring device 50 that includes information requesting a supernatant water image. . The terminal device 45 creates a supernatant water image request based on the user's operation. The terminal device 45 transmits the created supernatant water image request to the monitoring device 50.
The terminal device 45 receives the supernatant water image response sent by the monitoring device 50 in response to the supernatant water image request sent to the monitoring device 50 . The terminal device 45 displays the monitoring image included in the supernatant water image response. The user refers to the supernatant water image displayed on the terminal device 45 and diagnoses the internal state of the solid-liquid separation tank included in the supernatant water image.
By operating the terminal device 45, the user causes a diagnosis result notification addressed to the monitoring device 50 to be created, which includes information indicating the supernatant water image and the diagnosis result of the internal state of the solid-liquid separation tank. The terminal device 45 creates a diagnosis result notification based on the user's operation. The terminal device 45 transmits the created diagnosis result notification to the monitoring device 50.

(Operation of monitoring system)
FIG. 7 is a diagram showing an example 1 of the operation of the monitoring system according to the present embodiment. Referring to FIG. 7, the monitoring device 50 accumulates the diagnosis results of the internal state of the solid-liquid separation tank included in the diagnosis result notification sent by the terminal device 45, and monitors the accumulated internal state of the solid-liquid separation tank. A process of performing machine learning based on diagnosis results and generating a learning model of the diagnosis results will be described.
(Step S1-1)
In the data processing device 30 , the ultrasonic transmitter/receiver circuit 32 generates an electric signal for transmitting ultrasonic waves, and outputs the generated electric signal to the ultrasonic sensor 20 .
(Step S2-1)
In the data processing device 30, the ultrasonic transmitter/receiver circuit 32 receives the electrical signal output by the ultrasonic sensor 20.
(Step S3-1)
In the data processing device 30 , the ultrasonic transmission/reception circuit 32 outputs the received electrical signal to the data conversion circuit 33 . The data conversion circuit 33 acquires the electrical signal output by the ultrasonic transmission/reception circuit 32. The data conversion circuit 33 amplifies the acquired electrical signal. The data conversion circuit 33 performs masking processing on the amplified electrical signal. The data conversion circuit 33 converts the amplified electric signal into a digital signal by digitally processing the signal intensity based on the result of masking processing. The data calculation unit 34 acquires a digital signal from the data conversion circuit 33, and performs temperature correction calculation related to position (distance) information and interface level determination calculation on the acquired digital signal.
(Step S4-1)
In the data processing device 30, the data calculation unit 34 transmits a digital signal on which a temperature correction calculation related to position (distance) information and an interface level determination calculation have been performed to the monitoring device 50 via the gateway device 31.
(Step S5-1)
In the monitoring device 50, the communication device 51 receives the digital signal transmitted by the data processing device 30. The graphic generator 54 acquires the digital signal received by the communication device 51. The graphic converting unit 54 converts the values of the acquired digital signals into pixel data.
(Step S6-1)
In the monitoring device 50, the graphic converting unit 54 causes the recording device 52 to store the pixel data converted into digital signals.
(Step S7-1)
The terminal device 45 creates a supernatant water image request.

(Step S8-1)
The terminal device 45 transmits the created supernatant water image request to the monitoring device 50.
(Step S9-1)
In the monitoring device 50, the communication device 51 receives the supernatant water image request transmitted by the terminal device 45. The graphic generation unit 54 acquires the supernatant water image request received by the communication device 51. The graphic generation unit 54 acquires pixel data stored in the recording device 52 based on the acquired supernatant water image request. The graphic generator 54 creates a supernatant water image based on the acquired pixel data. The graphic generation unit 54 creates a clear water image response addressed to the terminal device 45 that includes information indicating the created clear water image.
(Step S10-1)
In the monitoring device 50, the graphic generation unit 54 outputs the created supernatant water image response to the communication device 51. The communication device 51 acquires the supernatant water image response output by the graphic converting unit 54 and transmits the obtained supernatant water image response to the terminal device 45 .
(Step S11-1)
The terminal device 45 receives the supernatant water image response transmitted by the monitoring device 50. The terminal device 45 displays the supernatant water image by processing the information indicating the supernatant water image included in the received supernatant water image response. The terminal device 45 creates a diagnosis result notification including information indicating the supernatant water image and the result of diagnosing the supernatant water image.
(Step S12-1)
The terminal device 45 transmits the created diagnosis result notification to the monitoring device 50.
(Step S13-1)
In the monitoring device 50, the communication device 51 receives the diagnosis result notification sent by the terminal device 45. The learning unit 56 acquires the diagnosis result notification received by the communication device 51, and obtains information indicating a supernatant water image included in the acquired diagnosis result notification and the state of the inside of the solid-liquid separation tank (inside the tank) based on the supernatant water image. The recording device 52 stores the teacher data of the diagnosis result in association with the diagnosis result of the diagnosis result.
(Step S14-1)
In the monitoring device 50, the learning unit 56 acquires training data of the diagnosis results stored in the recording device 52. The learning unit 56 performs machine learning on the supernatant water image and the diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, based on the training data of the acquired diagnosis result. A learning model of the diagnosis results is generated in relation to the internal state of the separation tank.
(Step S15-1)
In the monitoring device 50, the learning unit 56 causes the recording device 52 to store the generated learning model of the diagnosis result.

Note that the diagnosis result notification may be a diagnosis result based on a monitoring image instead of a supernatant water image. That is, in step S7-1, the terminal device 45 creates a monitoring image request, in step S8-1, the terminal device 45 transmits the created monitoring image request to the monitoring device 50, and in step S9-1, the monitoring device 50 An image may be created, and the monitoring device 50 may transmit a monitoring image response to the terminal device 45 in step S10-1.

FIG. 8 is a diagram showing a second example of the operation of the monitoring system according to the present embodiment. Referring to FIG. 8, monitoring device 50 acquires the digital signal transmitted by data processing device 30, and creates a supernatant water image based on the acquired digital signal. A process in which the monitoring device 50 determines the internal state of the solid-liquid separation tank based on the created supernatant water image will be described.
Since steps S1-1 to S6-1 in FIG. 7 can be applied to steps S1-2 to S6-2, the description thereof will be omitted here.
(Step S7-2)
In the monitoring device 50, the current state determination unit 55 acquires the pixel data stored in the recording device 52, and creates a supernatant water image based on the acquired pixel data.
(Step S8-2)
In the monitoring device 50, the current state determining unit 55 acquires the learning model of the diagnosis result stored in the recording device 52.
(Step S9-2)
In the monitoring device 50, the current state determining unit 55 determines the internal state of the solid-liquid separation tank in the created supernatant water image based on the learning model of the acquired diagnosis result.
(Step S10-2)
In the monitoring device 50, the current state determination unit 55 determines whether the determination result of the internal state of the solid-liquid separation tank is malfunctioning or abnormal. The current state determination unit 55 terminates when the determination result of the internal state of the solid-liquid separation tank is neither malfunction nor abnormal, that is, it is determined to be normal.
(Step S11-2)
In the monitoring device 50, when the current state determination unit 55 determines that the internal state of the solid-liquid separation tank is malfunctioning or abnormal, the current status determination unit 55 transmits information indicating the determination result of the internal state of the solid-liquid separation tank. Create status notification information with the information processing device 40 as the destination.
(Step S12-2)
In the monitoring device 50, the current status determining unit 55 outputs the created status notification information to the communication device 51. The communication device 51 acquires the status notification information output by the current status determination unit 55 and transmits the acquired status notification information to the information processing device 40 .

Note that the monitoring device 50 creates a supernatant water image in step S7-2, but this is just an example. For example, the monitoring device 50 may create a monitoring image based on pixel data, and focus on the supernatant water image by ignoring the portion deeper than the sludge interface in subsequent steps.

FIG. 9 is a diagram showing a third example of the operation of the monitoring system according to the present embodiment. With reference to FIG. 9, a process in which the monitoring device 50 transmits information indicating a supernatant water image based on the tank internal state information request transmitted by the information processing device 40 will be described.
Since steps S1-1 to S6-1 in FIG. 7 can be applied to steps S1-3 to S6-3, the description thereof will be omitted here.
(Step S7-3)
The information processing device 40 creates an in-tank state information request based on the user's operation.
(Step S8-3)
The information processing device 40 transmits the created tank state information request to the monitoring device 50.
(Step S9-3)
In the monitoring device 50, the communication device 51 receives the tank state information request transmitted by the information processing device 40. The graphic generation unit 54 acquires the tank internal state information request received by the communication device 51. The graphic generating unit 54 acquires pixel data stored in the recording device 52 based on the acquired tank state information request, and creates a supernatant water image based on the acquired pixel data.
(Step S10-3)
In the monitoring device 50, the graphic creation unit 54 creates an in-tank state information response addressed to the information processing device 40, which includes information indicating the created supernatant water image.
(Step S11-3)
In the monitoring device 50 , the graphic section 54 outputs the created tank state information response to the communication device 51 . The communication device 51 acquires the in-tank state information response outputted by the graphic generator 54 and transmits the obtained in-tank state information response to the information processing device 40 .
After step S11-3, the information processing device 40 receives the tank state information response transmitted by the monitoring device 50, and acquires information indicating the supernatant water image included in the received tank state information response. The information processing device 40 displays the supernatant water image by performing image processing on the information indicating the obtained supernatant water image. With this configuration, the user of the information processing device 40 can check the internal state of the solid-liquid separation tank.
Note that the monitoring device 50 may create a monitoring image instead of the supernatant water image, the tank condition information response may include information indicating the monitoring image, and the information processing device 40 may create a monitoring image instead of the supernatant water image. A monitoring image may be displayed by performing image processing on the information.

In the embodiment described above, as an example, a case has been described in which the ultrasonic sensor 20 is installed in the post-settling tank 17 and the internal state of the post-settling tank 17 is determined, but the present invention is not limited to this example. For example, an ultrasonic sensor 20 may be installed in the pre-precipitation tank 11 to determine the internal state of the pre-precipitation tank 11, or an ultrasonic sensor 20 may be installed in the concentration tank 12 to determine the internal state of the concentration tank 12. may be determined. That is, the ultrasonic sensor 20 is installed in at least one of the post-sedimentation tank 17, the pre-sedimentation tank 11, and the concentration tank 12 to determine the internal state.
In the embodiment described above, a case has been described in which the monitoring system 100 is connected to one sewage treatment facility 10, but the present invention is not limited to this example. For example, the monitoring system 100 may be connected to a plurality of sewage treatment facilities 10, or the plurality of monitoring systems 100 may be connected to one sewage treatment facility 10. If the monitoring system 100 is connected to multiple sewage treatment facilities 10, if an unsteady state that has never been experienced occurs in equipment A, it will be possible to connect the monitoring system 100 to a plurality of sewage treatment facilities 10. If so, there is a high possibility that it will be judged as "abnormal" and output. In other words, since the monitoring device 50 is capable of learning more, it is possible to increase the number of cases that can be used for determination. Therefore, it is possible to increase the number of unsteady states that can be determined to be abnormal or malfunctioning.
In the embodiment described above, a case has been described in which the monitoring device 50 performs machine learning, but the present invention is not limited to this example. For example, a device that performs machine learning may be implemented as a device different from the monitoring device 50. In this case, the learning device uses the supernatant water image, which is an image representing the inside of a solid-liquid separation tank for solid-liquid separation of wastewater, and the diagnosis result based on the supernatant water image inside the solid-liquid separation tank to the monitoring device 50. Get from. The learning device generates a diagnosis result representing the relationship between the supernatant water image and the internal state of the solid-liquid separation tank based on the acquired supernatant water image and the diagnosis result based on the supernatant water image of the internal state of the solid-liquid separation tank. It has a learning section that generates a learning model by machine learning (supervised machine learning).
In the embodiment described above, a case has been described in which it is determined whether the determination result of the internal state of the solid-liquid separation tank is normal, abnormal, or malfunctioning based on the supernatant water image, but the present invention is limited to this example. do not have. For example, it may be determined whether the internal state of the solid-liquid separation tank is normal or abnormal based on the supernatant water image, or it may be determined whether the internal state of the solid-liquid separation tank is normal or abnormal based on the supernatant water image. The determination result of the state may be classified into four or more types.

In the embodiment described above, the current state determination unit 55 compares the created supernatant water image with past supernatant water images in a normal state, and if it is determined that there is a change, the current state determination unit 55 compares the created supernatant water image with the past normal state supernatant water image, and if it is determined that there is a change, the current state determination unit 55 compares the created supernatant water image with the past normal state supernatant water image, and if it is determined that there is a change, The internal state of the solid-liquid separation tank may be determined using the learning model of the diagnosis results.
In the embodiment described above, the data processing device 30 may include the display switching operation section 36 and the image data display section 37.
FIG. 10 is a diagram showing another example of the data processing device according to this embodiment. An example of the display switching operation section 36 is configured by a display switching button. An example of the image data display section 37 is a display. The image data display section 37 may display the measured data as is, or may display long-term data in a limited display width by thinning out the measured data. By displaying long-term data in a limited display width, it is possible to monitor long-term changes over time.
If a still image is to be displayed on the image data display section 37, pixel data can be picked up at any appropriate interval and switched and displayed, but as in this embodiment, measurement is always performed and new data is displayed. If more and more pixels are added, there is a risk that data processing will be delayed or hindered when pixel data is picked up and switched for display, and if measurement becomes unstable due to image display, it would be a waste of money.
For this reason, in this embodiment, several preset display time widths are prepared, a data storage area for the time width corresponding to each of the plurality of display time widths is created, and the interval at which new data is added is determined. , and create an image database corresponding to each of the plurality of display time widths. Suppose that the image data display section 37 is composed of 200 pixels in the vertical direction (=depth direction) and 240 pixels in the horizontal direction (=time series), and if data is stored every second, the horizontal The data will be displayed for 4 minutes in the direction, and if stored every 10 seconds, the data will be displayed for 40 minutes in the horizontal direction. By deleting the oldest data at the same time as new data is added, it can be operated with a limited data area. Furthermore, by providing an area for stocking 240 data or more data required for the display width and scrolling the display, changes from the past can be observed as if they were a moving image. In this embodiment, these two types of data storage and display are possible.

In the embodiment described above, the image data storage section 35 of the data processing device 30 may be accessed from an external terminal and the data stored in the image data storage section 35 may be retrieved.
In the embodiment described above, the data calculation unit 34 of the data processing device 30 may be accessed from an external terminal. In this case, the data stored in the data calculation section 34 may be extracted and output to the external terminal in response to a command from the external terminal. With this configuration, the data output by the data calculation unit 34 can be displayed on the external terminal, so online monitoring is possible.
Further, in this case, the latest data may be output from the data calculation unit 34 to the external terminal in response to a command from the external terminal. The interval at which data is output can be set on an external terminal. With this configuration, data can be displayed sequentially on the external terminal, allowing remote live image monitoring. Specifically, the unique identification number (=password) given to the data calculation unit 34 is checked sequentially between the data calculation unit and the external terminal using dedicated software installed on the external terminal. Since one-to-one communication is possible between the external terminal and the data calculation unit, it is possible to prevent data extraction by eavesdropping by installing a signal distributor or the like.

