KR20220039595A - Multi point block remote monitoring system for watching unauthorized discharge of toxicity waste water based on internet of things and artifical intelligence - Google Patents

Abstract

Disclosed is a multi-point block remote monitoring system using IoT and AI. The remote monitoring system comprises: at least one IoT sensor which divides a route of sewage to be discharged into a river into a plurality of blocks, provided at at least one point-type monitoring place of each divided block, and is capable of monitoring, in real-time, components of the sewage; a first interface unit which receives component values of the sewage detected by the at least one sensor; a gateway having a first processor for controlling the first interface unit; and a server having a second processor that tracks pollution sources of the sewage based on big data in which sewage pollution sources are mutually matched according to the component values of the sewage and component data received from an IoT server. According to the present invention, the remote monitoring system is capable of preventing harmful wastewater from polluting the river, thereby constructing a clean water environment.

Description

MULTI POINT BLOCK REMOTE MONITORING SYSTEM FOR WATCHING UNAUTHORIZED DISCHARGE OF TOXICITY WASTE WATER BASED ON INTERNET OF THINGS AND ARTIFICAL INTELLIGENCE

The present invention relates to a multi-point block remote monitoring system using IoT and AI that can monitor the unauthorized discharge of toxic wastewater in real time and quickly find the source of its pollution and block the discharge.

Recently, water quality management such as the use of water resources, treatment of water and wastewater, and prevention of water pollution has been raised as an important task. Factories or livestock establishments must purify the generated wastewater below the permitted standards and discharge it into rivers. However, the number of cases of unauthorized discharge due to an increase in maintenance cost or breakdown of the purification system is increasing. The Environmental Management Corporation is investigating the fact of pollution due to the death of fish in the river due to the unauthorized discharge of such toxic or harmful wastewater and is searching for the source of the pollution. Alternatively, environmental officials are monitoring contamination by collecting and analyzing wastewater that flows into rivers regularly or irregularly on business trips.

However, in this conventional method for monitoring and managing wastewater, it is difficult to find the source of the pollution in the state where the wastewater has already polluted the river, and even if it is difficult to find, it is impossible to restore the pollution of the river to its original state because it is already contaminated. there is. In addition, the number of cases of contamination of water supply sources due to the unauthorized discharge of toxic wastewater is increasing, posing a threat to the health of citizens.

It is an object of the present invention to provide a multi-point block remote monitoring system using IoT and AI that can analyze the discharge of toxic or harmful wastewater in real time and quickly and accurately find the contamination source to prevent further contamination.

A multi-point type block remote monitoring system using IoT and AI for achieving the above-mentioned tasks is provided. The remote monitoring system divides the path of sewage discharged to the river into a plurality of blocks, is provided at at least one point monitoring point of each divided block, and at least one IoT sensor capable of detecting the components of the sewage in real time; A gateway having a first interface unit for receiving a sewage component value sensed from at least one sensor and a first processor for controlling the first interface unit, and big data and the IoT in which sewage pollution sources according to the component values of the sewage are matched with each other and a server having a second processor that tracks a source of pollution of sewage based on the component data received from the server.

The big data may include a lookup table in which a pollutant associated with each component data is matched.

The second processor may build the big data using Deep Learning or Machine Learning among the implementation methods of Artificial Intelligence.

The second processor may identify whether the component data exceeds a normal reference value, and infer a water pollution source.

The second processor may predict an unauthorized discharge through another route in which the system is not installed through mathematical modeling using a correlation between the water quality data of the dotted point and the water quality data of the block point.

The second processor may transmit a message to the manager by dividing the pollution degree of the sewage into a detection step, a caution step, and a warning step according to the amount of the new component data.

The multi-point sewage block monitoring system according to the present invention can prevent further progress of contamination by predicting the cause of contamination at the initial stage of contamination by inspecting the components of sewage in real time and tracking the changing components of sewage. Therefore, it is possible to build a clean water environment by preventing toxic or harmful wastewater from polluting rivers.

