JP6712630B2 - Abnormality monitoring device, abnormality monitoring method, and abnormality monitoring program - Google Patents

Description

The present invention relates to an abnormality monitoring device, an abnormality monitoring method, and an abnormality monitoring program.

Conventionally, sensor data acquired by a sensor installed in a detection target device is used as input data as a technique for detecting an abnormality in a device (hereinafter, detection target device) in various environments such as factories, plants, buildings, and data centers. , AI and machine learning methods are used to detect an abnormality in the detection target device.

For example, in the time-series deep running method, in the learning phase, out of the data in which the sensor data at the time of normality and the sensor data at the time of abnormality are mixed, the sensor data at the time of abnormality is learned as teacher data, and the abnormal data is detected at the detection phase. If close data is input, it is determined as abnormal.

JP, 2017-142654, A

However, in the above-mentioned conventional method, since the sensor data at the time of abnormality is used as the teacher data, there is a problem that it takes time and effort to acquire the sensor data at the time of abnormality. For example, in equipment such as a plant, it is difficult to obtain data at the time of abnormality because it is carefully designed so that no failure occurs.

In order to solve the above problems and achieve the object, the abnormality monitoring device of the present invention is a plurality of models for outputting the abnormality degree of a detection target device, and a plurality of models to which different machine learning methods are applied. For each model, the data acquired by the sensor installed in the detection target device is input, and the learning unit that performs machine learning of each model and the data acquired by the sensor are input, and each model is input. Is used to output the degree of abnormality of each of the detection target devices.

Further, the abnormality monitoring method of the present invention is an abnormality monitoring method executed by an abnormality monitoring device, and is a plurality of models for outputting the abnormality degree of a detection target device, and different machine learning methods are applied to each model. For each of the plurality of models, the data acquired by the sensor installed in the detection target device is respectively input, and the learning step of performing machine learning of each model, and the data acquired by the sensor as input, And an output step of outputting the degree of abnormality of the detection target device by using each model.

Further, the abnormality monitoring program of the present invention is a plurality of models for outputting an abnormality degree of a detection target device, and is installed in the detection target device for a plurality of models to which different machine learning methods are applied. Each of the data acquired by the sensor is input, the learning step of performing machine learning of each model, and the data acquired by the sensor as an input, the abnormality degree of the detection target device using each of the models, respectively. And outputting the output step to the computer.

According to the present invention, it is possible to easily and accurately monitor the abnormality of the detection target device even when the teacher data is not prepared.

FIG. 1 is a block diagram showing a configuration example of an abnormality monitoring system according to the first embodiment. FIG. 2 is a block diagram showing a configuration example of the abnormality monitoring device according to the first embodiment. FIG. 3 is a diagram illustrating an example of data stored in the sensor data storage unit. FIG. 4 is a diagram illustrating a screen display example in the abnormality monitoring device according to the first embodiment. FIG. 5 is a diagram illustrating an overall processing flow in the abnormality monitoring device according to the first embodiment. FIG. 6 is a flowchart showing an example of the flow of processing in the abnormality monitoring device according to the first embodiment. FIG. 7 is a block diagram showing a configuration example of the abnormality monitoring device according to the second embodiment. FIG. 8 is a diagram illustrating an overall processing flow in the abnormality monitoring device according to the second embodiment. FIG. 9 is a flowchart showing an example of the flow of processing in the abnormality monitoring device according to the second embodiment. FIG. 10 is a diagram illustrating a computer that executes an abnormality monitoring program.

Hereinafter, embodiments of an abnormality monitoring device, an abnormality monitoring method, and an abnormality monitoring program according to the present application will be described in detail with reference to the drawings. It should be noted that the abnormality monitoring device, the abnormality monitoring method, and the abnormality monitoring program according to the present application are not limited by this embodiment.

[First Embodiment]
In the following embodiments, the configuration of the abnormality monitoring system 100 according to the first embodiment, the configuration of the abnormality monitoring device 10, and the processing flow of the abnormality monitoring device 10 will be sequentially described, and finally, the effect of the first embodiment. Will be explained.