In the embodiment described above, the data calculation unit 34 of the data processing device 30 may be configured to transmit data to an external terminal. The data calculation unit 34 may transmit data to an external terminal based on settings for transmitting data. With this configuration, the external terminal can be used for remote monitoring of the sewage treatment facility 10.
In the embodiment described above, the data calculation unit 34 of the data processing device 30 may be configured to output data to an external data server or recording medium. The data calculation unit 34 outputs data to an external data server or recording medium based on the settings. The external data server creates a database based on the data output by the data calculation unit 34. The external data server may display images or process data based on the created database.
In the embodiment described above, when the data calculation unit 34 of the data processing device 30 transmits data to an external terminal, the data may be transmitted according to the RS232C standard, for example. In addition, when the data calculation unit 34 of the data processing device 30 transmits data to an external terminal, it may be transmitted as is between the external terminal, or a signal converter may be provided and the data may be transmitted using the RS422, RS485 standard or USB ( It may also be converted into a transmission protocol such as Universal Serial Bus (Universal Serial Bus), LAN, or optical fiber for transmission. Further, data may be sent from the external terminal to the server regularly or irregularly. In this case, the central monitoring device may request data from an external terminal (such as a small PC) and cause the external terminal to output the data.
In this case, the external terminal may have the functions of the monitoring device 50 described above. The external terminal may acquire the data output by the data calculation unit 34, determine the internal state of the solid-liquid separation tank based on the supernatant water image based on the acquired data, and output the determination result to the server. . Further, the server may have the function of the current status determination unit 55 of the monitoring device described above. The external terminal acquires the data output by the data calculation unit 34 and transmits the acquired data to the server. The server acquires the data transmitted by the external device, and determines the internal state of the solid-liquid separation tank based on the supernatant water image based on the acquired data.

According to the monitoring system 100 according to the present embodiment, the monitoring device 50 displays a supernatant water image, which is an image representing supernatant water inside a solid-liquid separation tank for solid-liquid separation of wastewater, and an inside of the solid-liquid separation tank. Based on the diagnosis result based on the supernatant water image, the first learning model is used as a learning model for the diagnosis result that has learned the relationship between the supernatant water image and the internal state of the solid-liquid separation tank. A determination unit as a current status determination unit 55 that determines the internal state of a solid-liquid separation tank from a supernatant water image representing the supernatant water inside a certain solid-liquid separation tank, and the supernatant water of the solid-liquid separation tank that is the subject of diagnosis. and an output section that outputs information specifying the internal state of the solid-liquid separation tank determined by the determination section using the image and the first learning model.
With this configuration, the monitoring device 50 uses the first learning model that has learned the relationship between the supernatant water image and the diagnosis results inside the solid-liquid separation tank to determine the diagnosis of the solid-liquid separation tank that is the target of diagnosis. Since the internal state of the solid-liquid separation tank can be determined from the supernatant water image representing the internal supernatant water, the internal state of the solid-liquid separation tank can be monitored. Using the first learning model, it is possible to judge the internal state of the solid-liquid separation tank from a supernatant water image representing the supernatant water inside the solid-liquid separation tank, which is the target of diagnosis. Compared to the case of diagnosing the inside of a separation tank, no human experience is required, and variations in diagnostic results can be reduced. In addition, when a person diagnoses the inside of a solid-liquid separation tank based on experience, the diagnosis is mainly made by looking at the supernatant water, so the monitoring device 50 monitors the supernatant water and sludge accumulation in the solid-liquid separation tank. It is possible to perform a diagnosis closer to that performed by a human than diagnosing the internal state of a solid-liquid separation tank from an image including layers.
If the system is configured as an on-site system, the dimensions and characteristics of the tank will not change, making it easy to compare the past and present, making it easy to distinguish between steady state, unsteady state, or abnormality. . By acquiring a collection of cases, the latest cases, etc. from an external source (either online or offline) and updating the acquired case collection, latest cases, etc., when an abnormality is detected, what is the state of the abnormality? It is possible to output the determination of the problem and the presentation of countermeasures even if the problem has not occurred in the past and there is no learning history. By making it possible to refer to an accessible database when an abnormality occurs, it is possible to estimate the condition and obtain countermeasures. Furthermore, it is possible to reduce errors in judgments that would not occur on site (equipment). Therefore, the risk of error determination can be reduced, and the time required for determination can also be shortened. Reduces the risk of data hacking and system attacks.

Furthermore, the diagnosis result based on the monitored image is generated based on either or both of the accumulated state of solid matter and the suspended state of solid matter included in the monitored image. With this configuration, the monitoring device 50 can perform monitoring based on either or both of the accumulated state of solids and the suspended state of solids included in the supernatant water image and the monitoring image including the supernatant water image. Using the first learning model that has learned the relationship between the generated diagnostic results, the internal state of the solid-liquid separation tank can be determined from the supernatant water image representing the supernatant water inside the solid-liquid separation tank that is the target of diagnosis. .
Further, the determination unit determines whether the internal state of the solid-liquid separation tank is normal, malfunctioning, or abnormal from the supernatant water image showing the inside of the solid-liquid separation tank that is the object of diagnosis. With this configuration, the monitoring device 50 can diagnose the supernatant water image and the diagnosis result inside the solid-liquid separation tank based on the supernatant water image and the diagnosis result based on the supernatant water image inside the solid-liquid separation tank. Using the first learning model that has learned the relationship between You can determine if there is.
Furthermore, when the determination unit determines that the internal state of the solid-liquid separation tank is either malfunctioning or abnormal, it notifies that the internal state of the solid-liquid separation tank is either malfunctioning or abnormal. It further includes a notification section. With this configuration, when it is determined that the internal state of the solid-liquid separation tank is either malfunctioning or abnormal, it is possible to confirm that the internal state of the solid-liquid separation tank is either malfunctioning or abnormal. This allows the user to be notified of the need to take action regarding the internal state of the solid-liquid separation tank.

[Modification 1 of embodiment]
(Monitoring system)
FIG. 11 is a diagram illustrating a configuration example of a monitoring system according to Modification 1 of the embodiment of the present invention. The monitoring system 100a according to the first modification of the embodiment diagnoses the state of sludge accumulation in solid-liquid separation tanks such as settling tanks and thickening tanks. In Modification 1 of the embodiment, the sewage treatment facility 10 is applied as an example of a facility including a solid-liquid separation tank, similarly to the embodiment.

(Monitoring system 100a)
The monitoring system 100a includes an ultrasonic sensor 20, a data processing device 30, a gateway device 31, an information processing device 40a, a terminal device 45a, and a monitoring device 50a.
The gateway device 31, the information processing device 40a, the terminal device 45a, and the monitoring device 50a are connected via a network NW.
In the data processing device 30, the data calculation unit 34 transmits the digital signal to the monitoring device 50a via the gateway device 31.
(Monitoring device 50a)
The monitoring device 50a is realized by a device such as a personal computer, a server, or an industrial computer. The monitoring device 50a includes a communication device 51, a recording device 52, an information processing section 53a, and bus lines such as an address bus and a data bus for electrically connecting each component as shown in FIG. It is equipped with BL.
The recording device 52 stores a program (monitoring application) executed by the monitoring device 50a. The recording device 52 also stores pixel data output by the information processing section 53a.
The recording device 52 stores training data of a diagnosis result that associates information indicating a supernatant water image with a diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, and supernatant data based on the training data of the diagnosis result. A learning model of diagnosis results obtained by machine learning of the relationship between the clear water image and the internal state of the solid-liquid separation tank is stored.
The recording device 52 stores cause teacher data in which information indicating a supernatant water image is associated with information specifying a cause resulting in a diagnostic result of the internal state of the solid-liquid separation tank based on the supernatant water image, and cause teacher data. Based on this, a learning model of the cause obtained by machine learning of the relationship between the supernatant water image and information specifying the cause of the internal state of the solid-liquid separation tank is stored.

FIG. 12 is a diagram showing an example of teacher data. FIG. 12 shows training data for diagnosis results and training data for causes. The training data of the diagnosis result is data that associates a supernatant water image with a diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image. The cause training data is data that associates a supernatant water image with information that specifies a cause that is a diagnostic result of the internal state of the solid-liquid separation tank based on the supernatant water image. In the description of FIG. 12, a monitoring image will be used for convenience.
In Modified Example 1 of the embodiment, as an example, one of "normal", "abnormal", and "unwell" is associated with each of a plurality of supernatant water images as a diagnostic result, similarly to the embodiment. Further, an estimated result of the cause of the diagnosis result is associated with each of the plurality of supernatant water images based on the diagnosis result.
In FIG. 12, (1) is diagnosed as normal because the supernatant water has a sufficient depth. If it is diagnosed as normal, the estimated cause of the diagnosis result is not stored.
(2) is diagnosed as abnormal because the depth of the supernatant water is shallow. In this case, bulking is stored as an example of the estimated cause of the diagnosis result. Bulking is a phenomenon in which the sedimentation of sludge deteriorates, making it difficult to obtain supernatant water.
Case (3) is diagnosed as malfunctioning because accumulated sludge is seen floating up in the supernatant water. In this case, as examples of the estimated results of the cause of the diagnosis result, a high sludge input speed, a large sludge input amount, and a high sludge interface are stored. Returning to FIG. 11, the explanation will be continued.

The information processing unit 53a functions as, for example, a graphic generation unit 54, a current status determination unit 55a, a learning unit 56a, and a cause determination unit 57.
The current state determination unit 55a acquires pixel data stored in the recording device 52, and creates a supernatant water image based on the acquired pixel data. The current state determination unit 55a acquires the learning model of the diagnosis result stored in the recording device 52. The current state determination unit 55a determines the internal state of the solid-liquid separation tank in the created supernatant water image based on the learning model of the acquired diagnosis result.
The learning section 56a has the following functions in addition to the functions of the learning section 56. The learning unit 56a acquires the diagnosis result notification received by the communication device 51, and obtains cause training data that associates the information indicating the supernatant water image included in the acquired diagnosis result notification with the estimated result of the cause resulting in the diagnosis result. The information is stored in the recording device 52. The learning unit 56a acquires the teacher data of the cause stored in the recording device 52. The learning unit 56a performs machine learning (supervised learning) on the supernatant water image and the result of estimating the cause, which is a diagnostic result of the internal state of the solid-liquid separation tank based on the supernatant water image, based on the acquired teacher data on the cause. By doing so, a learning model of the cause is generated that associates the supernatant water image with information specifying the cause of the internal state of the solid-liquid separation tank. For example, the learning unit 56a recognizes the supernatant water image using a convolutional neural network. Based on the information indicating the supernatant water image, the cause learning model classifies the supernatant water image into one of the information that specifies the cause of the internal state of the solid-liquid separation tank. The learning unit 56a causes the recording device 52 to store the generated learning model of the cause.

The cause determination unit 57 acquires information indicating the supernatant water image and the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55a. If the obtained determination result of the internal state of the solid-liquid separation tank is poor or abnormal, the cause determination unit 57 acquires the learning model of the cause stored in the recording device 52. The cause determining unit 57 determines information that specifies the cause of the internal state of the solid-liquid separation tank in the acquired supernatant water image based on the acquired learning model of the cause. The cause determining unit 57 generates information including information indicating the supernatant water image, information indicating the internal state of the solid-liquid separation tank, and information indicating the determination result of information specifying the cause of the internal state of the solid-liquid separation tank. Create status notification information with the processing device 40a as the destination. The cause determination unit 57 outputs the created status notification information to the communication device 51. The communication device 51 acquires the status notification information output by the cause determination unit 57, and transmits the acquired status notification information to the information processing device 40a.
All or part of the information processing unit 53a is a functional unit (hereinafter referred to as a software functional unit) that is realized by a processor such as a CPU executing a program such as a monitoring application stored in the recording device 52. be. Note that all or part of the information processing section 53a may be realized by hardware such as LSI, ASIC, or FPGA, or may be realized by a combination of a software function section and hardware.
The information processing device 40 can be applied to the information processing device 40a.

(Terminal device 45a)
The terminal device 45a is realized by a device such as a personal computer, a server, or an industrial computer. An example of the terminal device 45a is installed in a monitoring center that monitors the sewage treatment facility 10.
When diagnosing the internal state of the solid-liquid separation tank, the user operates the terminal device 45a to create a supernatant water image request addressed to the monitoring device 50a that includes information requesting a supernatant water image. . The terminal device 45a creates a supernatant water image request based on the user's operation. The terminal device 45a transmits the created supernatant water image request to the monitoring device 50a.
The terminal device 45a receives the supernatant water image response sent by the monitoring device 50a in response to the supernatant water image request sent to the monitoring device 50a. The terminal device 45a displays the supernatant water image included in the supernatant water image response. The user refers to the supernatant water image displayed by the terminal device 45a, diagnoses the internal state of the solid-liquid separation tank included in the supernatant water image, and further estimates the cause of the internal state of the solid-liquid separation tank. By operating the terminal device 45a, the user can access the monitoring device 50a, which includes information indicating a supernatant water image, a diagnosis result of the internal state of the solid-liquid separation tank, and information specifying the cause of the diagnosis result. Create a diagnosis result notification addressed to . The terminal device 45a creates a diagnosis result notification based on the user's operation. The terminal device 45a transmits the created diagnosis result notification to the monitoring device 50a.

(Operation of monitoring system)
FIG. 13 is a diagram illustrating a first example of the operation of the monitoring system according to the first modification of the embodiment. Referring to FIG. 13, the monitoring device 50a accumulates the diagnosis result of the internal state of the solid-liquid separation tank included in the diagnosis result notification sent by the terminal device 45a, and information specifying the cause of the diagnosis result. Then, machine learning is performed based on the accumulated diagnosis results of the internal state of the solid-liquid separation tank and information specifying the causes of the diagnosis results, and a learning model of the diagnosis results and a learning model of the causes are generated. The process will be explained.
Since steps S1-1 to S10-1 in FIG. 7 can be applied to steps S1-4 to S10-4, the description thereof will be omitted here.
(Step S11-4)
The terminal device 45a receives the supernatant water image response transmitted by the monitoring device 50a. The terminal device 45a displays the supernatant water image by performing image processing on information indicating the supernatant water image included in the received supernatant water image response. The terminal device 45a creates a diagnosis result notification addressed to the monitoring device 50a that includes the diagnosis result of the internal state of the solid-liquid separation tank and information specifying the cause of the diagnosis result.
(Step S12-4)
The terminal device 45a transmits the created diagnosis result notification to the monitoring device 50a.