In addition, the water quality big data (BIG DATA) collected in the multi-point type sewage block monitoring system according to the present invention and the result of water quality data processing using artificial intelligence (Artificial Intelligence) are provided as new public data to a water management institution to provide a water manager The level of management can be increased, and water resource management costs can be reduced by making national infrastructure intelligent using IoT, artificial intelligence, public data, and big data.

1 is a diagram illustrating a multi-point block based on a sewage discharge path.
FIG. 2 is a diagram illustrating block B-2 of FIG. 1 .
3 is a view showing a sewage discharge path of a multi-point block.
4 is a block diagram illustrating a multi-point type block remote monitoring system according to an embodiment of the present invention.
5 is a flowchart illustrating a multi-point type block remote monitoring method according to an embodiment of the present invention.

Hereinafter, a multi-point type block remote monitoring system according to an embodiment of the present invention will be described with reference to the accompanying drawings.

1 is a diagram illustrating a multi-point block based on a sewage discharge path.

Hereinafter, a multi-point type block remote monitoring system according to an embodiment of the present invention will be described with reference to the accompanying drawings.

1 is a diagram illustrating a multi-point block based on a sewage discharge path.

Factories, livestock farms, and commercial or residential buildings discharge sewage, including wastewater, through a sewage pipe after self-cleaning treatment. At this time, the purified sewage flows into the river through the sewer pipe.

Referring to Figure 1, based on the flow of sewage pipe through which sewage is discharged in a certain area densely populated with factories, livestock farms, commercial or household buildings, a plurality of blocks, for example, A-1 to A-3 blocks, B-1 to It can be divided into B-9 blocks, C-1 to C3 blocks, D1 to D3 blocks, and E1 to E6 blocks.

FIG. 2 is an enlarged view of block B-2 of FIG. 1 .

Referring to FIG. 2 , sensors 1 for specifying the components of sewage may be installed in a sewage pipe through which purified sewage flows in a number of factories, farms or buildings located in block B-2, that is, a point-shaped monitoring point.

3 is a view showing a sewage discharge path of a multi-point block.

Referring to FIG. 3 , an area for discharging sewage may be divided into blocks.

Block (B) may include a plurality of first sewage discharge sources (B-21, B-22, B-23, ...). The plurality of first sewage discharge sources (B-21, B-22, B-23, ...) may each merge into the first sub sewage pipe SB1 through the first branch sewer pipe B1. The first point type monitoring point b1p is located in the first branch sewer pipe B1, and a sensor 1, for example, an NTU, pH, TDS sensor, etc. may be installed.

The sewage flowing in the sub sewage pipe SB1 may be merged into the main sewage pipe.

A block-type sensor and gateway for monitoring the block section (main sewer pipe) may be installed at the end of the main sewer pipe. The block-type sensor may include a TOC sensor, a COD sensor, and the like.

The point monitoring point may also be located in the first through the sub sewer pipe or the main sewage pipe.

4 is a block diagram illustrating a multi-point type block remote monitoring system according to an embodiment of the present invention.

Referring to FIG. 4 , the multi-point block monitoring system includes an IoT sensor 1 , a gateway 2 , and a server 3 .

The IoT sensor 1 may be installed at each point-type monitoring point or block-type monitoring point of the sewage block as shown in FIG. 3 .

The IoT sensor 1 can measure heavy metals, chemicals, turbidity, acidity, alkalinity, etc. contained in sewage.

The IoT sensor 1 may be acquired in real time as raw data of components contained in sewage. The IoT sensor 1 may include a TDS, pH, NTU sensor, etc. installed at a point type monitoring point.

The IoT sensor 1 may include a TOC sensor, a COD sensor, etc. installed at the block-type monitoring point.

The IoT sensor 1 may include, for example, an Ethernet communication module for transmitting the measured raw data of sewage components to the gateway 2 .

The gateway 2 may include a first interface unit 21 , a first processor 22 , and a first memory 23 .

The first interface unit 22 may collect raw sewage data obtained from a plurality of IoT sensors 1 and transmit it to the server 3 through the wired/wireless Internet.

