A real-time state sensing method for online monitoring of water valve

Abstract

This invention relates to the field of valve monitoring technology, and in particular to a real-time status perception method for online monitoring of water valves. The method includes: constructing a real-time valve status monitoring strategy to adapt to valve status monitoring under different application scenarios; optimizing the target valve status acquisition strategy and valve coordination strategy based on the water quality characteristics flowing through the target valve in the target area; during the execution of the valve control strategy, sensing the valve status under multiple water quality scenarios by combining scenario requirements and the pipeline topology of the target area; and predicting the future valve status based on the valve status under multiple water quality scenarios.

Description

Technical Field

[0001] This invention relates to the field of valve monitoring technology, and in particular to a real-time status sensing method for online monitoring of water valves. Background Technology

[0002] A water system is an integrated system of engineering facilities, management agencies, policies and regulations used to manage, treat, transport and distribute water resources (mainly drinking water) as well as to collect, treat and discharge sewage (wastewater) and rainwater.

[0003] Monitoring the pipeline network and valves in a water system is a core element in ensuring a safe, stable, and efficient water supply. This monitoring relies heavily on automation, information technology, and intelligent systems to construct a multi-layered monitoring framework. The core monitoring targets include the pipeline network and valves. Valve monitoring includes their open / closed status, opening degree (e.g., regulating valves and pressure reducing valves), water flow through the valves, and water pressure.

[0004] Current technologies for valve monitoring do not take into account the environment in which the valve is located or the impact of the water quality flowing through the valve on valve operation and valve status acquisition, resulting in insufficient accuracy in valve status perception. Summary of the Invention

[0005] This invention provides a method for accurately obtaining the valve status by adapting to the water quality characteristics of the area where the valve is located.

[0006] The technical solution proposed in this invention is: a real-time status sensing method for online monitoring of water valves, the method comprising:

[0007] Develop a real-time valve status monitoring strategy to adapt to valve status monitoring in different application scenarios;

[0008] Based on the water quality characteristics flowing through the target valve within the target area, optimize the target valve status acquisition strategy and valve coordination strategy;

[0009] In the execution of valve control strategies, the valve status under multiple water quality scenarios is perceived by combining scenario requirements and the pipeline topology of the target area.

[0010] Based on the valve status under various water quality scenarios, predict the future state of the valve.

[0011] Preferably, the strategy for constructing a real-time valve status monitoring system includes:

[0012] Construct a valve-pipeline network model using valves as nodes;

[0013] Intelligent monitoring strategies are built based on valve-pipeline network diagram models.

[0014] Preferably, the step of constructing a valve-pipeline network model with valves as nodes includes:

[0015] Retrieve pipeline network information from the database;

[0016] Constructing a pipeline network-valve diagram model, including:

[0017] With valves as nodes, and pipeline scheduling and valve operation as composite edges;

[0018] Then, the directed graph of the pipeline system ,in, Represents a set of nodes; Represents the set of edges;

[0019] ; ; ;

[0020] in, Indicates the target valve; Indicates the coordinates of the target valve. Indicate the type of the target valve; Represents the state vector of the target valve; Indicates the valves adjacent to the target valve; Represents the operation vector;

[0021] ;in, This indicates the valve opening degree, flow rate, pressure, and temperature.

[0022] operation vector ;in, Indicates from valve To valve The change in valve opening. Indicates valve and valves Operation time interval; Indicates from valve Switch to valve The scheduling cost.

[0023] Preferably, the intelligent monitoring strategy based on the valve-pipeline network diagram model includes:

[0024] Constructing the scheduling objective function ; This represents the actual pressure vector of the node. Represents the target pressure vector; Represents the L2 norm;

[0025] This represents the vector of valve opening change. ,in, Indicates the number of valve scheduling operations;

[0026] Represents the flow vector between nodes; Represents the water demand vector; Describing the L1 norm, These represent pressure weight, flow weight, and cost weight, respectively.

[0027] The non-dominated sorting genetic algorithm (NSGA) is used to solve the objective function and obtain the optimal solution to the objective function, namely, the optimal actual pressure vector, the optimal flow vector between nodes, the scheduling cost, and the change in opening degree.

[0028] Based on the valve opening change and valve status, the valve opening is optimized to achieve the optimal valve opening, thereby ensuring that the water delivery in the pipeline network reaches the optimal transmission state.

[0029] Preferably, the strategy for obtaining the target valve status and the valve coordination strategy based on the water quality characteristics flowing through the target valve within the target area include:

[0030] Obtain water quality characteristics of the target area and construct a water quality feature vector. ;in, These represent the normalized values ​​of turbidity, residual chlorine, pH, and conductivity, respectively.

[0031] Using water quality feature vectors and a clustering algorithm, water quality is classified into drinking water, reclaimed water, rainwater, and industrial water.

[0032] Set water quality risk index ;in, Indicates parameter weights, Indicates the pollutant weighting. Indicates the weighted sum of pollutants;

[0033] Valve status collection frequency is set according to water quality. ;in, Indicates the sensitivity coefficient; Indicates the basic sampling frequency of valve status; Indicates the valve status adaptive sampling frequency; water quality change rate. ;

[0034] Based on the water quality risk index, optimize the valve status acquisition frequency, including:

[0035] when hour, ;in, Indicates the frequency weighting coefficient;

[0036] when hour, ;

[0037] when hour, ;

[0038] in, These represent the maximum risk index and the minimum risk index, respectively.