(Step S13-4)
In the monitoring device 50a, the communication device 51 receives the diagnosis result notification transmitted by the terminal device 45a. The learning unit 56a acquires the diagnosis result notification received by the communication device 51, and acquires information indicating the supernatant water image included in the acquired diagnosis result notification, the diagnosis result of the internal state of the solid-liquid separation tank, and the diagnosis result. Obtain information that identifies the cause of the problem.
The learning unit 56a causes the recording device 52 to store training data of a diagnosis result in which information indicating the acquired supernatant water image is associated with a diagnosis result of the internal state of the solid-liquid separation tank. The learning unit 56a causes the recording device 52 to store cause teacher data in which information indicating the acquired supernatant water image is associated with information specifying a cause that is a diagnostic result of the internal state of the solid-liquid separation tank.
(Step S14-4)
In the monitoring device 50a, the learning unit 56a acquires training data of the diagnosis results stored in the recording device 52. The learning unit 56a performs machine learning on the supernatant water image and the diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, based on the training data of the acquired diagnosis result. A learning model of the diagnosis results is generated in relation to the internal state of the separation tank.
The learning unit 56a acquires the teacher data of the cause stored in the recording device 52. The learning unit 56a performs machine learning on the supernatant water image and information that specifies the cause of the diagnosis of the internal state of the solid-liquid separation tank based on the acquired teacher data of the cause. A learning model of the cause is generated in association with information that specifies the cause of the diagnostic result of the internal state of the liquid separation tank.
(Step S15-4)
In the monitoring device 50a, the learning unit 56a causes the recording device 52 to store the generated learning model of the diagnosis result. The learning unit 56a causes the recording device 52 to store the generated learning model of the cause.

Note that the diagnosis result notification may be a diagnosis result based on a monitoring image instead of a supernatant water image. That is, in step S7-4, the terminal device 45a creates a surveillance image request, in step S8-4, the terminal device 45a transmits the created surveillance image request to the surveillance device 50a, and in step S9-4, the surveillance device 50a monitors the An image may be created, and the monitoring device 50a may transmit a monitoring image response to the terminal device 45a in step S10-4.

FIG. 14 is a diagram illustrating a second example of the operation of the monitoring system according to the first modification of the embodiment. Referring to FIG. 14, monitoring device 50a acquires the digital signal transmitted by data processing device 30, and creates a supernatant water image based on the acquired digital signal. The monitoring device 50a will explain the process of determining the internal state of the solid-liquid separation tank based on the created supernatant water image.
Since steps S1-1 to S6-1 in FIG. 7 can be applied to steps S1-5 to S6-5, the description thereof will be omitted here.
(Step S7-5)
In the monitoring device 50a, the current state determining unit 55a acquires the pixel data stored in the recording device 52, and creates a supernatant water image based on the acquired pixel data.
(Step S8-5)
In the monitoring device 50a, the current state determining unit 55a acquires the learning model of the diagnosis result stored in the recording device 52.
(Step S9-5)
In the monitoring device 50a, the current state determining unit 55a determines the internal state of the solid-liquid separation tank in the created supernatant water image based on the learning model of the acquired diagnosis result.
(Step S10-5)
In the monitoring device 50a, the cause determination unit 57 acquires the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55a. The cause determination unit 57 determines whether the obtained determination result of the internal state of the solid-liquid separation tank is malfunctioning or abnormal. If the cause determination unit 57 determines that the obtained determination result of the internal state of the solid-liquid separation tank is neither malfunction nor abnormality, the process ends.

(Step S11-5)
In the monitoring device 50a, the cause determination unit 57 acquires the learning model of the cause stored in the recording device 52 when the acquired determination result of the internal state of the solid-liquid separation tank is determined to be malfunctioning or abnormal. .
(Step S12-5)
In the monitoring device 50a, the cause determining unit 57 determines information specifying the cause of the state inside the solid-liquid separation tank of the acquired supernatant water image based on the acquired learning model of the cause.
(Step S13-5)
In the monitoring device 50a, the cause determination unit 57 includes information indicating the supernatant water image, information indicating the determination result of the internal state of the solid-liquid separation tank, and information indicating the determination result of the cause of the internal state of the solid-liquid separation tank. Create status notification information that includes the information processing device 40a as the destination.
(Step S14-5)
In the monitoring device 50a, the cause determination unit 57 outputs the created status notification information to the communication device 51. The communication device 51 acquires the status notification information output by the cause determination unit 57, and transmits the acquired status notification information to the information processing device 40a.
Note that the monitoring device 50 creates a supernatant water image in step S7-5, but this is only an example. For example, the monitoring device 50 may create a monitoring image based on pixel data and focus on the supernatant water image by ignoring the portion deeper than the sludge interface in subsequent steps.
Since FIG. 9 can be applied to the process in which the monitoring device 50a transmits information indicating the supernatant water image based on the tank internal state information request transmitted by the information processing device 40a, a description thereof will be omitted.

In the first modification of the embodiment described above, a case has been described in which the monitoring system 100a is connected to one sewage treatment facility 10, but the present invention is not limited to this example. For example, the monitoring system 100a may be connected to a plurality of sewage treatment facilities 10, or the plurality of monitoring systems 100a may be connected to one sewage treatment facility 10. If the monitoring system 100a is connected to a plurality of sewage treatment facilities 10, if an unsteady state that has never been experienced occurs in equipment A, it will be possible to detect whether an unsteady state has occurred in equipment B. For example, there is a high possibility that it will be determined as an "abnormality" and that information identifying the cause of the abnormality will be determined and output. In other words, since the monitoring device 50a is capable of learning more, it is possible to increase the number of cases that can be used for determination. Therefore, it is possible to increase the number of unsteady states that can be determined to be abnormal or malfunctioning.
In the first modification of the embodiment described above, a case has been described in which the monitoring device 50a performs machine learning, but the present invention is not limited to this example. For example, a device that performs machine learning may be implemented as a device different from the monitoring device 50a. In this case, the learning device is the learning device described in the embodiment, and the learning device acquires the supernatant water image and information that specifies the cause of the diagnosis result based on the supernatant water image from the monitoring device 50a. The learning section of the learning device uses the supernatant water image and information that specifies the cause of the diagnosis result based on the supernatant water image to determine the supernatant water image and information that specifies the cause of the internal state of the solid-liquid separation tank. A second learning model representing the relationship is generated by machine learning (supervised machine learning).
In the first modification of the embodiment described above, it is determined whether the internal state of the solid-liquid separation tank is normal, abnormal, or malfunctioning based on the supernatant water image, and the solid-liquid separation tank Explains cases where bulking, fast sludge input speed, large sludge input amount, and high sludge interface are stored based on whether the judgment result of the internal condition is abnormal or malfunctioning. However, it is not limited to this example. For example, it may be classified into one or more causes based on whether the determination result of the internal state of the solid-liquid separation tank is abnormal or malfunctioning.

According to the monitoring system 100a according to the first modified example of the embodiment, the monitoring device 50a performs a diagnosis based on the supernatant water image and information specifying the cause of the diagnosis result based on the supernatant water image. Then, using the second learning model as a learning model of the cause that has learned the relationship between the supernatant water image and the information that specifies the cause of the diagnosis result inside the solid-liquid separation tank, the solid-liquid separation that is the target of diagnosis is A cause determination unit 57 is provided that determines information specifying the cause of the internal state of the solid-liquid separation tank from the supernatant water image of the tank. The output unit further outputs information specifying the cause of the internal state of the solid-liquid separation tank determined by the cause determination unit using the supernatant water image of the solid-liquid separation tank to be diagnosed and the second learning model. do.
With this configuration, the monitoring device 50a uses the second learning model that has learned the relationship between the supernatant water image and the information that specifies the cause of the diagnosis result inside the solid-liquid separation tank to determine the target of diagnosis. Since information identifying the cause of the internal state of the solid-liquid separation tank can be determined from the supernatant water image of the solid-liquid separation tank, the cause of the internal state of the solid-liquid separation tank can be monitored. Using the second learning model, it is possible to determine the cause of the internal state of the solid-liquid separation tank from the supernatant water image showing the inside of the solid-liquid separation tank, which is the target of diagnosis. Compared to the case of diagnosing the cause of the internal state of a separation tank, human experience is not required, and variations in diagnostic results can be reduced.

[Modification 2 of embodiment]
(Monitoring system)
FIG. 15 is a diagram showing a configuration example of a monitoring system according to modification 2 of the embodiment of the present invention. The monitoring system 100b according to the second modification of the embodiment diagnoses the state of sludge accumulation in solid-liquid separation tanks such as settling tanks and thickening tanks. In the second modification of the embodiment, the sewage treatment equipment 10 is applied as an example of equipment including a solid-liquid separation tank, similarly to the embodiment.

(Monitoring system 100b)
The monitoring system 100b includes an ultrasonic sensor 20, a data processing device 30, a gateway device 31, an information processing device 40b, a terminal device 45b, and a monitoring device 50b.
The gateway device 31, the information processing device 40b, the terminal device 45b, and the monitoring device 50b are connected via the network NW.
In the data processing device 30, the data calculation unit 34 transmits the digital signal to the monitoring device 50b via the gateway device 31.

(Monitoring device 50b)
The monitoring device 50b is realized by a device such as a personal computer, a server, or an industrial computer. The monitoring device 50b includes a communication device 51, a recording device 52, an information processing section 53b, and bus lines such as an address bus and a data bus for electrically connecting each component as shown in FIG. It is equipped with BL.
The recording device 52 stores a program (monitoring application) executed by the monitoring device 50b. The recording device 52 also stores pixel data output by the information processing section 53b.
The recording device 52 stores the supernatant water image based on the training data of the diagnosis result that associates the information indicating the supernatant water image with the diagnosis result of the inside of the solid-liquid separation tank based on the supernatant water image, and the supernatant water image based on the training data of the diagnosis result. A learning model of the diagnosis result obtained by machine learning of the relationship between the information and the internal state of the solid-liquid separation tank is stored.
The recording device 52 stores cause training data in which information indicating the monitoring image is associated with information specifying the cause of the diagnosis result inside the solid-liquid separation tank based on the supernatant water image, and cause training data based on the cause training data. , a learning model of the cause obtained by machine learning of the relationship between the supernatant water image and information specifying the cause of the internal state of the solid-liquid separation tank is stored.
The recording device 52 stores training data of a countermeasure method in which information indicating a supernatant water image is associated with information specifying a countermeasure method for a diagnosis result of a solid-liquid separation tank based on the supernatant water image, and training data of a countermeasure method. Based on this, a learning model of a countermeasure method obtained by machine learning of the relationship between the supernatant water image and information specifying a countermeasure method for the internal state of the solid-liquid separation tank is stored.

FIG. 16 is a diagram showing an example of teacher data. FIG. 16 shows training data for diagnosis results, training data for causes, and training data for countermeasures. The training data of the diagnosis result is data that associates a supernatant water image with a diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image. The cause training data is data that associates a supernatant water image with information that specifies a cause that is a diagnostic result of the internal state of the solid-liquid separation tank based on the supernatant water image. The training data for the countermeasure method is data that associates a supernatant water image with information specifying a countermeasure method for the internal state of the solid-liquid separation tank based on the supernatant water image. In the description of FIG. 16, a monitoring image will be used for convenience.
In the second modification of the embodiment, as an example, as in the embodiment, one of "normal", "abnormal", and "disorder" is associated with each of the plurality of monitoring images as a diagnostic result. Further, an estimated result of the cause of the diagnosis result is associated with each of the plurality of monitoring images based on the diagnosis result. Further, information specifying a method of dealing with the diagnosis result is associated with each of the plurality of monitoring images based on the diagnosis result.
In FIG. 16, (1) is diagnosed as normal because the supernatant water has a sufficient depth. If it is diagnosed as normal, the estimated cause of the diagnosis result and the countermeasure method are not stored.
(2) is diagnosed as abnormal because the depth of the supernatant water is shallow. In this case, bulking is stored as the estimated result of the cause of the diagnosis. Furthermore, promotion of sludge extraction, injection of sludge settling agent, etc. are stored as methods for dealing with the presumed cause of the diagnosis result.
Case (3) is diagnosed as malfunctioning because accumulated sludge is seen floating up in the supernatant water. In this case, as examples of the estimated results of the cause of the diagnosis result, a high sludge input speed, a large sludge input amount, and a high sludge interface are stored. Further, as an example of a method for dealing with the estimated cause of the diagnosis result, reduction of the input speed, reduction of the input amount, and promotion of sludge removal are stored. Returning to FIG. 15, the explanation will be continued.

The information processing unit 53b functions as, for example, a graphic generation unit 54, a current status determination unit 55a, a learning unit 56b, a cause determination unit 57b, and a countermeasure determination unit 58.
The learning section 56b has the following functions in addition to the functions of the learning section 56a. The learning unit 56b acquires the diagnosis result notification received by the communication device 51, and determines a countermeasure method by associating information indicating a supernatant water image included in the acquired diagnosis result notice with information specifying a countermeasure method for the diagnosis result. The teacher data is stored in the recording device 52.
The learning unit 56b acquires training data of coping methods stored in the recording device 52. The learning unit 56b performs machine learning (supervised learning) on the supernatant water image and information specifying how to deal with the diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, based on the obtained training data of the countermeasure method. By doing this, a learning model of how to deal with the internal state of the solid-liquid separation tank is created by associating the supernatant water image with how to deal with the internal state of the solid-liquid separation tank. For example, the learning unit 56b uses a convolutional neural network to recognize the supernatant water image. Based on the information indicating the supernatant water image, the learning model of the countermeasure method classifies the supernatant water image into one of the information that specifies the countermeasure method for the internal state of the solid-liquid separation tank. The learning unit 56b causes the recording device 52 to store the generated learning model of the coping method.