The first interface unit 22 may include a wired interface unit and a wireless interface unit.

The wired interface unit may include a terrestrial/satellite broadcasting antenna connection tuner for receiving a broadcast signal, a cable broadcasting cable connection interface, and the like.

The wired interface unit may include a connection interface of an optical cable device.

The wired interface unit may include a connection interface of a wired network device such as Ethernet. The wireless interface unit is Wi-Fi, Bluetooth, ZigBee, Z-wave, RFID, WiGig, WirelessHD, Ultra-Wide Band (UWB), Wireless USB, Near Field (NFC) Communication), etc., may include a connection interface of a wireless network device.

The wireless interface unit may include an IR transceiver module for transmitting and/or receiving a remote control signal.

The wireless interface unit may include a mobile communication device connection interface such as 2G to 5G.

The first processor 22 may control the first interface unit 22 to transmit the raw sewage component raw data obtained from the IoT sensor 1 to the server 2 through the wired/wireless Internet.

The first processor 22 may be implemented in a form included in a main SoC that is embedded in the gateway 2 and mounted on a PCB.

The first processor 22 may generally control the components of the gateway 2 .

The first processor 22 may transmit the collected raw sewage component data to the server 3 .

The first processor 22 loads at least a part of the control program including instructions from the nonvolatile memory in which the control program is installed into the volatile memory, and executes the loaded control program instructions. It includes a processor, and may be implemented as, for example, a central processing unit (CPU), an application processor (AP), or a microprocessor.

The first processor 22 may include a single core, a dual core, a triple core, a quad core, and multiple cores thereof. A plurality of first processors 22 may be provided. The first processor 22 may include, for example, a main processor and a sub-processor operating in a sleep mode (eg, a mode in which only standby power is supplied). In addition, the processor, ROM and RAM are interconnected through an internal bus.

The first processor 22 may be implemented in a form included in a main SoC mounted on an embedded PCB.

The control program may include program(s) implemented in the form of at least one of a BIOS, a device driver, an operating system, firmware, a platform, and an application program (application). The application program may be installed or stored in advance when the gateway 2 is manufactured, or may be installed based on the received data by receiving data of the application program from the outside at the time of later use. Data of the application program may be downloaded to the gateway 2 from, for example, an external server such as an application market. Such a control program, an external server, etc. is an example of a computer program product, but is not limited thereto.

The first memory 23 is a computer-readable recording medium, in which unlimited data is stored. The first memory 23 is accessed by the first processor 22, and reading, writing, modifying, deleting, updating, and the like of data are performed by them.

The first memory 23 may store raw sewage component data transmitted in real time from a plurality of IoT sensors 1 .

The first memory 23 may include an operating system, various applications executable on the operating system, additional data, and the like.

The first memory 23 includes a non-volatile memory in which the control program is installed, and a volatile memory in which at least a part of the installed control program is loaded.

The first memory 23 may be a flash memory type, a hard disk type, a multimedia card micro type, or a card type memory (eg, SD or XD memory). , RAM (Random Access Memory) SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) Magnetic Memory, Magnetic It may include at least one type of storage medium among a disk and an optical disk.

The server 3 may include a second interface unit 31 , a second processor 32 , and a second memory 33 .

The second interface unit 31 may collect raw sewage component data from a plurality of IoT sensors 1 in real time.

Since the configuration of the second interface unit 31 is similar to that of the first interface unit 21 , a description thereof will be omitted.

The second processor 32 generally controls each component of the server 3 . The second processor 32 analyzes and processes raw sewage component raw data in real time to construct a big data database. The second processor 32 analyzes raw sewage component data to see if there are any new components other than standard components, whether the TOC value of the sewage is out of the acceptable industrial wastewater discharge standard value, whether there is a change in alkalinity or acidity of the sewage, heavy metal substances in the sewage Identifies whether this exists. If a change in the water quality of sewage is found, the pollutant source can be tracked using big data that matches the water pollutant source according to the component change.