[Control system configuration]
FIG. 1 is a block diagram showing a configuration example of an abnormality monitoring system according to the first embodiment. The abnormality monitoring system 100 according to the first embodiment includes an abnormality monitoring device 10, a detection target device 20, and a user terminal 30, and is connected to each other via a network 40 such as the Internet. The configuration shown in FIG. 1 is merely an example, and the specific configuration and the number of each device are not particularly limited.

The abnormality monitoring device 10 collects the data acquired by the sensor 21 installed in the detection target device 20. Then, the abnormality monitoring device 10 inputs the collected data to a plurality of models for outputting the degree of abnormality of the detection target device 20 and a plurality of models to which different machine learning methods are applied, respectively. Then, machine learning of each model is performed. Then, the abnormality monitoring device 10 inputs the collected data and outputs the time-series graph data indicating the abnormality degree of the detection target device 20 output from each model to the display unit (not shown) of the user terminal 30. To do.

The detection target device 20 is an IoT (Internet of Things) device that is a target of abnormality detection, and may be any device, for example, a device in a plant, a building air conditioner, a rack in a data center, a coin laundry washing machine. , Store commercial refrigerators, convenience store cafe machines, parking adjustment machines, factory equipment, robot arms, etc.

Further, the detection target device 20 is provided with a sensor 21 that acquires various data. For example, a thin attachment sensor is attached as the sensor 21 to the detection target device 20. The sensors 21 may be provided at a plurality of locations on the detection target device 20, or the sensors 21 may be provided around the detection target device 20. Although omitted in FIG. 1, it is assumed that the detection target device 20 is connected to, for example, an OT (Operational Technology) network or the like, and is connected to a network 40 such as the Internet via the OT network.

The sensor 21 acquires various sensor data regarding the detection target device 20. For example, the sensor 21 acquires sensor data such as acceleration (3 axes), luminous intensity, temperature, humidity, magnetic force, and pressure. When the sensor 21 is a thin stick sensor, for example, regarding temperature, sensor data of the temperature of the adhesive surface (surface temperature of the detection target device 20) and the temperature on the opposite side of the adhesive surface (detection target) The sensor data of the ambient temperature of the device 20) is acquired.

The user terminal 30 is, for example, an information processing device such as a desktop PC, a tablet PC, a notebook PC, a smartphone, a mobile phone, a PDA (Personal Digital Assistant), or the like. In the user terminal 30, for example, the operation of the administrator of the detection target device 20 is accepted, and time-series graph data indicating the abnormality degree of the detection target device 20 is displayed on the screen.

[Abnormality monitoring device configuration]
Next, the configuration of the abnormality monitoring device 10 will be described with reference to FIG. FIG. 2 is a block diagram showing a configuration example of the abnormality monitoring device according to the first embodiment. As shown in FIG. 2, this abnormality monitoring device 10 has a communication processing unit 11, a control unit 12, and a storage unit 13. The processing of each unit of the abnormality monitoring device 10 will be described below.

The communication processing unit 11 controls communication regarding various types of information. For example, the communication processing unit 11 receives sensor data from the sensor 21 of the detection target device 20 and transmits the learning result to the user terminal 30.

The storage unit 13 stores data and programs required for various processes by the control unit 12, and particularly, those closely related to the present invention include a sensor data storage unit 13a and an abnormal data storage unit 13b. For example, the storage unit 13 is a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk.

The sensor data storage unit 13a stores the sensor data collected from the sensor 21 of the detection target device 20 by the collecting unit 12a described later. For example, the sensor data storage unit 13a stores the values of various sensor data in association with the time when the sensor data was acquired. Here, an example of data stored in the sensor data storage unit 13a will be described using the example of FIG. FIG. 3 is a diagram illustrating an example of data stored in the sensor data storage unit. As illustrated in FIG. 3, various sensors such as “acceleration (X axis), acceleration (Y axis), acceleration (Z axis), luminous intensity, and air temperature are associated with “time” when the sensor 21 acquires the sensor data. Store the value of data.