The cause determination unit 57b acquires information indicating the supernatant water image and the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55a. If the obtained determination result of the internal state of the solid-liquid separation tank is poor or abnormal, the cause determination unit 57b acquires the learning model of the cause stored in the recording device 52. The cause determination unit 57b determines the cause of the state inside the solid-liquid separation tank of the acquired supernatant water image based on the acquired learning model of the cause.
The countermeasure determination unit 58 acquires information indicating the supernatant water image and the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55a. If the acquired determination result of the internal state of the solid-liquid separation tank is poor or abnormal, the countermeasure determination unit 58 acquires the learning model of the countermeasure stored in the recording device 52. The countermeasure determination unit 58 determines a countermeasure method for the internal state of the solid-liquid separation tank in the obtained supernatant water image based on the acquired learning model of the countermeasure method.
The countermeasure determining unit 58 acquires information specifying the cause of the state inside the solid-liquid separation tank in the supernatant water image from the cause determining unit 57b. The countermeasure determination unit 58 generates information including information indicating the supernatant water image, information specifying the cause of the internal state of the solid-liquid separation tank, and information specifying a countermeasure method for the internal state of the solid-liquid separation tank. Status notification information destined for the processing device 40b is created. The countermeasure determination unit 58 outputs the created status notification information to the communication device 51.
The communication device 51 acquires the status notification information output by the cause determination unit 57b, and transmits the acquired status notification information to the information processing device 40b.
All or part of the information processing unit 53b is a functional unit (hereinafter referred to as a software functional unit) that is realized by a processor such as a CPU executing a program such as a monitoring application stored in the recording device 52. be. Note that all or part of the information processing section 53b may be realized by hardware such as LSI, ASIC, or FPGA, or may be realized by a combination of a software function section and hardware.
The information processing device 40 can be applied to the information processing device 40b.

(Terminal device 45b)
The terminal device 45b is realized by a device such as a personal computer, a server, or an industrial computer. An example of the terminal device 45b is installed in a monitoring center that monitors the sewage treatment facility 10.
When diagnosing the internal state of the solid-liquid separation tank, the user operates the terminal device 45b to create a supernatant water image request addressed to the monitoring device 50b that includes information requesting a supernatant water image. . The terminal device 45b creates a supernatant water image request based on the user's operation. The terminal device 45b transmits the created supernatant water image request to the monitoring device 50b.
The terminal device 45b receives the supernatant water image response sent by the monitoring device 50b in response to the supernatant water image request sent to the monitoring device 50b. The terminal device 45b displays the supernatant water image included in the supernatant water image response. The user refers to the supernatant water image displayed by the terminal device 45b, diagnoses the internal state of the solid-liquid separation tank included in the supernatant water image, and further estimates the cause of the internal state of the solid-liquid separation tank. By operating the terminal device 45b, the user receives information indicating the supernatant water image, the diagnosis result of the internal state of the solid-liquid separation tank, information identifying the cause of the diagnosis result, and how to deal with the diagnosis result. A diagnosis result notification containing information specifying the method and addressed to the monitoring device 50b is created. The terminal device 45b creates a diagnosis result notification based on the user's operation. The terminal device 45b transmits the created diagnosis result notification to the monitoring device 50b.

(Operation of monitoring system)
FIG. 17 is a diagram showing an example 1 of the operation of the monitoring system according to the second modification of the embodiment. Referring to FIG. 17, the monitoring device 50b receives the diagnosis result of the internal state of the solid-liquid separation tank included in the diagnosis result notification transmitted by the terminal device 45b, information specifying the cause of the diagnosis result, and the diagnosis result. The process of accumulating information specifying how to deal with the results will be described. The monitoring device 50b performs machine learning based on the accumulated diagnosis results of the internal state of the solid-liquid separation tank, information specifying the causes of the diagnosis results, and information specifying how to deal with the diagnosis results. , a process for generating a learning model for diagnosis results, a learning model for causes, and a learning model for coping methods will be described.
Since steps S1-1 to S10-1 in FIG. 7 can be applied to steps S1-6 to S10-6, the description thereof will be omitted here.
(Step S11-6)
The terminal device 45b receives the supernatant water image response transmitted by the monitoring device 50b. The terminal device 45b displays the supernatant water image by processing the information indicating the supernatant water image included in the received supernatant water image response. The terminal device 45b sends the monitoring device 50b as a destination, which includes a diagnosis result of the internal state of the solid-liquid separation tank, information specifying the cause of the diagnosis result, and information specifying a method to deal with the diagnosis result. Create a diagnosis result notification.
(Step S12-6)
The terminal device 45b transmits the created diagnosis result notification to the monitoring device 50b.

(Step S13-6)
In the monitoring device 50b, the communication device 51 receives the diagnosis result notification transmitted by the terminal device 45b. The learning unit 56b acquires the diagnosis result notification received by the communication device 51, and includes information indicating the supernatant water image included in the acquired diagnosis result notification, the diagnosis result of the internal state of the solid-liquid separation tank, and the diagnosis result. and information that identifies how to deal with it.
The learning unit 56b includes training data of diagnosis results that associate information indicating the acquired supernatant water image with diagnosis results of the internal state of the solid-liquid separation tank, and information indicating the supernatant water image and the internal state of the solid-liquid separation tank. Records training data for the cause, which associates information that specifies the cause of the diagnosis result of the condition, and training data for the countermeasure, which associates information showing the supernatant water image with information that specifies how to deal with the diagnosis result. The information is stored in the device 52.
(Step S14-6)
In the monitoring device 50b, the learning unit 56b acquires training data of the diagnosis results stored in the recording device 52. The learning unit 56b performs machine learning on the supernatant water image and the diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, based on the training data of the acquired diagnosis result. A learning model of the diagnosis results is generated in relation to the internal state of the separation tank.
The learning unit 56b acquires the teacher data of the cause stored in the recording device 52. The learning unit 56b performs machine learning on the supernatant water image and the information that specifies the cause of the diagnosis of the internal state of the solid-liquid separation tank based on the acquired teacher data of the cause. A learning model of the cause is generated in association with information that specifies the cause of the diagnostic result of the internal state of the liquid separation tank.
The learning unit 56b acquires training data of coping methods stored in the recording device 52. The learning unit 56b performs machine learning on the supernatant water image and information specifying how to deal with the internal state of the solid-liquid separation tank, based on the acquired teaching data of the countermeasure method. A learning model of how to deal with the internal state of the separation tank is generated in association with information specifying how to deal with the situation inside the separation tank.
(Step S15-6)
In the monitoring device 50b, the learning unit 56b causes the recording device 52 to store the generated diagnostic result learning model, cause learning model, and countermeasure learning model.
Note that the diagnosis result notification may be a result of diagnosis based on a monitoring image instead of a supernatant water image. That is, in step S7-6, the terminal device 45b creates a surveillance image request, in step S8-1, the terminal device 45b transmits the created surveillance image request to the surveillance device 50b, and in step S9-1, the surveillance device 50b monitors the An image may be created, and the monitoring device 50b may transmit a monitoring image response to the terminal device 45b in step S10-1.

FIG. 18 is a diagram illustrating a second example of the operation of the monitoring system according to the second modification of the embodiment. Referring to FIG. 18, monitoring device 50b acquires the digital signal transmitted by data processing device 30, and creates a supernatant water image based on the acquired digital signal. A process in which the monitoring device 50b determines the internal state of the solid-liquid separation tank based on the created supernatant water image will be described.
Since steps S1-1 to S6-1 in FIG. 7 can be applied to steps S1-7 to S6-7, the description thereof will be omitted here.
(Step S7-7)
In the monitoring device 50b, the current state determining unit 55a acquires the pixel data stored in the recording device 52, and creates a supernatant water image based on the acquired pixel data.
(Step S8-7)
In the monitoring device 50b, the current state determining unit 55a acquires the learning model of the diagnosis result stored in the recording device 52.
(Step S9-7)
In the monitoring device 50b, the current state determining unit 55a determines the internal state of the solid-liquid separation tank in the created supernatant water image based on the learning model of the acquired diagnosis result.
(Step S10-7)
In the monitoring device 50b, the cause determination unit 57b acquires the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55a. The cause determination unit 57b determines whether the obtained determination result of the internal state of the solid-liquid separation tank is malfunctioning or abnormal. If the cause determination unit 57b determines that the obtained determination result of the internal state of the solid-liquid separation tank is neither malfunction nor abnormality, the process ends.

(Step S11-7)
In the monitoring device 50b, the cause determination unit 57b acquires the learning model of the cause stored in the recording device 52 when the acquired determination result of the internal state of the solid-liquid separation tank is determined to be malfunctioning or abnormal. .
(Step S12-7)
In the monitoring device 50b, the cause determination unit 57b determines the cause of the state inside the solid-liquid separation tank of the acquired supernatant water image based on the acquired learning model of the cause.
(Step S13-7)
In the monitoring device 50b, the countermeasure determination unit 58 acquires information indicating the supernatant water image and the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55a. If the acquired determination result of the internal state of the solid-liquid separation tank is poor or abnormal, the countermeasure determination unit 58 acquires the learning model of the countermeasure stored in the recording device 52.
(Step S14-7)
In the monitoring device 50b, the countermeasure determination unit 58 determines a countermeasure method for the internal state of the solid-liquid separation tank in the obtained supernatant water image based on the acquired learning model of the countermeasure method.
(Step S15-7)
In the monitoring device 50b, the countermeasure determining unit 58 acquires information specifying the cause of the state inside the solid-liquid separation tank in the supernatant water image from the cause determining unit 57b. The countermeasure determination unit 58 generates information including information indicating the supernatant water image, information specifying the cause of the internal state of the solid-liquid separation tank, and information specifying a countermeasure method for the internal state of the solid-liquid separation tank. Status notification information destined for the processing device 40b is created.
(Step S16-7)
In the monitoring device 50b, the countermeasure determination unit 58 outputs the created status notification information to the communication device 51. The communication device 51 acquires the status notification information output by the countermeasure method determining unit 58, and transmits the acquired status notification information to the information processing device 40b.
Note that the monitoring device 50 creates a supernatant water image in step S7-7, but this is just an example. For example, the monitoring device 50 may create a monitoring image based on pixel data and focus on the supernatant water image by ignoring the portion deeper than the sludge interface in subsequent steps.
Since FIG. 9 can be applied to the process in which the monitoring device 50b transmits information indicating the supernatant water image based on the tank internal state information request transmitted by the information processing device 40b, a description thereof will be omitted.

In the second modification of the embodiment described above, a case has been described in which the monitoring system 100b is connected to one sewage treatment facility 10, but the present invention is not limited to this example. For example, the monitoring system 100b may be connected to a plurality of sewage treatment facilities 10, or the plurality of monitoring systems 100b may be connected to one sewage treatment facility 10. If the monitoring system 100b is connected to a plurality of sewage treatment facilities 10, if an unsteady state that has never been experienced occurs in equipment A, it will be possible to detect whether an unsteady state has occurred in equipment B. For example, there is a high possibility that it will be determined as an "abnormality" and that information specifying the cause of the abnormality and information specifying a countermeasure will be determined and output. In other words, since the monitoring device 50b is capable of learning more, it is possible to increase the number of cases that can be used for determination. Therefore, it is possible to increase the number of unsteady states that can be determined to be abnormal or malfunctioning.
In the second modification of the embodiment described above, a case has been described in which the monitoring device 50b performs machine learning, but the present invention is not limited to this example. For example, a device that performs machine learning may be implemented as a device different from the monitoring device 50b. In this case, in the learning device described in the first modification of the embodiment, the learning device acquires the supernatant water image and information specifying how to deal with the diagnosis result based on the supernatant water image from the monitoring device 50b. do. The learning section of the learning device identifies how to deal with the supernatant water image and the diagnostic results inside the solid-liquid separation tank based on the supernatant water image and information that specifies how to deal with the diagnostic results based on the supernatant water image. A third learning model expressing the relationship with the information is generated by machine learning (supervised machine learning).
In the second modification of the embodiment, the information processing device 40b may notify the operator of the sewage treatment equipment 10 of the countermeasure included in the status notification, or may send control information for causing the equipment control device 19 to execute the countermeasure. may be created and the created control information may be sent to the equipment control device 19.
In the second modification of the embodiment described above, it is determined whether the internal state of the solid-liquid separation tank is normal, abnormal, or malfunctioning based on the supernatant water image, and the solid-liquid separation tank Based on whether the internal condition of the sludge is determined to be abnormal or malfunctioning, it is possible to promote sludge extraction, introduce sludge settling agents, etc., reduce the injection speed, reduce the input amount, and remove sludge. Although the case where promotion of is stored has been described, it is not limited to this example. For example, the situation may be classified into one or more methods based on whether the determination result of the internal state of the solid-liquid separation tank is abnormal or malfunctioning.
In the second modification of the embodiment described above, the first modification of the embodiment further includes a process of determining information for specifying a method to deal with the internal state of the solid-liquid separation tank from the supernatant water image of the solid-liquid separation tank. This example is not limited to this example. For example, the embodiment may further include a process of determining information that specifies how to deal with the internal state of the solid-liquid separation tank from the supernatant water image of the solid-liquid separation tank.

According to the monitoring system 100b according to the second modification of the embodiment, the monitoring device 50b includes the supernatant water image and information specifying how to deal with the diagnosis result based on the supernatant water image in the monitoring device 50a according to the embodiment. Based on the above, the third learning model is used as a learning model of a countermeasure method that has learned the relationship between the supernatant water image and information specifying a countermeasure method for the diagnosis result inside the solid-liquid separation tank. A countermeasure determination unit 58 is provided that determines information specifying a countermeasure for the internal state of the solid-liquid separation tank from the supernatant water image of the solid-liquid separation tank. The output unit includes information specifying how to deal with the internal state of the solid-liquid separation tank determined by the solution determination unit 58 using the supernatant water image of the solid-liquid separation tank to be diagnosed and the third learning model. further output.
With this configuration, the monitoring device 50b performs diagnosis using the third learning model that has learned the relationship between the supernatant water image and information specifying how to deal with the diagnosis result inside the solid-liquid separation tank. Since information specifying how to deal with the internal state of the solid-liquid separation tank can be determined from the supernatant water image of the target solid-liquid separation tank, it is possible to monitor how to deal with the internal state of the solid-liquid separation tank. Using the third learning model, it is possible to judge how to deal with the internal state of the solid-liquid separation tank from the supernatant water image of the solid-liquid separation tank, which is the target of diagnosis. Compared to the case of diagnosing how to deal with internal conditions, human experience is not required and the variation in diagnostic results can be reduced.

[Modification 3 of embodiment]
(Monitoring system)
FIG. 19 is a diagram showing a configuration example of a monitoring system according to modification 3 of the embodiment of the present invention. The monitoring system 100c according to the third modification of the embodiment not only diagnoses the state of sludge accumulation in solid-liquid separation tanks such as settling tanks and concentration tanks, but also detects signs of change. In the third modification of the embodiment, the sewage treatment facility 10 is applied as an example of a facility including a solid-liquid separation tank, similarly to the embodiment.

(Monitoring system 100c)
The monitoring system 100c includes an ultrasonic sensor 20, a data processing device 30, a gateway device 31, an information processing device 40c, a terminal device 45c, and a monitoring device 50c.
The gateway device 31, the information processing device 40c, the terminal device 45c, and the monitoring device 50c are connected via the network NW.
In the data processing device 30, the data calculation unit 34 transmits the digital signal to the monitoring device 50c via the gateway device 31.