When the water quality change source is tracked, the second processor 32 prevents contamination of the water intake source (waterworks) due to toxic sewage when a water purification plant (waterworks) is located around the toxic sewage flowing through the point-type monitoring point or block-type monitoring point. Notify the manager in charge so that At this time, the notification to the water treatment plant (waterworks) may be made by reflecting whether the detected component exceeds the reference value, and whether the component change is continuously maintained, increased, or decreased.

When the sewage pollution source is tracked, the second processor 32 may deliver a warning message or mail to an external device (smartphone, computer) of an environmental monitoring manager or a manager of the sewage pollution source. The manager may include a sewage general manager, a manager of a point where sewage pollution is observed, and the like.

The second processor 32 collects data, analyzes the collected data, processes at least a portion of the collected data, and generates result information as a mathematical modeling rule-based or artificial intelligence algorithm. Machine learning, a neural network , or by using at least one of a deep learning algorithm.

For example, the second processor 32 may perform the functions of a learning unit and a recognition unit. The learning unit may, for example, perform a function of generating a learned neural network, and the recognition unit may perform a function of recognizing (or reasoning, predicting, estimating, determining) data using the learned neural network network. The learning unit may create or update the neural network. The learning unit may acquire learning data to generate a neural network. For example, the learning unit may acquire learning data from a memory or from the outside. The training data may be data used for learning of the neural network.

The learning unit may perform a preprocessing operation on the acquired training data before training the neural network using the training data, or may select data to be used for learning from among a plurality of training data. For example, the learning unit may process the learning data into a preset format, filter it, or add/remove noise to process the learning data into a form suitable for learning. The learned neural network network may be composed of a plurality of neural network networks (or layers). Nodes of the plurality of neural networks have weights, and the plurality of neural networks may be connected to each other so that an output value of one neural network is used as an input value of another neural network. Examples of neural networks include Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN) and It can include models such as Deep Q-Networks.

Meanwhile, the recognizer may acquire target data. The target data may be obtained from a memory or externally. The target data may be data to be recognized by the neural network. The recognizer may perform preprocessing on the acquired target data before applying the target data to the learned neural network, or select data to be used for recognition from among a plurality of target data. For example, the recognition unit may process the target data into a preset format, filter, or add/remove noise to process the target data into a form suitable for recognition. The recognizer may obtain an output value output from the neural network by applying the preprocessed target data to the neural network. According to various embodiments, the recognition unit may acquire an academic rate value (or a reliability value) together with an output value.

The second processor 32 loads at least a part of the control program including instructions from the nonvolatile memory in which the control program is installed into the volatile memory, and executes the loaded control program instructions. It includes a processor, and may be implemented as, for example, a central processing unit (CPU), an application processor (AP), or a microprocessor.

The second processor 32 may include a single core, a dual core, a triple core, a quad core, and multiple cores thereof. A plurality of second processors 32 may be provided. The second processor 32 may include, for example, a main processor and a sub-processor operating in a sleep mode (eg, a mode in which only standby power is supplied). In addition, the processor, ROM and RAM are interconnected through an internal bus.

The second processor 23 may be implemented in a form included in a main SoC mounted on an embedded PCB.

The control program may include program(s) implemented in the form of at least one of a BIOS, a device driver, an operating system, firmware, a platform, and an application program (application). The application program may be installed or stored in advance when the server 3 is manufactured, or may be installed based on the received data by receiving data of the application program from the outside at the time of later use. The data of the application program may be downloaded to the server 2 from an external server such as, for example, an application market. Such a control program, an external server, etc. is an example of a computer program product, but is not limited thereto.

The second memory 33 is a computer-readable recording medium and stores non-limited data. The memory 24 is accessed by the second processor 23, and reading, writing, modifying, deleting, updating, and the like of data are performed by them.

The second memory 33 stores raw sewage data detected at each point-type monitoring point or block-type monitoring point and its analysis information.

The second memory 33 includes a lookup table that matches pollutant sources (factories, livestock farms, home or commercial buildings) for each component of sewage. The second processor 32 may quickly and accurately track the pollutant source of the analyzed sewage component with reference to the lookup table.