The abnormality data storage unit 13b stores the degree of abnormality calculated by a plurality of models described below. For example, the abnormal data storage unit 13b stores a value indicating the degree of abnormality calculated by each model in association with time as a learning result of each model having different machine learning methods.

The control unit 12 has an internal memory for storing a program that defines various processing procedures and the like and required data, and executes various processing by these, and particularly, as those closely related to the present invention, It has a collection unit 12a, a learning unit 12b, and an output unit 12c. Here, the control unit 12 is an electronic circuit such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

The collection unit 12a collects the sensor data acquired by the sensor 21 installed in the detection target device 20. Specifically, the collection unit 12a collects the sensor data of the sensor 21 installed in the detection target device 20, stores the sensor data in the sensor data storage unit 13a in association with the time.

For example, the collection unit 12a collects sensor data from the sensor 21 installed in the detection target device 20 such as a factory or office at regular intervals (for example, every one second), and stores the sensor data in the sensor data storage unit 13a. Here, the sensor data acquired by the sensor 21 is, for example, various data such as acceleration (three axes), luminous intensity, temperature, humidity, magnetic force, and pressure. Note that the collection unit 12a may collect the sensor data at any timing, such that the collection unit 12a may collect the sensor data at regular intervals, or may collect the sensor data when a predetermined condition is satisfied. You may

The learning unit 12b outputs the sensor data collected by the collection unit 12a to a plurality of models for outputting the degree of abnormality of the detection target device 20 and a plurality of models to which different machine learning methods are applied. Input each and perform machine learning of each model.

For example, the learning unit 12b uses MT (Mahalanobis Taguchi Method) method, ARIMA (Autoregressive Integrated Moving Average Model) method, LOF (Local Outlier Factor) method, and SST (Social Skills Training) method (singular spectrum conversion method) as machine learning methods. ), the automatic encoder method and the LSTM (Long Short-term Memory) method are applied to each model, and sensor data is input to perform unsupervised machine learning. The machine learning method is not limited to the above example, and any machine learning method may be applied.

The output unit 12c receives the sensor data collected by the collection unit 12a as an input, and outputs the abnormality degree of the detection target device 20 using each model. For example, when the output request of the abnormality degree is issued from the user terminal 30, the output unit 12c reads the abnormality degree data calculated by each model from the abnormality data storage unit 13b, and the abnormality degree calculated by each model. Is generated and the graph data is output to the user terminal 30.

Here, a screen display example in the abnormality monitoring device 10 according to the first embodiment will be described using the example of FIG. FIG. 4 is a diagram illustrating a screen display example in the abnormality monitoring device according to the first embodiment. In the example of FIG. 4, a plurality of graph data are displayed side by side. As illustrated in FIG. 4, as the “measurement data” measured by the sensor 21 on the left side of the screen, “acceleration (3 axes)”, “tilt (3 axes)”, “magnetic force (3 axes)”, “luminosity”. , "Temperature" and "atmospheric pressure" are displayed as time-series graph data.

Further, on the right side of the screen, as the "abnormality determined by AI", the model to which the "MT method" is applied, the model to which the "singular spectrum conversion method" is applied, the model to which the "LOF method" is applied, and the "ARIMA method" ”Is applied, the model to which “LSTM” is applied, and the time series graph data indicating the degree of abnormality calculated for each model to which the “auto encoder” is applied are displayed. In the graph of “abnormality degree determined by AI”, the threshold value is displayed with a thick line, and when the abnormality degree exceeds the thick line, it is determined to be abnormal. For example, in the model to which the “MT method” illustrated in FIG. 4 is applied, the threshold value is set to “50”. This threshold may be set manually, or may be automatically set by learning or the like.