(Monitoring device 50c)
The monitoring device 50c is realized by a device such as a personal computer, a server, or an industrial computer. The monitoring device 50c includes a communication device 51, a recording device 52, an information processing unit 53c, and bus lines such as an address bus and a data bus for electrically connecting each component as shown in FIG. It is equipped with BL.
The recording device 52 stores a program (monitoring application) executed by the monitoring device 50c. The recording device 52 also stores pixel data output by the information processing section 53c.
The recording device 52 stores training data of a diagnosis result that associates information indicating a supernatant water image with a diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, and supernatant data based on the training data of the diagnosis result. A learning model of diagnosis results obtained by machine learning of the relationship between the clear water image and the internal state of the solid-liquid separation tank is stored.
The recording device 52 stores cause teacher data in which information indicating a supernatant water image is associated with information specifying a cause resulting in a diagnostic result of the internal state of the solid-liquid separation tank based on the supernatant water image, and cause teacher data. Based on this, a learning model of the cause obtained by machine learning of the relationship between the supernatant water image and information specifying the cause of the internal state of the solid-liquid separation tank is stored.
The recording device 52 stores training data of a countermeasure method in which information indicating a supernatant water image is associated with information specifying a countermeasure method for a diagnostic result of the internal state of the solid-liquid separation tank based on the supernatant water image, and a countermeasure method. A learning model of a countermeasure obtained by machine learning of the relationship between the supernatant water image and information specifying a countermeasure for the internal state of the solid-liquid separation tank is stored based on the training data.
The recording device 52 stores change teacher data in which information indicating a supernatant water image is associated with information specifying a change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained, and change teacher data. Based on the data, a learning model of changes obtained by machine learning of the relationship between the supernatant water image and information specifying changes in the internal state of the solid-liquid separation tank is stored.

The information processing unit 53c functions as, for example, a graphics generation unit 54, a current status determination unit 55a, a learning unit 56c, a cause determination unit 57b, a countermeasure determination unit 58c, and a change sign derivation unit 59.
The learning section 56c has the following functions in addition to the functions of the learning section 56b. The learning unit 56c acquires the change teacher data stored in the recording device 52. The learning unit 56c performs machine learning (supervised learning) on the supernatant water image and information specifying the change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained, based on the acquired change training data. learning) to generate a learning model of changes that associates a supernatant water image with information that specifies changes in the internal state of the solid-liquid separation tank after the supernatant water image is obtained. For example, the learning unit 56c uses a convolutional neural network to recognize the supernatant water image. Based on the information indicating the supernatant water image, the change learning model classifies the supernatant water image into one of the information that specifies the change in the internal state of the solid-liquid separation tank after the supernatant water image was obtained. be done. The learning unit 56c causes the recording device 52 to store the generated change learning model.
The countermeasure determination unit 58c acquires information indicating the supernatant water image and the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55a. If the acquired determination result of the internal state of the solid-liquid separation tank is poor or abnormal, the countermeasure determination unit 58c acquires a learning model of the countermeasure stored in the recording device 52. The countermeasure determination unit 58c determines a countermeasure method for the internal state of the solid-liquid separation tank in the obtained supernatant water image based on the acquired learning model of the countermeasure method.
The change sign deriving unit 59 acquires information indicating the supernatant water image from the current state determining unit 55a. The change sign deriving unit 59 acquires the learning model of change stored in the recording device 52. The change sign deriving unit 59 derives a sign of change in the solid-liquid separation tank of the acquired supernatant water image based on the acquired change learning model.
All or part of the information processing unit 53c is a functional unit (hereinafter referred to as a software functional unit) that is realized by a processor such as a CPU executing a program such as a monitoring application stored in the recording device 52. be. Note that all or part of the information processing section 53c may be realized by hardware such as LSI, ASIC, or FPGA, or may be realized by a combination of a software function section and hardware.
The information processing device 40 can be applied to the information processing device 40c.

(Terminal device 45c)
The terminal device 45c is realized by a device such as a personal computer, a server, or an industrial computer. An example of the terminal device 45c is installed in a monitoring center that monitors the sewage treatment facility 10.
When diagnosing the internal state of the solid-liquid separation tank, the user operates the terminal device 45c to create a supernatant water image request addressed to the monitoring device 50c that includes information requesting a supernatant water image. . The terminal device 45c creates a supernatant water image request based on the user's operation. The terminal device 45c transmits the created supernatant water image request to the monitoring device 50c.
The terminal device 45c receives the supernatant water image response sent by the monitoring device 50c in response to the supernatant water image request sent to the monitoring device 50c. The terminal device 45c displays the supernatant water image included in the supernatant water image response. The user refers to the supernatant water image displayed by the terminal device 45c, diagnoses the internal state of the solid-liquid separation tank included in the supernatant water image, and further estimates the cause of the internal state of the solid-liquid separation tank, A method to deal with the internal state of the solid-liquid separation tank is specified, the internal state of the solid-liquid separation tank after the supernatant water image is obtained is estimated, and changes therein are identified.
By operating the terminal device 45c, the user can receive information indicating the supernatant water image, the diagnosis result of the internal state of the solid-liquid separation tank, information specifying the cause of the diagnosis result, and information indicating the internal state of the solid-liquid separation tank. Diagnosis results addressed to the monitoring device 50c, including information specifying how to deal with the internal condition and information specifying changes in the internal condition of the solid-liquid separation tank after the supernatant water image is obtained. Let notifications be created. The terminal device 45c creates a diagnosis result notification based on the user's operation. The terminal device 45c transmits the created diagnosis result notification to the monitoring device 50c.

(Operation of monitoring system)
FIG. 20 is a diagram illustrating a first example of the operation of the monitoring system according to the third modification of the embodiment. Referring to FIG. 20, the monitoring device 50c receives the information indicating the supernatant water image included in the diagnosis result notification sent by the terminal device 45c, the diagnosis result of the internal state of the solid-liquid separation tank, and the cause of the diagnosis result. information that specifies the diagnosis result, information that specifies how to deal with the diagnosis result, and information that specifies the change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained. Information showing clear water images, diagnosis results of the internal state of the solid-liquid separation tank, information identifying the cause of the diagnosis results, information specifying how to deal with the diagnosis results, and monitoring images were obtained. Machine learning is performed based on the information that identifies the subsequent change in the internal state of the solid-liquid separation tank, and a learning model for diagnosis results, a learning model for causes, a learning model for countermeasures, and a learning model for changes are generated. The process will be explained.
Since steps S1-1 to S10-1 in FIG. 7 can be applied to steps S1-8 to S10-8, the description thereof will be omitted here.
(Step S11-8)
The terminal device 45c receives the supernatant water image response transmitted by the monitoring device 50c. The terminal device 45c displays the supernatant water image by processing the information indicating the supernatant water image included in the received supernatant water image response. The terminal device 45c has information indicating the supernatant water image, a diagnosis result of the internal state of the solid-liquid separation tank, information specifying the cause of the diagnosis result, and information specifying a method for dealing with the diagnosis result. , and information specifying a change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained, a diagnosis result notification addressed to the monitoring device 50c is created.

(Step S12-8)
The terminal device 45c transmits the created diagnosis result notification to the monitoring device 50c.
(Step S13-8)
In the monitoring device 50c, the communication device 51 receives the diagnosis result notification transmitted by the terminal device 45c. The learning unit 56c acquires the diagnosis result notification received by the communication device 51, and acquires information indicating the supernatant water image included in the acquired diagnosis result notification, the diagnosis result of the internal state of the solid-liquid separation tank, and the diagnosis result. information that specifies how to deal with the problem and information that specifies the change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained.
The learning unit 56c includes teacher data of diagnosis results that associates information indicating the acquired supernatant water image with diagnosis results of the internal state of the solid-liquid separation tank, and information indicating the supernatant water image and the internal state of the solid-liquid separation tank. The teacher data of the cause is associated with the information that specifies the cause of the diagnosis result of the condition, the teacher data of the countermeasure is associated with the information indicating the supernatant water image and the information that specifies how to deal with the diagnosis result, The recording device 52 stores change teacher data in which information indicating a clear water image is associated with information specifying a change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained.
(Step S14-8)
In the monitoring device 50c, the learning unit 56c acquires training data of the diagnosis results stored in the recording device 52. The learning unit 56c performs machine learning on the supernatant water image and the diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, based on the acquired training data of the diagnosis result. A learning model of the diagnosis results is generated in relation to the internal state of the separation tank.
The learning unit 56c acquires the teacher data of the cause stored in the recording device 52. The learning unit 56c performs machine learning on the supernatant water image and information for specifying the cause of the diagnosis result of the internal state of the solid-liquid separation tank based on the acquired teacher data of the cause. A learning model of the cause is generated in association with information that specifies the cause of the diagnostic result of the internal state of the liquid separation tank.
The learning unit 56c acquires training data of coping methods stored in the recording device 52. The learning unit 56c performs machine learning on the supernatant water image and information specifying how to deal with the internal state of the solid-liquid separation tank, based on the acquired teaching data of the countermeasure method. A learning model of how to deal with the internal state of the separation tank is generated in association with information specifying how to deal with the situation inside the separation tank.
The learning unit 56c acquires the change teacher data stored in the recording device 52. The learning unit 56c performs machine learning on the supernatant water image and information specifying the change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained, based on the acquired change training data. , a change learning model is generated that associates a supernatant water image with information specifying a change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained.

(Step S15-8)
In the monitoring device 50c, the learning unit 56c causes the recording device 52 to store the generated diagnostic result learning model, cause learning model, countermeasure learning model, and change learning model.

Note that the diagnosis result notification may be the result of diagnosis based on the monitoring image instead of the supernatant water image. That is, in step S7-8, the terminal device 45c creates a surveillance image request, in step S8-8 the terminal device 45c transmits the created surveillance image request to the surveillance device 50c, and in step S9-8, the surveillance device 50c monitors the An image may be created, and the monitoring device 50c may transmit a monitoring image response to the terminal device 45c in step S10-8.

FIG. 21 is a diagram illustrating a second example of the operation of the monitoring system according to the third modification of the embodiment. Referring to FIG. 21, monitoring device 50c acquires the digital signal transmitted by data processing device 30, and creates a supernatant water image based on the acquired digital signal. A process in which the monitoring device 50c determines the internal state of the solid-liquid separation tank based on the created supernatant water image will be described.
Since steps S1-1 to S6-1 in FIG. 7 can be applied to steps S1-9 to S6-9, the explanation here will be omitted.
(Step S7-9)
In the monitoring device 50c, the current state determination unit 55a acquires the pixel data stored in the recording device 52, and creates a supernatant water image based on the acquired pixel data.
(Step S8-9)
In the monitoring device 50c, the current state determining unit 55a acquires the learning model of the diagnosis result stored in the recording device 52.
(Step S9-9)
In the monitoring device 50c, the current state determining unit 55a determines the internal state of the solid-liquid separation tank in the created supernatant water image based on the learning model of the acquired diagnosis result.
(Step S10-9)
In the monitoring device 50c, the cause determination unit 57b acquires the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55a. The cause determination unit 57b determines whether the obtained determination result of the internal state of the solid-liquid separation tank is malfunctioning or abnormal. If the cause determination unit 57b determines that the obtained determination result of the internal state of the solid-liquid separation tank is neither malfunction nor abnormality, the process moves to step S15-9.
(Step S11-9)
In the monitoring device 50c, the cause determination unit 57b acquires the learning model of the cause stored in the recording device 52 when the acquired determination result of the internal state of the solid-liquid separation tank is determined to be malfunctioning or abnormal. .
(Step S12-9)
In the monitoring device 50c, the cause determining unit 57b determines the cause of the state inside the solid-liquid separation tank of the acquired supernatant water image based on the acquired learning model of the cause.
(Step S13-9)
In the monitoring device 50c, the countermeasure determination unit 58c acquires information indicating the supernatant water image and the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55a. If the acquired determination result of the internal state of the solid-liquid separation tank is poor or abnormal, the countermeasure determination unit 58c acquires a learning model of the countermeasure stored in the recording device 52.

(Step S14-9)
In the monitoring device 50c, the countermeasure determination unit 58c determines a countermeasure method for the internal state of the solid-liquid separation tank in the obtained supernatant water image based on the acquired learning model of the countermeasure method.
(Step S15-9)
In the monitoring device 50c, the change sign deriving unit 59 acquires the learning model of change stored in the recording device 52. In the monitoring device 50c, the change sign deriving unit 59 detects a sign of a change in the state inside the solid-liquid separation tank in the acquired supernatant water image based on the acquired change learning model.
(Step S16-9)
In the monitoring device 50c, the change sign deriving unit 59 acquires information indicating the supernatant water image and the determination result of the internal state of the solid-liquid separation tank from the current state determining unit 55a. The change sign deriving unit 59 acquires information specifying the cause of the state inside the solid-liquid separation tank in the supernatant water image from the cause determining unit 57b. The change sign deriving unit 59 extracts information indicating the supernatant water image, the determination result of the internal state of the solid-liquid separation tank, information specifying the cause of the internal state of the solid-liquid separation tank, and the information indicating the internal state of the solid-liquid separation tank. Status notification information addressed to the information processing device 40c is created, including information specifying how to deal with the situation and the detection result of a sign of a change in the internal status of the solid-liquid separation tank.
(Step S17-9)
In the monitoring device 50c, the change sign deriving unit 59 outputs the created status notification information to the communication device 51. The communication device 51 acquires the status notification information output by the countermeasure method determining unit 58c, and transmits the acquired status notification information to the information processing device 40c.
Note that the monitoring device 50 creates a supernatant water image in step S7-9, but this is just an example. For example, the monitoring device 50 may create a monitoring image based on pixel data and focus on the supernatant water image by ignoring the portion deeper than the sludge interface in subsequent steps.
Since FIG. 9 can be applied to the process in which the monitoring device 50c transmits information indicating the supernatant water image based on the tank internal state information request transmitted by the information processing device 40c, a description thereof will be omitted.