5 is a flowchart illustrating a multipoint block remote monitoring method according to an embodiment of the present invention.

In step S1, the IoT sensor 1 performs an Ethernet communication session connection with the gateway 2 .

In step S2, the gateway 2 performs a wireless communication session connection with the server 3 using Lora, NB-IoT, 4G, 5G, and the like.

In step S3 , the IoT sensor 1 is registered with the gateway 2 , and the controller information is generated by the gateway 2 .

In step S4 , the gateway 2 transmits IoT controller information including registration information of the IoT sensor 1 , that is, location information and sewage discharge source information, to the server 3 .

In step S5 , the IoT sensor 1 transmits raw sewage component raw data to the gateway 2 .

In step S6, the gateway 2 transmits raw sewage component raw data collected from the IoT sensor 1 to the server 3, and the server 3 builds a database.

In step S7, the server 3 analyzes raw sewage component raw data and tracks the sewage pollution source using big data and artificial intelligence.

In step S8, the server 3 transmits a message or mail to the manager's mobile device or computer 4 regarding the source of sewage pollution.

Referring back to FIG. 3, the plurality of first sewage discharge sources (B-21, B-22, B-23, ...) merge into the first sub sewage pipe (SB1) through the first branch sewage pipe (B1), respectively, The IoT sensor 1 may be disposed at the first point type monitoring point b1p located in the first branch sewer pipe B1. At this time, it is practically very difficult for the IoT sensor 1 to exhibit a performance sufficient to detect all components included in the sewage. Therefore, at the first point type monitoring point (b1p) It is preferable to limit the installed IoT sensor 1 to a target sensor that can detect only a specific target component. The target component can be found by identifying the first sewage discharge source (B-21, B-22, B-23, ...) and the component materials they use in advance. This prior identification can also give the meaning of warning to the first sewage discharge source (B-21, B-22, B-23, ...). In addition, the local government may induce the first sewage discharge source (B-21, B-22, B-23, ...) to register or report in advance in the case of a change or introduction of a new component substance.

Sewage can be transported through open air above ground and underground sewer pipes. Contamination of sewage may be measured by the ground unmanned monitoring device 5 installed in the open air on the ground and the underground unmanned monitoring device 6 installed in the underground sewage pipe.

Hereinafter, the ground unmanned detection device 5 for detecting sewage pollution flowing on the ground in real time will be described in detail with reference to FIG. 6 .

The ground unmanned sensing device 5 includes a pole 51 installed at a point-shaped monitoring point, a solar cell 52 installed on the top of the pole 51, a sensor power box 53 provided on the pole 51, and a pole It may include a sensor support part 54 installed horizontally on the upper part of the 51 , and a sensor assembly 55 provided on the sensor support part 54 .

The pole 51 is positioned high enough from the sewage surface to protect the sensor assembly 55 from the rapid current or foreign substances contained in the rapid current, and the solar cell 52 is moved to the high position because the water level of the sewage changes with each season. to install.

The solar cell 52 receives power for operating the sensor driver 551, the sensor 553, and the communication module for transmitting the raw data extracted by the sensor 553 to the gateway (2 in FIG. 4). can produce

The sensor power box 53 may be provided with a battery capable of charging and discharging, and a communication module for transmitting raw data extracted by the sensor 553 to the gateway 2 .

The sensor support unit 54 has a tubular shape through which a power line connecting the sensor driving unit 551 and a battery and a communication line connecting the sensor 553 and a communication module may pass. The sensor assembly 55 may be installed in the center support part 54 .

The sensor assembly 55 may include a sensor driver 551 , a sensor connection line 552 , and a sensor 553 .

The sensor driving unit 551 may include a drum capable of rotating so that the sensor connection wire 552 is wound as shown in FIG. 6 (a) or unwound as shown in FIG. 6 (b) and a motor capable of rotating the drum there is.

The sensor connection line 552 is flexible to be wound around the drum, and may include a communication line connected to the communication module.