As described above, in the abnormality monitoring device 10, by displaying a plurality of graph data side by side, the administrator of the detection target device 20 can easily compare the learning results of the models, and any learning method can be commonly used. It is possible to understand whether or not an abnormality has been determined. Further, in the abnormality monitoring device 10, when the administrator knows the time when the abnormality has actually occurred in the detection target device 20, it is easy to specify the model in which the abnormality can be properly detected at the corresponding time. Further, in the abnormality monitoring device 10, since the value of the sensor data is displayed on the left side of the screen, the causal relationship between the sensor data and the learning result can be grasped, and further, the items of the necessary sensor data and the unnecessary sensor data can be displayed. It is possible to facilitate selection of items.

Note that the display example of FIG. 4 is merely an example, and the present invention is not limited to this. For example, even if the results of the degree of abnormality calculated by each model are displayed in different colors in one graph, for example. Good. Thereby, in the abnormality monitoring device 10, it is possible to make it easy to see a portion commonly regarded as abnormal by a plurality of learning methods. Also, the arrangement of the graphs is not limited to the example of FIG. 4, and the arrangement of the graphs may be set in advance, may be designated by the user, or the frequency and accuracy of abnormality detection may be set. You may make it change dynamically, such as displaying a high thing on the upper left. Further, in the abnormality monitoring device 10, the administrator may select a model capable of properly detecting an abnormality so that only the graph of the selected model is displayed. That is, in the abnormality monitoring device 10, it is possible to select or preferentially display only the learning method that is compatible with the monitoring of the detection target device 20.

Next, the flow of the overall processing in the abnormality monitoring device 10 according to the first embodiment will be described using the example of FIG. FIG. 5 is a diagram illustrating an overall processing flow in the abnormality monitoring device according to the first embodiment. As illustrated in FIG. 5, the abnormality monitoring device 10 periodically collects sensor data from the sensor 21 of the detection target device 20 (see (1) in FIG. 5). Then, the abnormality monitoring device 10 inputs the collected sensor data to each of the models A to F each time the sensor data is collected, and performs unsupervised machine learning in parallel in real time ((2 in FIG. 5). )reference).

Then, when there is an output request from the user terminal 30, the abnormality monitoring device 10 outputs the abnormality degree calculated by each model to the user terminal 30 as a learning result (see (3) in FIG. 5). In this way, the abnormality monitoring device 10 makes a plurality of models learn at once in real time, and displays the learning results of the respective models on the user terminal 30. Therefore, it is difficult to acquire data at the time of an abnormality. Since even the device 20 can allow the administrator to simultaneously examine which model is the best, the abnormality of the detection target device 20 can be easily and accurately detected using the model to which the optimum learning method is applied. It is possible to monitor.

That is, depending on the type of the detection target device 20, the individual characteristics, the environment, and the like, which learning method is superior may change, but the abnormality monitoring device 10 displays the learning results of a plurality of models in this way. It is possible to select a learning method having good compatibility with the monitoring of the detection target device 20 or to display the learning method with priority. Further, in the abnormality monitoring device 10, since it is possible to save the trouble of preparing the teacher data and selecting the type of the sensor 21, it is possible to start the abnormality monitoring using the sensor 21 and machine learning at an early stage.

[Procedure for processing an abnormality monitoring device]
Next, an example of a processing procedure by the abnormality monitoring device 10 according to the first embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing an example of the flow of processing in the abnormality monitoring device according to the first embodiment.

As illustrated in FIG. 6, when the collection unit 12a of the abnormality monitoring device 10 collects the data of the sensor 21 in the detection target device 20 (Yes in step S101), the collected data is stored in the sensor data storage unit 13a (step S101). S102). Then, the learning unit 12b inputs the collected sensor data to a plurality of models to which different machine learning methods are applied (step S103), and performs machine learning of each model (step S104).