In the third modification of the embodiment described above, a case has been described in which the monitoring system 100c is connected to one sewage treatment facility 10, but the present invention is not limited to this example. For example, the monitoring system 100c may be connected to a plurality of sewage treatment facilities 10, or the plurality of monitoring systems 100c may be connected to one sewage treatment facility 10. If the monitoring system 100c is connected to a plurality of sewage treatment facilities 10, if an unsteady state that has never been experienced occurs in equipment A, it will be possible to detect whether an unsteady state has occurred in equipment B. For example, it is determined to be an "abnormality" and information is used to identify the cause of the abnormality, information to identify countermeasures, and changes in the internal state of the solid-liquid separation tank after the supernatant water image is obtained. There is a high possibility that the information will be determined and output. In other words, since the monitoring device 50c is capable of learning more, it is possible to increase the number of cases that can be used for determination. Therefore, it is possible to increase the number of unsteady states that can be determined to be abnormal or malfunctioning.
In the third modification of the embodiment described above, a case has been described in which the monitoring device 50c performs machine learning, but the present invention is not limited to this example. For example, a device that performs machine learning may be implemented as a device different from the monitoring device 50c. In this case, in the learning device described in the second modification of the embodiment, the learning device specifies the supernatant water image and the change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained. information from the monitoring device 50c. The learning section of the learning device analyzes the supernatant water image and the internal state of the solid-liquid separation tank based on the supernatant water image and information specifying changes in the internal state of the solid-liquid separation tank after the supernatant water image is obtained. A fourth learning model representing a relationship with information specifying a change in state is generated by machine learning (supervised machine learning).
In modification 3 of the embodiment, the information processing device 40c may notify the operator of the sewage treatment facility 10 of information that specifies a change in the internal state of the solid-liquid separation tank, which is included in the state notification.

According to the monitoring system 100c according to the third modification of the embodiment, the monitoring device 50c monitors the supernatant water image and the internal state of the solid-liquid separation tank after the supernatant water image is obtained in the monitoring device 50b according to the embodiment. Diagnosis is performed using the fourth learning model as a change learning model that has learned the relationship between the supernatant water image and the information identifying changes in the internal state of the solid-liquid separation tank. The apparatus includes a change sign deriving unit 59 that detects a sign of a change in the internal state of the solid-liquid separation tank from the supernatant water image of the solid-liquid separation tank, which is the object of the process. The output unit outputs information that identifies a sign of a change in the internal state of the solid-liquid separation tank detected by the change sign derivation unit using the supernatant water image of the solid-liquid separation tank to be diagnosed and the fourth learning model. Output more.
With this configuration, the monitoring device 50c uses the fourth learning model that has learned the relationship between the supernatant water image and the information specifying the change in the internal state of the solid-liquid separation tank to detect the target of diagnosis. Since signs of changes in the internal state of the solid-liquid separation tank can be detected from the supernatant water image of the solid-liquid separation tank, changes in the internal state of the solid-liquid separation tank can be monitored. By using the fourth learning model, it is possible to detect signs of changes in the internal state of the solid-liquid separation tank from images of the supernatant water of the solid-liquid separation tank, which is the target of diagnosis. Compared to the case of detecting signs of changes in internal conditions, human experience is not required and variations in diagnostic results can be reduced.

[Modification 4 of embodiment]
(Monitoring system)
FIG. 22 is a diagram illustrating a configuration example of a monitoring system according to modification 4 of the embodiment of the present invention. A monitoring system 100d according to a fourth modification of the embodiment is the same as the third modification of the embodiment in which a monitoring device 50d is connected between the data processing device 30d and the gateway device 31 without going through the network NW. The monitoring system 100d according to the fourth modification of the embodiment diagnoses the state of sludge accumulation in solid-liquid separation tanks such as settling tanks and thickening tanks, and detects signs of change. In modification 4 of the embodiment, the sewage treatment facility 10 is applied as an example of a facility including a solid-liquid separation tank, similarly to the embodiment. In FIG. 22, the sewage treatment equipment 10 is omitted.

(Monitoring system 100d)
The monitoring system 100d includes an ultrasonic sensor 20, a data processing device 30d, a monitoring device 50d, a gateway device 31, an information processing device 40d, and a terminal device 45d.
The gateway device 31, the information processing device 40d, and the terminal device 45d are connected via the network NW.
In the data processing device 30d, the data calculation unit 34 transmits the digital signal to the monitoring device 50d.

(Monitoring device 50d)
FIG. 23 is a diagram illustrating an example of a monitoring device of a monitoring system according to modification example 4 of the present embodiment. The monitoring device 50d is realized by a device such as a personal computer, a server, or an industrial computer. The monitoring device 50d includes a communication device 51, a recording device 52, an information processing section 53d, and bus lines such as an address bus and a data bus for electrically connecting each component as shown in FIG. It is equipped with BL.
The recording device 52 stores a program (monitoring application) executed by the monitoring device 50d. The recording device 52 also stores pixel data output by the information processing section 53d.
The recording device 52 contains training data of diagnosis results that associates information indicating a monitoring image with a diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, and supernatant water based on the training data of the diagnosis results. A learning model of the diagnosis result obtained by machine learning of the relationship between the image and the internal state of the solid-liquid separation tank is stored.
The recording device 52 stores cause teacher data in which information indicating a supernatant water image is associated with information specifying a cause resulting in a diagnostic result of the internal state of the solid-liquid separation tank based on the supernatant water image, and cause teacher data. Based on this, a learning model of the cause obtained by machine learning of the relationship between the supernatant water image and information specifying the cause of the internal state of the solid-liquid separation tank is stored.
The recording device 52 stores training data of a countermeasure method in which information indicating a supernatant water image is associated with information specifying a countermeasure method for a diagnostic result of the internal state of the solid-liquid separation tank based on the supernatant water image, and a countermeasure method. A learning model of a countermeasure obtained by machine learning of the relationship between the supernatant water image and information specifying a countermeasure for the internal state of the solid-liquid separation tank is stored based on the training data.
The recording device 52 stores change teacher data in which information indicating a supernatant water image is associated with information specifying a change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained, and change teacher data. Based on the data, a learning model of changes obtained by machine learning of the relationship between the supernatant water image and information specifying changes in the internal state of the solid-liquid separation tank is stored.

The information processing unit 53d functions as, for example, a graphic generation unit 54d, a current status determination unit 55d, a learning unit 56d, a cause determination unit 57d, a countermeasure determination unit 58d, and a change sign derivation unit 59d.
The graphic generator 54d acquires the digital signal received by the communication device 51. The graphic converting unit 54d converts the value of the acquired digital signal into pixel data. The graphic converting unit 54d causes the recording device 52 to store the pixel data after converting the digital signal.
The graphic generation unit 54d acquires the supernatant water image request received by the communication device 51. The graphic generation unit 54d acquires pixel data stored in the recording device 52 based on the acquired supernatant water image request. The graphic section 54d creates a supernatant water image based on the acquired pixel data. The graphic generation unit 54d creates a clear water image response addressed to the information processing device 40d, which includes information indicating the created clear water image. The graphic generator 54d outputs the created supernatant water image response to the communication device 51.
The graphic generating unit 54d acquires the tank internal state information request received by the communication device 51. The graphic generating unit 54d acquires pixel data stored in the recording device 52 based on the acquired tank state information request, and creates a supernatant water image based on the acquired pixel data. The graphic generating unit 54d creates an in-tank state information response addressed to the information processing device 40d, which includes information indicating the created supernatant water image. The graphic generator 54d outputs the created tank state information response to the communication device 51.

The current state determination unit 55d acquires the pixel data stored in the recording device 52, and creates a supernatant water image based on the acquired pixel data. The current state determination unit 55d acquires the learning model of the diagnosis result stored in the recording device 52. The current state determining unit 55d determines the internal state of the solid-liquid separation tank in the created supernatant water image based on the learning model of the acquired diagnosis result. If the determination result of the internal state of the solid-liquid separation tank is poor or abnormal, the current status determination unit 55d sends the information processing device 40d containing information indicating the determination result of the internal state of the solid-liquid separation tank as a destination. Create status notification information. The current status determination unit 55d outputs the created status notification information to the communication device 51. The communication device 51 acquires the status notification information output by the current status determination unit 55d, and transmits the acquired status notification information to the information processing device 40d.
When creating a supernatant water image, the current status determination unit 55d may use the measured data as is, or may include data measured over a long period of time in a limited display width by thinning out the data. good. By including data measured over a long period of time in a limited display width, changes over a longer period of time can be monitored. If it is a still image, pixel data can be picked up at arbitrary appropriate intervals and switched and displayed, but in the fourth modification of the present embodiment, new data is constantly added through measurement. If pixel data is picked up and switched and displayed at arbitrary and appropriate intervals, there is a risk that data processing will be delayed or hindered, and if measurement becomes unstable due to image display, it will be a waste of money. Therefore, in the fourth modification of the present embodiment, several preset display time widths are prepared, and data storage areas for time widths corresponding to each of the plurality of display time widths are created. In this embodiment, an interval at which new data is added is specified, and an image database (data storage area (address)) corresponding to each of a plurality of intervals is created.

An operation to switch the display is performed on the monitoring device 50d, and a display time width is selected. The current status determination unit 55d acquires data from the database corresponding to the selected time display width, and creates a supernatant water image using the acquired data. If the time display width is switched, data is acquired from the database corresponding to the selected time display width, and a supernatant water image is created using the acquired data. With this configuration, smooth switching can be performed without processing the data in the database in which the data is stored and without the time lag of creating a supernatant water image.
The learning unit 56d acquires the diagnosis result notification received by the communication device 51, and obtains information indicating a supernatant water image included in the acquired diagnosis result notification and the state of the inside of the solid-liquid separation tank (inside the tank) based on the supernatant water image. The recording device 52 stores the teacher data of the diagnosis result in association with the diagnosis result of the diagnosis result. The learning unit 56d acquires training data of the diagnosis results stored in the recording device 52. The learning unit 56d performs machine learning (supervised learning) on the supernatant water image and the diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, based on the acquired diagnostic result training data. A learning model for diagnosis results that correlates clear water images and the internal state of the solid-liquid separation tank is generated. For example, the learning unit 56d uses a convolutional neural network to recognize the supernatant water image. Based on the information indicating the supernatant water image, the learning model of the diagnosis result classifies the supernatant water image as one of normal, malfunctioning, and abnormal as the internal state of the solid-liquid separation tank. The learning unit 56d causes the recording device 52 to store the generated learning model of the diagnosis result.
The learning unit 56d acquires training data of coping methods stored in the recording device 52. The learning unit 56d performs machine learning (supervised training) on the supernatant water image and information for specifying a response method to the diagnosis result of the internal state of the solid-liquid separation tank based on the supernatant water image, based on the obtained training data of the countermeasure method. By doing this, a learning model of how to deal with the internal state of the solid-liquid separation tank is created by associating the supernatant water image with how to deal with the internal state of the solid-liquid separation tank. For example, the learning unit 56d uses a convolutional neural network to recognize the supernatant water image. Based on the information indicating the supernatant water image, the learning model of the countermeasure method classifies the supernatant water image into one of the information that specifies the countermeasure method for the internal state of the solid-liquid separation tank. The learning unit 56d causes the recording device 52 to store the generated learning model of the coping method.

The learning unit 56d acquires the change teacher data stored in the recording device 52. The learning unit 56d performs machine learning (supervised learning) on the supernatant water image and information specifying the change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained, based on the acquired change training data. learning) to generate a learning model of changes that associates a supernatant water image with information that specifies changes in the internal state of the solid-liquid separation tank after the supernatant water image is obtained. For example, the learning unit 56d uses a convolutional neural network to recognize the supernatant water image. Based on the information indicating the supernatant water image, the change learning model classifies the supernatant water image into one of the information that specifies the change in the internal state of the solid-liquid separation tank after the supernatant water image was obtained. be done. The learning unit 56d causes the recording device 52 to store the generated learning model of change.

The cause determination unit 57d acquires information indicating the supernatant water image and the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55d. When the acquired determination result of the internal state of the solid-liquid separation tank is poor or abnormal, the cause determination unit 57d acquires the learning model of the cause stored in the recording device 52. The cause determination unit 57d determines information specifying the cause of the state inside the solid-liquid separation tank of the acquired supernatant water image based on the acquired learning model of the cause. The cause determining unit 57d generates information including information indicating the supernatant water image, information indicating the internal state of the solid-liquid separation tank, and information indicating the determination result of information specifying the cause of the internal state of the solid-liquid separation tank. Status notification information destined for the processing device 40d is created. The cause determination unit 57d outputs the created status notification information to the communication device 51. The communication device 51 acquires the status notification information output by the cause determination unit 57d, and transmits the acquired status notification information to the information processing device 40d.

The countermeasure determination unit 58d acquires information indicating the supernatant water image and the determination result of the internal state of the solid-liquid separation tank from the current status determination unit 55d. If the acquired determination result of the internal state of the solid-liquid separation tank is poor or abnormal, the countermeasure determination unit 58d acquires the learning model of the countermeasure stored in the recording device 52. The countermeasure determination unit 58d determines a countermeasure method for the internal state of the solid-liquid separation tank in the obtained supernatant water image based on the acquired learning model of the countermeasure method.
The countermeasure determination unit 58d acquires information specifying the cause of the state inside the solid-liquid separation tank in the supernatant water image from the cause determination unit 57d. The countermeasure determination unit 58d generates information including information indicating the supernatant water image, information specifying the cause of the internal state of the solid-liquid separation tank, and information specifying a countermeasure method for the internal state of the solid-liquid separation tank. Status notification information destined for the processing device 40d is created. The countermeasure determination unit 58d outputs the created status notification information to the communication device 51.

The change sign deriving unit 59d acquires information indicating the supernatant water image from the current state determining unit 55d. The change sign deriving unit 59d acquires the learning model of change stored in the recording device 52. The change sign deriving unit 59d derives a sign of change in the solid-liquid separation tank from the acquired supernatant water image based on the acquired change learning model.
All or part of the information processing unit 53d is a functional unit (hereinafter referred to as a software functional unit) that is realized by a processor such as a CPU executing a program such as a monitoring application stored in the recording device 52. be. Note that all or part of the information processing section 53c may be realized by hardware such as LSI, ASIC, or FPGA, or may be realized by a combination of a software function section and hardware.
The information processing device 40 can be applied to the information processing device 40d.

(Terminal device 45d)
The terminal device 45d is realized by a device such as a personal computer, a server, or an industrial computer. An example of the terminal device 45d is installed in a monitoring center that monitors the sewage treatment facility 10.
When diagnosing the internal state of the solid-liquid separation tank, the user operates the terminal device 45d to create a supernatant water image request addressed to the monitoring device 50d that includes information requesting a supernatant water image. . The terminal device 45d creates a supernatant water image request based on the user's operation. The terminal device 45d transmits the created supernatant water image request to the monitoring device 50d.
The terminal device 45d receives the supernatant water image response sent by the monitoring device 50d in response to the supernatant water image request sent to the monitoring device 50d. The terminal device 45d displays the supernatant water image included in the supernatant water image response. The user refers to the supernatant water image displayed by the terminal device 45d, diagnoses the internal state of the solid-liquid separation tank included in the supernatant water image, and further estimates the cause of the internal state of the solid-liquid separation tank, A method to deal with the internal state of the solid-liquid separation tank is specified, the internal state of the solid-liquid separation tank after the supernatant water image is obtained is estimated, and changes therein are identified.
By operating the terminal device 45d, the user can receive information showing the supernatant water image, a diagnosis result of the internal state of the solid-liquid separation tank, information specifying the cause of the diagnosis result, and information indicating the internal state of the solid-liquid separation tank. Diagnosis results addressed to the monitoring device 50d, including information specifying how to deal with the internal condition and information specifying changes in the internal condition of the solid-liquid separation tank after the supernatant water image is obtained. Let notifications be created. The terminal device 45d creates a diagnosis result notification based on the user's operation. The terminal device 45d transmits the created diagnosis result notification to the monitoring device 50d.