The sensor 553 may be provided at the end of the sensor connection line 552 to measure the pollutant component of the sewage in a state submerged in the sewage.

The above-described unmanned ground detection device 5 may descend at a set time interval to measure sewage contamination and transmit it to the gateway 2 . Such an unmanned ground detection device 5 does not require mobilization of manpower for measurement and can measure sewage contamination stably at predetermined time intervals regardless of the level of sewage according to the season.

Hereinafter, the underground unmanned detection device 6 for detecting sewage contamination flowing underground in real time will be described in detail with reference to FIG. 7 .

The underground unmanned detection device 6 may be provided in the manhole 60 provided in the stratum below the ground. The manhole 60 may have a structure that can be opened and closed in order to repair the unmanned underground detection device 6 in case of failure.

The underground unmanned detection device 6 is a manhole 60 dug to pass between the ground and the sewage pipe at the monitoring point of the sewage pipe, a pillar 61 installed in the manhole 60, and a solar cell installed on the top of the pillar 61 ( 62), the sensor power box 63 provided at the lower end of the pillar 61, and the sensor assembly 64 provided in the sewage pipe from the sensor power box 63 may be included.

The pillar 61 is for installing the solar cell 62 outside the strata to supply power to the sensor power box 63 . The pillar 61 is detachable so that power between the sensor power box 63 and the sensor assembly 64 can be connected or disconnected.

The solar cell 62 may generate power for operating the sensor 642 and a communication module for transmitting raw data extracted by the sensor 642 to an external device.

The sensor power box 63 may be provided with a rechargeable battery and a communication module for transmitting raw data extracted by the sensor 642 to an external device.

The sensor assembly 64 may include a sensor connection line 641 and a sensor 642 .

The sensor connection line 642 is flexible to move according to the flow of sewage, and may include a communication line that can be connected to or separated from the communication module.

The sensor 642 may be provided at the end of the sensor connection line 641 to measure the contamination component while submerged in tap water.

The above-described unmanned underground detection device 6 may measure sewage contamination every set time and transmit it to the gateway. Such an unmanned underground detection device 6 does not require mobilization of manpower for measurement, and can stably measure the contamination of sewage flowing in a sewage pipe buried underground at a predetermined time interval.

In the above, preferred embodiments of the present invention have been illustrated and described, but the present invention is not limited to the specific embodiments described above, and it is common in the technical field to which the present invention pertains without departing from the gist of the present invention as claimed in the claims. Various modifications may be made by those having the knowledge of, of course, and these modified embodiments should not be individually understood from the technical spirit or perspective of the present invention.

1: IoT sensor
2: Gateway
21: first interface unit
22: first processor
23: first memory
3: Server
31: second interface unit
32: second processor
33: second memory
4: External device

Claims (5)

at least one IoT sensor that divides the path of sewage discharged into the river into a plurality of blocks and is provided at at least one point-shaped monitoring point of each divided block and can detect the components of the sewage in real time;
a gateway having a first interface for receiving the sewage component value sensed from the at least one sensor and a first processor for controlling the first interface; and
Multi-point block sewage using IoT and AI including a server having a second processor that tracks the source of sewage pollution based on big data matched with each other and the component data received from the gateway according to the component value of the sewage remote monitoring system. The method of claim 1,
The big data is a multi-point block sewage remote monitoring system using IoT and AI that includes a lookup table that matches the pollutant source associated with each component data. The method of claim 1,
The second processor is a multi-point block sewage remote monitoring system using IoT and AI to build the big data using Deep Learning or Machine Learning among the implementation methods of Artificial Intelligence. . The method of claim 1,
The second processor identifies whether there is a new component different from the reference component from the component data, and identifies whether the component data exceeds the discharge allowable standard value to track the water pollution source Multi-point block sewage remote monitoring system using IoT and AI . 5. The method of claim 4,
The second processor is a multi-point block sewage remote monitoring system using IoT and AI that transmits a message to the manager by dividing it into a detection step, a caution step, and a warning step based on the amount of the new component data according to the degree of contamination of the sewage.

Images