Then, the output unit 12c determines whether the output request of the abnormality degree which is the learning result of each model is received from the user terminal 30 (step S105), and when the output request of the abnormality degree is received (step S105 affirmative), The learning result of each model is output to the user terminal 30 (step S106). If the output request of the abnormality degree is not accepted (No at Step S105), the process is ended as it is. In addition, in the example of FIG. 6, the processes of steps S101 to S106 are described as a series of processes, but the processes of steps S101 to S104 and the processes of steps S105 to S106 may be performed separately.

(Effect of the first embodiment)
The abnormality monitoring device 10 according to the first embodiment is a plurality of models for collecting sensor data acquired by the sensor 21 installed in the detection target device 20 and outputting the abnormality degree of the detection target device 20. Then, the collected sensor data is input to a plurality of models to which different machine learning methods are applied, and machine learning of each model is performed. Then, the abnormality monitoring device 10 receives the collected data as an input and outputs the abnormality degree of the detection target device 20 using each model. Therefore, the abnormality monitoring device 10 can easily and accurately monitor the abnormality of the detection target device 20 even if the teacher data is not prepared.

Further, in the abnormality monitoring device 10, the administrator of the detection target device 20 compares the learning results of the models by outputting the time-series graph data showing the degree of abnormality calculated by each model to the display unit. It is possible to make it easier, for example, to easily identify the model in which the abnormality has been properly detected.

(Second embodiment)
In the above-described first embodiment, the case where the abnormality monitoring device 10 outputs the abnormality degree calculated by each model has been described, but the present invention is not limited to this. For example, when the abnormality of the detection target device 20 is detected by using the abnormality degree calculated by each model and the abnormality of the detection target device 20 is detected, the abnormality detection result of the detection target device 20 is displayed as the user terminal 30. You may make it output to.

Therefore, hereinafter, the abnormality monitoring device 10A according to the second embodiment detects an abnormality of the detection target device 20 by using a model for detecting an abnormality using the abnormality degree calculated by each model as input data. Then, a case where the abnormality detection result of the detection target device 20 is output to the user terminal 30 when the abnormality of the detection target device 20 is detected will be described. Note that description of the same configuration and processing as those of the abnormality monitoring device 10 according to the first embodiment will be omitted.

FIG. 7 is a block diagram showing a configuration example of the abnormality monitoring device according to the second embodiment. As illustrated in FIG. 7, the abnormality monitoring device 10A according to the second embodiment is different from the abnormality monitoring device 10 according to the first embodiment in that a detection unit 12d is included.

The detection unit 12d detects the abnormality of the detection target device 20 using the abnormality degree calculated by each model. Specifically, the detection unit 12d detects the abnormality of the detection target device 20 by using the model for detecting the abnormality, with the abnormality degree calculated by each model as input data.

When the detection unit 12d detects an abnormality in the detection target device 20, the output unit 12c outputs the abnormality detection result of the detection target device 20 to the user terminal 30. For example, the output unit 12c may display the abnormality detection result in a graph as in the case illustrated in FIG. 4, or output a message or alert indicating that the abnormality is detected to the user terminal 30. Good.

Next, the flow of the overall processing in the abnormality monitoring device 10A according to the second embodiment will be described using the example of FIG. FIG. 8 is a diagram illustrating an overall processing flow in the abnormality monitoring device according to the second embodiment. As illustrated in FIG. 8, the abnormality monitoring device 10A periodically collects sensor data from the sensor 21 of the detection target device 20 (see (1) in FIG. 8). Then, the abnormality monitoring device 10A inputs the collected sensor data to each of the models A to F every time the sensor data is collected, and performs unsupervised machine learning in parallel in real time ((2 in FIG. 8). )reference).

Then, the abnormality monitoring device 10A inputs the learning result of each of the models A to F to the model G for detecting the abnormality (see (3) in FIG. 8), and the abnormality of the detection target device 20 is detected by the model G. If is detected, the abnormality detection result of the detection target device 20 is output to the user terminal 30 (see (4) in FIG. 8). An administrator who confirms the abnormality detection result from the user terminal 30 may input feedback on the abnormality detection result.