(Operation of monitoring system)
FIG. 24 is a diagram illustrating an example 1 of operation of the monitoring system according to modification 4 of the embodiment. Referring to FIG. 24, the monitoring device 50d receives the information indicating the supernatant water image included in the diagnosis result notification sent by the terminal device 45d, the diagnosis result of the internal state of the solid-liquid separation tank, and the cause of the diagnosis result. information that specifies the diagnosis result, information that specifies how to deal with the diagnosis result, and information that specifies the change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained. Information showing the clear water image, diagnosis results of the internal state of the solid-liquid separation tank, information specifying the cause of the diagnosis results, information specifying how to deal with the diagnosis results, and the supernatant water image are obtained. Machine learning is performed based on the information that identifies the change in the internal state of the solid-liquid separation tank after the solid-liquid separation tank, and a learning model of the diagnosis result, a learning model of the cause, a learning model of the countermeasure, and a learning model of the change are generated. The process to do this will be explained.
Steps S1-1 to S10-1 in FIG. 7 can be applied to steps S1-10 to S10-10, and steps S11-8 to S15-8 in FIG. 20 can be applied to steps S11-10 to S15-10. , the explanation here is omitted.

FIG. 25 is a diagram illustrating a second example of the operation of the monitoring system according to the fourth modification of the embodiment. Referring to FIG. 25, monitoring device 50d acquires the digital signal transmitted by data processing device 30d, and creates a supernatant water image based on the acquired digital signal. A process in which the monitoring device 50d determines the internal state of the solid-liquid separation tank based on the created supernatant water image will be described.
Steps S1-1 to S6-11 can be applied to steps S1-1 to S6-1 in FIG. 7, and steps S7-11 to S17-11 can be applied to steps S7-9 to S17-9 in FIG. , the explanation here is omitted.
Since FIG. 9 can be applied to the process in which the monitoring device 50d transmits information indicating the supernatant water image based on the in-tank state information request transmitted by the information processing device 40d, a description thereof will be omitted.

In the modification 4 of the embodiment described above, in the modification 3 of the embodiment, the monitoring device 50d is connected between the data processing device 30d and the gateway device 31 without going through the network NW. Not limited to. For example, in the embodiment, the present invention can also be applied to a case where the monitoring device 50 is connected between the data processing device 30 and the gateway device 31 without going through the network NW. Modification 1 of the embodiment can also be applied to a case where the monitoring device 50a is connected between the data processing device 30 and the gateway device 31 without going through the network NW. In the second modification of the embodiment, the present invention can also be applied to a case where the monitoring device 50b is connected between the data processing device 30 and the gateway device 31 without going through the network NW.

According to the monitoring system 100d according to the fourth modification of the embodiment, the monitoring device 50d is connected to the sewage treatment facility by connecting the monitoring device 50d between the data processing device 30 and the gateway device 31 without going through the network NW. It can be installed at the site where 10 is installed. Therefore, the data of the data processing device 30d can be monitored in real time compared to the case where the monitoring device 50d is installed at a location away from the site where the sewage treatment equipment 10 is installed via the network NW.
Since the monitoring device 50d can perform the determination and derivation in real time, the time required for the determination and derivation can be shortened. Since the time required for determination and derivation can be shortened, it is possible to immediately notify the status when it is determined that there is an abnormality or malfunction.
Since the monitoring device 50d can be installed at the site where the sewage treatment equipment 10 is installed, it is compared with the case where the monitoring device 50d is installed at a location away from the site where the sewage treatment equipment 10 is installed via the network NW. This reduces the risk of data hacking and system attacks.
Since the monitoring device 50d can be installed at the site where the sewage treatment equipment 10 is installed, it is compared with the case where the monitoring device 50d is installed at a location away from the site where the sewage treatment equipment 10 is installed via the network NW. Therefore, it is easy to determine the unique situation of the site (equipment), determine the cause, determine how to deal with it, and derive signs.
The information processing device 40d installed in the monitoring center collects information (programs, monitoring applications, learning models, image data, AI analysis results) can be updated remotely.
Information (mainly pixel data and AI analysis results) recorded in the recording device 52 of the monitoring device 50d installed at the site can be updated to the information processing device 40d installed remotely through the gateway device 31 and the network NW. can.

Hereinafter, a monitoring system according to another embodiment will be described. A monitoring system according to another embodiment has a similar configuration to the monitoring system shown in FIG. 1, but differs in the following points.

The recording device 52 includes training data of diagnosis results that associates information indicating a monitoring image with a diagnosis result of the interior (inside the tank) of the solid-liquid separation tank based on the monitoring image, and monitoring data based on the training data of the diagnosis results. A learning model of the diagnosis result obtained by machine learning of the relationship between the image and the internal state of the solid-liquid separation tank is stored.
The training data of the diagnosis result is data that associates a monitoring image with a diagnosis result of the internal state of the solid-liquid separation tank based on the monitoring image. In this embodiment, as an example, one of "normal", "abnormal", and "disorder" is associated with each of the plurality of monitoring images as a diagnostic result. To explain using FIG. 6, (1) is diagnosed as normal because the supernatant water and the sludge accumulation layer are separated and the solid-liquid separation is in a good state. In case (2), the settling property of the sludge deteriorates and the sludge floats to the surface, so it is diagnosed as abnormal. In case (3), the accumulated sludge is seen to be floating up, so it is diagnosed as being in poor condition.

The graphic conversion unit 54 acquires the monitoring image request received by the communication device 51. The graphic converting unit 54 obtains pixel data stored in the recording device 52 based on the obtained monitoring image request. The graphic generator 54 creates a monitoring image based on the acquired pixel data. The graphic creation unit 54 creates a monitoring image response that includes information indicating the created monitoring image and is addressed to the information processing device 40 .
The graphic generator 54 determines whether the created monitoring image is an error image. The graphic conversion unit 54 outputs a monitoring image response including the monitoring image determined not to be an error image to the communication device 51.
FIG. 26 is an example of an error image. The error image is a monitoring image created when the processing tank 25 cannot be measured due to reasons such as the ultrasonic sensor 20 malfunctioning or being buried in sludge. An error image is an image in which the signal strength is weak both in the vertical and horizontal directions. For example, when the signal strength is below a predetermined size from a predetermined depth for a predetermined period of time, the graphic generator 54 determines that the monitoring image is an error image.

The graphic generating unit 54 acquires pixel data stored in the recording device 52 based on the acquired tank state information request, and creates a monitoring image based on the acquired pixel data. The graphic generating unit 54 creates an in-tank state information response that includes information indicating the created monitoring image and is addressed to the information processing device 40 .

The current status determination unit 55 acquires the pixel data stored in the recording device 52, and creates a monitoring image based on the acquired pixel data. The current status determination unit 55 determines whether the created monitoring image is an error image. The determination method is the same as the determination method by the graphic generator 54. When determining that the image is not an error image, the current status determination unit 55 determines the internal state of the solid-liquid separation tank in the created monitoring image based on the learning model of the acquired diagnosis result.

The learning unit 56 acquires the diagnosis result notification received by the communication device 51, and diagnoses the state inside the solid-liquid separation tank (inside the tank) based on information indicating a monitoring image included in the acquired diagnosis result notification and the monitoring image. The teacher data of the diagnosis result associated with the result is stored in the recording device 52. The learning unit 56 performs machine learning (supervised learning) on the monitoring image and the diagnosis result of the internal state of the solid-liquid separation tank based on the monitoring image, based on the acquired training data of the diagnosis result. A learning model of the diagnosis results is generated in relation to the internal state of the solid-liquid separation tank. For example, the learning unit 56 uses a convolutional neural network (CNN) to recognize the monitoring image. Based on the information indicating the monitored image, the learning model of the diagnosis result classifies the monitored image as one of normal, malfunctioning, and abnormal as the internal state of the solid-liquid separation tank.

The information processing device 40 acquires the monitoring image included in the received tank state information response. The information processing device 40 displays the acquired monitoring image.
When diagnosing the internal state of the solid-liquid separation tank, the user operates the terminal device 45 to create a monitoring image request addressed to the monitoring device 50 that includes information requesting a monitoring image. The terminal device 45 creates a monitoring image request based on the user's operation. The terminal device 45 transmits the created monitoring image request to the monitoring device 50.
The terminal device 45 receives the monitoring image response sent by the monitoring device 50 in response to the monitoring image request sent to the monitoring device 50. The terminal device 45 displays the monitoring image included in the monitoring image response. The user refers to the monitoring image displayed by the terminal device 45 and diagnoses the internal state of the solid-liquid separation tank included in the monitoring image.
By operating the terminal device 45, the user creates a diagnosis result notification addressed to the monitoring device 50 that includes information indicating the monitored image and the diagnosis result of the internal state of the solid-liquid separation tank.

That is, in other embodiments, the monitoring system uses monitoring images rather than supernatant water images. It is also determined whether the monitored image is an error image. Note that the supernatant water image may be created from the monitoring image after determining whether the monitoring image is an error image in the monitoring system. In other words, the determination as to whether or not it is an error image can be incorporated into the above-described embodiment and its modified examples.

(Operation of monitoring system)
FIG. 27 is a diagram illustrating an example 1 of operation of a monitoring system according to another embodiment. Referring to FIG. 27, monitoring device 50 accumulates the diagnosis result of the internal state of the solid-liquid separation tank included in the diagnosis result notification sent by terminal device 45, and information specifying the cause of the diagnosis result. Then, machine learning is performed based on the accumulated diagnosis results of the internal state of the solid-liquid separation tank and information specifying the causes of the diagnosis results, and a learning model of the diagnosis results and a learning model of the causes are generated. The process will be explained.

(Step S1-12)
In the data processing device 30 , the ultrasonic transmitter/receiver circuit 32 generates an electric signal for transmitting ultrasonic waves, and outputs the generated electric signal to the ultrasonic sensor 20 .
(Step S2-12)
In the data processing device 30, the ultrasonic transmitter/receiver circuit 32 receives the electrical signal output by the ultrasonic sensor 20.
(Step S3-12)
In the data processing device 30 , the ultrasonic transmission/reception circuit 32 outputs the received electrical signal to the data conversion circuit 33 . The data conversion circuit 33 acquires the electrical signal output by the ultrasonic transmission/reception circuit 32. The data conversion circuit 33 amplifies the acquired electrical signal. The data conversion circuit 33 performs masking processing on the amplified electrical signal. The data conversion circuit 33 converts the amplified electrical signal into a digital signal by digitally processing the signal intensity based on the result of masking processing. The data calculation unit 34 acquires a digital signal from the data conversion circuit 33, and performs a temperature correction calculation related to position (distance) information and an interface level determination calculation on the acquired digital signal.
(Step S4-12)
In the data processing device 30 , the data calculation unit 34 transmits a digital signal on which temperature correction calculations related to position (distance) information and interface level determination calculations have been performed to the monitoring device 50 via the gateway device 31 .
(Step S5-12)
In the monitoring device 50, the communication device 51 receives the digital signal transmitted by the data processing device 30. The graphic generator 54 acquires the digital signal received by the communication device 51. The graphic converting unit 54 converts the values of the acquired digital signals into pixel data.
(Step S6-12)
In the monitoring device 50, the graphic converting unit 54 causes the recording device 52 to store the pixel data converted into digital signals.
(Step S7-12)
The terminal device 45 creates a monitoring image request.

(Step S8-12)
The terminal device 45 transmits the created monitoring image request to the monitoring device 50.
(Step S9-12)
In the monitoring device 50, the communication device 51 receives the monitoring image request transmitted by the terminal device 45. The graphic conversion unit 54 acquires the monitoring image request received by the communication device 51. The graphic converting unit 54 obtains pixel data stored in the recording device 52 based on the obtained monitoring image request. The graphic generator 54 creates a monitoring image based on the acquired pixel data. The graphic section 54 includes information indicating the created monitoring image. A monitoring image response addressed to the terminal device 45 is created.
(Step S9a-12)
The graphic generator 54 determines whether the created monitoring image is an error image.
(Step S9b-12)
The graphic creation unit 54 ends the operation when the created monitoring image is an error image. This makes it possible to prevent error images from being included in the teacher data. When the created monitoring image is an error image, the graphic generation unit 54 may notify the terminal device 45 that the monitoring image is an error image.
(Step S10-12)
In the monitoring device 50, the graphic conversion unit 54 outputs the created monitoring image response to the communication device 51 when the created monitoring image is not an error image. The communication device 51 acquires the monitoring image response output by the graphic conversion unit 54 and transmits the acquired monitoring image response to the terminal device 45 .
(Step S11-12)
The terminal device 45 receives the monitoring image response sent by the monitoring device 50. The terminal device 45 displays the monitoring image by performing image processing on information indicating the monitoring image included in the received monitoring image response. The terminal device 45 creates a diagnosis result notification including information indicating the monitored image and the result of diagnosing the monitored image.
(Step S12-12)
The terminal device 45 transmits the created diagnosis result notification to the monitoring device 50.
(Step S13-12)
In the monitoring device 50, the communication device 51 receives the diagnosis result notification sent by the terminal device 45. The learning unit 56 acquires the diagnosis result notification received by the communication device 51, and diagnoses the state inside the solid-liquid separation tank (inside the tank) based on information indicating a monitoring image included in the acquired diagnosis result notification and the monitoring image. The teacher data of the diagnosis result associated with the result is stored in the recording device 52.
(Step S14-12)
In the monitoring device 50, the learning unit 56 acquires training data of the diagnosis results stored in the recording device 52. The learning unit 56 performs machine learning on the monitoring image and the diagnosis result of the internal state of the solid-liquid separation tank based on the monitoring image based on the acquired training data of the diagnosis result. Generates a learning model of diagnostic results that correlates with internal states.
(Step S15-12)
In the monitoring device 50, the learning unit 56 causes the recording device 52 to store the generated learning model of the diagnosis result.

FIG. 28 is a diagram illustrating a second example of the operation of a monitoring system according to another embodiment. Referring to FIG. 28, monitoring device 50 acquires the digital signal transmitted by data processing device 30, and creates a monitoring image based on the acquired digital signal. A process in which the monitoring device 50 determines the internal state of the solid-liquid separation tank based on the created monitoring image will be described.
Steps S1-13 to S6-13 can be applied to steps S1-12 to S6-12 in FIG. 27, so the description thereof will be omitted here.
(Step S7-13)
In the monitoring device 50, the current state determining unit 55 acquires the pixel data stored in the recording device 52, and creates a monitoring image based on the acquired pixel data.
(Step S8-13)
In the monitoring device 50, the current state determining unit 55 acquires the learning model of the diagnosis result stored in the recording device 52.
(Step S8a-13)
The current status determination unit 55 determines whether the created monitoring image is an error image.
(Step S9b-12)
The current status determination unit 55 ends the operation when the created monitoring image is an error image. If the created monitoring image is an error image, the current status determination unit 55 may output a status notification that the monitoring image is an error image to the information processing device 40 via the communication device 51.
(Step S9-13)
In the monitoring device 50, the current state determining unit 55 determines the internal state of the solid-liquid separation tank in the created monitoring image based on the learning model of the acquired diagnosis result.
(Step S10-13)
In the monitoring device 50, the current state determination unit 55 determines whether the determination result of the internal state of the solid-liquid separation tank is malfunctioning or abnormal. The current state determination unit 55 terminates when the determination result of the internal state of the solid-liquid separation tank is neither malfunction nor abnormal, that is, it is determined to be normal.
(Step S11-13)
In the monitoring device 50, when the current state determination unit 55 determines that the internal state of the solid-liquid separation tank is malfunctioning or abnormal, the current status determination unit 55 transmits information indicating the determination result of the internal state of the solid-liquid separation tank. Create status notification information with the information processing device 40 as the destination.
(Step S12-13)
In the monitoring device 50, the current status determining unit 55 outputs the created status notification information to the communication device 51. The communication device 51 acquires the status notification information output by the current status determination unit 55 and transmits the acquired status notification information to the information processing device 40 .

FIG. 29 is a diagram illustrating a third example of the operation of the monitoring system according to this embodiment. With reference to FIG. 9, a process in which the monitoring device 50 transmits information indicating a monitored image based on the tank internal state information request transmitted by the information processing device 40 will be described.
Steps S1-14 to S6-14 can be applied to steps S1-12 to S6-12 in FIG. 7, so the description thereof will be omitted here.
(Step S7-14)
The information processing device 40 creates an in-tank state information request based on the user's operation.
(Step S8-14)
The information processing device 40 transmits the created tank state information request to the monitoring device 50.
(Step S9-14)
In the monitoring device 50, the communication device 51 receives the tank state information request transmitted by the information processing device 40. The graphic generation unit 54 acquires the tank internal state information request received by the communication device 51. The graphic generating unit 54 acquires pixel data stored in the recording device 52 based on the acquired tank state information request, and creates a monitoring image based on the acquired pixel data.
(Step S9a-14)
The graphic generator 54 determines whether the created monitoring image is an error image.
(Step S9b-14)
The graphic creation unit 54 ends the operation when the created monitoring image is an error image. When the created monitoring image is an error image, the graphic generation unit 54 may output an in-tank state information response including information indicating that the monitoring image is an error image to the information processing device 40 via the communication device 51.
(Step S10-14)
In the monitoring device 50, the graphic generation unit 54 includes information indicating the created monitoring image. An in-tank status information response addressed to the information processing device 40 is created.
(Step S11-3)
In the monitoring device 50 , the graphic section 54 outputs the created tank state information response to the communication device 51 . The communication device 51 acquires the in-tank state information response outputted by the graphic generator 54 and transmits the obtained in-tank state information response to the information processing device 40 .
After step S11-3, the information processing device 40 receives the in-tank state information response transmitted by the monitoring device 50, and acquires information indicating the monitoring image included in the received in-tank state information response. The information processing device 40 displays the surveillance image by performing image processing on information indicating the acquired surveillance image. With this configuration, the user of the information processing device 40 can check the internal state of the solid-liquid separation tank.

The monitoring device 50 does not use monitoring images that are error images to create a learning model. Furthermore, the monitoring device 50 does not perform determination using the learning model on error images. This can prevent the learning model from erroneously diagnosing the error image as normal. In addition, when creating a supernatant water image from a monitoring image, if the monitoring image is an error image, the portion of the error image where the signal strength is small is created as a supernatant water image, and when creating a learning model or using a learning model. used for diagnosis and may lead to incorrect diagnosis. Therefore, by removing the error image, it is possible to prevent a false supernatant water image that is not based on the measurement result of supernatant water from being created from the error image.

Although the embodiment of the present invention has been described above in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and design changes and the like may be made without departing from the gist of the present invention.
For example, a computer program for realizing the functions of each device described above may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into a computer system and executed. Note that the "computer system" here may include hardware such as an OS and peripheral devices.
Furthermore, "computer-readable recording media" refers to flexible disks, magneto-optical disks, ROMs, writable non-volatile memories such as flash memory, portable media such as DVDs (Digital Versatile Discs), and media built into computer systems. A storage device such as a hard disk.

Furthermore, "computer-readable recording medium" refers to volatile memory (for example, DRAM (Dynamic It also includes those that retain programs for a certain period of time, such as Random Access Memory).
Further, the program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in a transmission medium. Here, the "transmission medium" that transmits the program refers to a medium that has a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line.
Moreover, the above-mentioned program may be for realizing a part of the above-mentioned functions. Furthermore, it may be a so-called difference file (difference program) that can realize the above-mentioned functions in combination with a program already recorded in the computer system.

10... Sewage treatment equipment, 11... Pre-sedimentation tank, 12... Concentration tank, 13... Storage tank, 14... Dehydrator, 15... Container, 16... Aeration tank, 17... Post-sedimentation tank, 18... Pump, 19... Equipment control Apparatus, 20... Ultrasonic sensor, 21 Oscillator, 22... Receiver, 23... Suspension deposit layer, 24... Supernatant water, 25... Treatment tank, 26... Interface, 27... Height, 30, 30d... Data processing Device, 31...Gateway device, 32...Ultrasonic transmission/reception circuit, 33...Data conversion circuit, 34...Data calculation section, 35...Image data storage section, 36...Display switching operation section, 37...Image data display section, 40, 40a, 40b, 40c, 40d... Information processing device, 45, 45a, 45b, 45c, 45d... Terminal device, 50, 50a, 50b, 50c, 50d... Monitoring device, 51... Communication device, 52... Recording device, 53, 53a, 53b, 53c...Information processing section, 54, 54d...Graphicization section, 55, 55a, 55d...Current status determination section, 56, 56a, 56b, 56c, 56d...Learning section, 57, 57b, 57d...Cause determination section , 58, 58c, 58d... Coping method determining unit, 59, 59d... Change sign deriving unit, 100, 100a, 100b, 100c, 100d... Monitoring system

Claims

Based on the supernatant water image, which is an image representing the supernatant water inside the solid-liquid separation tank for solid-liquid separation of wastewater, and the diagnosis result based on the supernatant water image, the supernatant water image and the inside of the solid-liquid separation tank are a determination unit that determines the internal state of the solid-liquid separation tank from a supernatant water image representing the supernatant water inside the solid-liquid separation tank that is a diagnosis target, using the first learning model that has learned the relationship with the state of the solid-liquid separation tank; and,
an output unit that outputs information specifying the internal state of the solid-liquid separation tank determined by the determination unit using the supernatant water image of the solid-liquid separation tank that is a diagnosis target and the first learning model; A monitoring system with
Based on a monitoring image that is an image representing the inside of a solid-liquid separation tank for solid-liquid separation of wastewater and a diagnosis result based on the monitoring image of the inside of the solid-liquid separation tank, the monitoring image and the solid-liquid separation tank are a determination unit that determines the internal state of the solid-liquid separation tank from a monitoring image representing the inside of the solid-liquid separation tank that is the subject of diagnosis, using a first learning model that has learned the relationship with the internal state of the solid-liquid separation tank;
an output unit that outputs information specifying the internal state of the solid-liquid separation tank determined by the determination unit using the monitoring image of the solid-liquid separation tank that is a diagnosis target and the first learning model; have,
The monitoring image does not include an error image that is an image at the time of a measurement failure.
Monitoring system.
The supernatant water image does not include an error image that is an image at the time of poor measurement.
The monitoring system according to claim 1.
Learning the relationship between the supernatant water image and information that specifies the cause of the diagnosis result inside the solid-liquid separation tank based on the supernatant water image and information that specifies the cause of the diagnosis result based on the supernatant water image. a cause determination unit that determines information for specifying the cause of the state inside the solid-liquid separation tank from the supernatant water image of the solid-liquid separation tank that is the object of diagnosis, using the second learning model obtained by ,
The output unit is configured to determine the cause of the state inside the solid-liquid separation tank determined by the cause determination unit using the supernatant water image of the solid-liquid separation tank to be diagnosed and the second learning model. The monitoring system according to claim 1, further outputting identifying information.
A relationship between the supernatant water image and information specifying how to deal with the diagnosis result inside the solid-liquid separation tank based on the supernatant water image and information specifying how to deal with the diagnosis result based on the supernatant water image. A countermeasure method determination method that determines information that specifies a countermeasure method for the condition inside the solid-liquid separation tank from the supernatant water image of the solid-liquid separation tank that is the target of diagnosis using a third learning model that has learned the above. has a department;
The output unit determines how to deal with the state inside the solid-liquid separation tank determined by the countermeasure determination unit using the supernatant water image of the solid-liquid separation tank that is a diagnosis target and the third learning model. The monitoring system according to claim 1, further outputting information specifying the method.
Identifying a supernatant water image and a change in the internal state of the solid-liquid separation tank based on the supernatant water image and information specifying a change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained. a change sign that detects a sign of a change in the state inside the solid-liquid separation tank from the supernatant water image of the solid-liquid separation tank that is a diagnosis target using a fourth learning model that has learned a relationship with information to be diagnosed; Equipped with a lead-out part,
The output unit is configured to output a change in the state inside the solid-liquid separation tank detected by the change sign derivation unit using the supernatant water image of the solid-liquid separation tank to be diagnosed and the fourth learning model. The monitoring system according to claim 1, further outputting information for identifying a sign.
The monitoring system according to claim 1, wherein the diagnostic result is generated based on either or both of a deposited state of solid matter and a suspended state of solid matter included in the supernatant water image.
The determination unit determines whether the internal state of the solid-liquid separation tank is normal, malfunctioning, or abnormal from the supernatant water image showing the inside of the solid-liquid separation tank that is the object of diagnosis. The monitoring system according to item 1.
When the determination unit determines that the state inside the solid-liquid separation tank is either malfunction or abnormality, it notifies that the state inside the solid-liquid separation tank is either malfunction or abnormality. The monitoring system according to claim 1, further comprising a notification section that performs.
Based on a supernatant water image, which is an image representing supernatant water inside a solid-liquid separation tank for solid-liquid separation of wastewater, and a diagnosis result based on the supernatant water image of the internal state of the solid-liquid separation tank, A learning device that includes a learning unit that generates, through learning, a first learning model that represents a relationship between a supernatant water image and an internal state of a solid-liquid separation tank.
Based on the monitoring image, which is an image representing the inside of a solid-liquid separation tank for separating wastewater into solid-liquid, and the diagnosis result based on the monitoring image of the internal state of the solid-liquid separation tank, the monitoring image and the solid-liquid separation tank are a learning unit that generates, through learning, a first learning model representing a relationship with the internal state of the separation tank;
The monitoring image does not include an error image that is an image at the time of poor measurement.
learning device.
The supernatant water image does not include an error image that is an image at the time of poor measurement.
The learning device according to claim 10.
The learning unit generates information that identifies a cause that results in a diagnosis result for the inside of the supernatant water image and the solid-liquid separation tank, based on the supernatant water image and information that identifies a cause that results in a diagnosis result based on the supernatant water image. Generating a second learning model expressing the relationship between
The learning device according to claim 10.
The learning unit specifies a method of handling the supernatant water image and the diagnosis result inside the solid-liquid separation tank based on the supernatant water image and information specifying a method of handling the diagnosis result based on the supernatant water image. generate a third learning model through learning that expresses the relationship with the information
The learning device according to claim 10.
The learning unit is configured to calculate the supernatant water image and the internal state of the solid-liquid separation tank based on the supernatant water image and information specifying a change in the internal state of the solid-liquid separation tank after the supernatant water image is obtained. The learning device according to claim 10, which generates a fourth learning model representing a relationship with information specifying a change in state.
The learning device according to claim 10, wherein the diagnosis result is generated based on either or both of a deposited state of solids and a suspended state of solids included in the supernatant water image.
Based on the supernatant water image, which is an image representing the supernatant water inside the solid-liquid separation tank for solid-liquid separation of wastewater, and the diagnosis result based on the supernatant water image, the supernatant water image and the inside of the solid-liquid separation tank are a step of determining the internal state of the solid-liquid separation tank from a supernatant water image representing the supernatant water inside the solid-liquid separation tank to be diagnosed using the first learning model that has learned the relationship with the state of the solid-liquid separation tank; ,
outputting information specifying the internal state of the solid-liquid separation tank determined in the determining step using the supernatant water image of the solid-liquid separation tank that is a diagnosis target and the first learning model; A monitoring method performed by a monitoring system having:
Based on the supernatant water image, which is an image representing the supernatant water inside the solid-liquid separation tank for solid-liquid separation of wastewater, and the diagnosis result based on the supernatant water image, the supernatant water image and the inside of the solid-liquid separation tank are A learning method executed by a learning device, comprising the step of generating, through learning, a first learning model representing a relationship between the state of
on the surveillance system computer,
Based on the supernatant water image, which is an image representing the supernatant water inside the solid-liquid separation tank for solid-liquid separation of wastewater, and the diagnosis result based on the supernatant water image, the supernatant water image and the inside of the solid-liquid separation tank are a step of determining the internal state of the solid-liquid separation tank from a supernatant water image representing the supernatant water inside the solid-liquid separation tank to be diagnosed using the first learning model that has learned the relationship with the state of the solid-liquid separation tank; ,
outputting information specifying the internal state of the solid-liquid separation tank determined in the determining step using the supernatant water image of the solid-liquid separation tank that is a diagnosis target and the first learning model; A program to run.
to the computer of the learning device,
Based on a supernatant water image that is an image representing supernatant water inside a solid-liquid separation tank for solid-liquid separation of wastewater and a diagnosis result based on the supernatant water image inside the solid-liquid separation tank, supernatant water A program that executes a step of generating, by learning, a first learning model representing a relationship between an image and an internal state of a solid-liquid separation tank.