As described above, the abnormality monitoring device 10A prepares the teacher data by performing the learning in real time with the plurality of models A to F, using the learning results of the respective models as the input data, and further performing the machine learning of the model G. Without performing the above, it is possible to detect the abnormality of the detection target device 20 easily and accurately. In the example of FIG. 8, the case where the learning results of all the models A to F are used has been described, but the present invention is not limited to this. For example, the administrator may select a model that is compatible with the detection target device 20. The learning result of only the model having a good compatibility with the detection target device 20 may be used by selecting or excluding the model having a bad compatibility.

Further, in the above description, the case where the learning result of each of the models A to F is input to the model G for detecting an abnormality and the machine learning of the model G is performed has been described, but the invention is not limited to this. Instead, for example, it is determined whether or not an abnormality has been detected based on the degree of abnormality detection output from each of the models A to F, and when a predetermined number or more (for example, two or more) of the models have detected the abnormality. May output the abnormality detection result to the user terminal 30.

[Procedure for processing an abnormality monitoring device]
Next, an example of a processing procedure performed by the abnormality monitoring device 10A according to the second embodiment will be described with reference to FIG. FIG. 9 is a flowchart showing an example of the flow of processing in the abnormality monitoring device according to the second embodiment.

As illustrated in FIG. 9, when the collection unit 12a of the abnormality monitoring device 10A collects the data of the sensor 21 in the detection target device 20 (Yes in step S201), the collected data is stored in the sensor data storage unit 13a (step S201). S202). Then, the learning unit 12b inputs the collected sensor data to a plurality of models to which different machine learning methods are applied (step S203), and performs machine learning of each model (step S204).

Then, the detection unit 12d determines the abnormality of the detection target device 20 by using the abnormality degree calculated by each model (step S205). As a result, when the detection unit 12d does not determine the abnormality of the detection target device 20 (No at Step S206), the process is ended. Further, when the detection unit 12d determines that the detection target device 20 is abnormal (Yes at Step S206), the output unit 12c determines that the detection target device 20 is detected when the detection unit 12d detects an abnormality. The abnormality detection result of 20 is output to the user terminal 30 (step S207).

(Effects of the second embodiment)
The abnormality monitoring device 10A according to the second embodiment detects the abnormality of the detection target device 20 by using the model for detecting the abnormality with the abnormality degree calculated by each model as input data, and detects the abnormality. When the abnormality of the detection target device 20 is detected, the abnormality detection result of the detection target device 20 is output to the user terminal 30, so that the abnormality of the detection target device 20 can be detected easily and accurately even if the teacher data is not prepared. It is possible to detect.

That is, in the abnormality monitoring device 10A, for example, daily sensor data is acquired from the sensor 21 of the detection target device 20, machine learning of each model is performed, and the abnormality is detected without learning the sensor data at the time of abnormality. It is possible to notify the administrator.

Further, in the above description of the first embodiment and the second embodiment, the example of the unsupervised data in which the present invention is preferably effective is described, but the present invention is not limited to this, and the teaching data is not limited to this. Of course, if it can be prepared, it can be applied to supervised machine learning, and in that case, higher accuracy can be obtained as compared with ordinary supervised machine learning by a single learned model.

(System configuration, etc.)
Further, each component of each device shown in the drawings is functionally conceptual and does not necessarily have to be physically configured as shown. That is, the specific form of distribution/integration of each device is not limited to that shown in the figure, and all or part of the device may be functionally or physically distributed/arranged in arbitrary units according to various loads and usage conditions. It can be integrated and configured. Further, each processing function performed by each device may be implemented entirely or in part by a CPU and a program that is analyzed and executed by the CPU, or may be realized as hardware by a wired logic.

Further, of the processes described in the present embodiment, all or part of the processes described as being automatically performed may be manually performed, or the processes described as being manually performed. Alternatively, all or part of the above can be automatically performed by a known method. In addition, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified.

(program)
It is also possible to create a program in which the processing executed by the abnormality monitoring device described in the above embodiment is described in a computer-executable language. For example, it is possible to create an abnormality monitoring program in which the processing executed by the abnormality monitoring apparatus 10 according to the embodiment is described in a computer-executable language. In this case, the computer executes the abnormality monitoring program to obtain the same effect as that of the above embodiment. Further, even if the abnormality monitoring program is recorded in a computer-readable recording medium, and the abnormality monitoring program recorded in the recording medium is read by a computer and executed, the same processing as that of the above-described embodiment is realized. Good.

FIG. 10 is a diagram illustrating a computer that executes an abnormality monitoring program. As illustrated in FIG. 10, the computer 1000 has, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. However, these units are connected by a bus 1080.

The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012, as illustrated in FIG. The ROM 1011 stores, for example, a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to the hard disk drive 1090, as illustrated in FIG. The disk drive interface 1040 is connected to the disk drive 1100, as illustrated in FIG. For example, a removable storage medium such as a magnetic disk or an optical disk is inserted into the disk drive 1100. The serial port interface 1050 is connected to, for example, a mouse 1110 and a keyboard 1120 as illustrated in FIG. The video adapter 1060 is connected to, for example, the display 1130, as illustrated in FIG.

Here, as illustrated in FIG. 10, the hard disk drive 1090 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. That is, the above-mentioned abnormality monitoring program is stored in, for example, the hard disk drive 1090 as a program module in which a command executed by the computer 1000 is described.

The various data described in the above embodiments are stored as program data in, for example, the memory 1010 or the hard disk drive 1090. Then, the CPU 1020 reads the program module 1093 and the program data 1094 stored in the memory 1010 or the hard disk drive 1090 into the RAM 1012 as necessary, and executes various processing procedures.

The program module 1093 and the program data 1094 related to the abnormality monitoring program are not limited to being stored in the hard disk drive 1090, but may be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive or the like. Good. Alternatively, the program module 1093 and the program data 1094 related to the abnormality monitoring program are stored in another computer connected via a network (LAN (Local Area Network), WAN (Wide Area Network), etc.), and the network interface 1070 is used. It may be read by the CPU 1020 via the.

The above-described embodiments and modifications thereof are included in the invention described in the claims and equivalents thereof, as well as included in the technology disclosed in the present application.

10, 10A Abnormality monitoring device 11 Communication processing unit 12 Control unit 12a Collection unit 12b Learning unit 12c Output unit 12d Detection unit 13 Storage unit 13a Sensor data storage unit 13b Abnormal data storage unit 20 Detection target device 21 Sensor 30 User terminal 100 Abnormality monitoring system

Claims (3)

A plurality of models for outputting the abnormality degree of the detection target device, for each of a plurality of models to which different machine learning method is applied, the data acquired by the sensor installed in the detection target device, respectively A learning unit that inputs and performs machine learning of each model,
With the data acquired by the sensor as input, time series graph data indicating the degree of abnormality of the detection target device is created by using each of the models, and an output unit that displays a plurality of graph data on the same screen. An abnormality monitoring device comprising: An abnormality monitoring method executed by an abnormality monitoring device, comprising:
A plurality of models for outputting the abnormality degree of the detection target device, for each of a plurality of models to which different machine learning method is applied, the data acquired by the sensor installed in the detection target device, respectively A learning process of inputting and performing machine learning of each model,
With the data acquired by the sensor as input, time series graph data indicating the abnormality degree of the detection target device is created using each of the models, and an output step of displaying a plurality of graph data on the same screen , An abnormality monitoring method comprising: A plurality of models for outputting the abnormality degree of the detection target device, for each of a plurality of models to which different machine learning method is applied, the data acquired by the sensor installed in the detection target device, respectively A learning step of inputting and performing machine learning of each model,
With the data acquired by the sensor as input, time series graph data indicating the abnormality degree of the detection target device is created using each of the models, and an output step of displaying a plurality of graph data on the same screen , An abnormality monitoring program that causes a computer to execute.

Images