[0039] Preferably, the strategy for obtaining the target valve status and the valve coordination strategy based on the water quality characteristics flowing through the target valve within the target area further includes:

[0040] Optimize valve coordination strategies, including:

[0041] Construct a valve collaborative optimization model:

[0042] Coordination objective function: ;

[0043] Constraints: ;in, ; Represents the target water quality feature vector; Indicates the difference in water quality characteristics due to mixing; This indicates the actual pressure at the node under the current water quality conditions; These represent the pressure weight, flow weight, and cost weight of the current water quality, respectively. The dimension of the water quality feature vector;

[0044] The NSGA algorithm is used to solve the coordination objective function to obtain the optimal valve opening change under the current water quality.

[0045] Preferably, in the execution of the valve control strategy, the sensing of valve status under multiple water quality scenarios, combined with scenario requirements and the pipeline topology of the target area, includes:

[0046] Constructing the topology-water quality coupled graph structure: ;in, Represents the water quality characteristic matrix. ;in, Indicates the number of water quality feature vectors;

[0047] Will The input is fed into a pre-trained convolutional network model, which outputs the scene type of the target region to identify the scene of the target region; the scene type of the target region includes: normal scheduling, emergency scheduling, and water pollution.

[0048] Based on the scene type of the target area, set the node perception focus and edge perception focus, including:

[0049] In a normal scheduling scenario, the node's perception focus includes traffic and pressure; the edge's perception focus is the traffic gradient.

[0050] In emergency dispatch scenarios, the node's perception focus includes the pressure change; the edge's perception focus is the pressure gradient.

[0051] In the case of water pollution, the node's sensing focus includes pollutant concentration; the sensing focus changes to valve opening.

[0052] After setting the node's sensing focus, the fusion state of the node is calculated and obtained based on the water quality type. ;in, Indicates the number of parameters included in the sensing focus; Indicates the parameters included in the perceived focus;

[0053] Kalman gain ;

[0054] After setting the edge-aware focus, the edge state is: ;

[0055] in, These represent the fusion state of the current node, the fusion state of the neighboring nodes, the water quality feature vector of the current node, and the water quality feature vector of the neighboring nodes, respectively.

[0056] Preferably, it also includes: predicting the future state of the valve based on the node state and edge state, including:

[0057] Based on water quality, construct a new node state vector. ;

[0058] New edge state vector ;in, Indicates the diffusion flux of pollutants;

[0059] A state prediction model is constructed using graph convolutional neural networks. and The input is fed into a pre-trained state prediction model, which outputs future node state vectors and edge state vectors.

[0060] The present invention also provides an electronic device, including a processor and a memory, a communication module and a sensor module connected to the processor, the electronic device being used to execute the aforementioned real-time status sensing method for online monitoring of water valves.

[0061] The present invention also provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement the aforementioned real-time status sensing method for online monitoring of water valves.

[0062] The beneficial effects of this invention are:

[0063] 1. In the execution of valve control strategies, this invention combines the pipeline topology of the scenario and target area to perceive the status of nodes (valve) and edges (valve operation) under multiple water quality scenarios; and dynamically adjusts the perception focus and frequency of nodes to achieve coordination between valve status, operation, water quality, and scenario.

[0064] 2. This invention constructs a valve collaborative optimization model, combines the changes in water quality between valves to obtain the optimal valve state (opening degree), coordinates the changes in the opening degree between valves, and provides a reference for valve operation. Attached Figure Description

[0065] Figure 1 This is a flowchart of a real-time status sensing method for online monitoring of water valves according to the present invention.

[0066] Figure 2 This is an optimization diagram of different valve opening degrees under different water qualities according to the present invention. Detailed Implementation

[0067] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious modifications will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0068] It is understood that the term "a" should be understood as "at least one" or "one or more," that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.

[0069] refer to Figure 1 The technical solution provided by this invention is: a real-time status sensing method for online monitoring of water valves, comprising the following steps:

[0070] Step 1: Construct a real-time valve status monitoring strategy to adapt to valve status monitoring in different application scenarios; specifically including the following steps:

[0071] Step 1.1: Construct a valve-pipeline network model using valves as nodes; including the following steps:

[0072] Retrieve pipeline network information from the database;

[0073] Constructing a pipeline network-valve diagram model, including:

[0074] With valves as nodes, and pipeline scheduling and valve operation as composite edges;

[0075] Then, the directed graph of the pipeline system ,in, Represents a set of nodes; Represents the set of edges;

[0076] ; ; ;

[0077] in, Indicates the target valve; Indicates the coordinates of the target valve. Indicate the type of the target valve; Represents the state vector of the target valve; Indicates the valves adjacent to the target valve; Represents the operation vector;

[0078] ;in, This indicates the valve opening degree, flow rate, pressure, and temperature.

[0079] operation vector ;in, Indicates from valve To valve The change in valve opening. Indicates valve and valves Operation time interval; Indicates from valve Switch to valve scheduling costs;

[0080] Step 1.2: Construct an intelligent monitoring strategy based on the valve-pipeline network diagram model, including the following steps:

[0081] Constructing the scheduling objective function ; This represents the actual pressure vector of the node. Represents the target pressure vector; It represents the L2 norm, which minimizes the overall deviation between actual pressure and target pressure, emphasizing smooth adjustment.

[0082] This represents the vector of valve opening change. ,in, Indicates the number of valve scheduling operations;

[0083] Represents the flow vector between nodes; Represents the water demand vector; It represents the L1 norm, which minimizes the total deviation between flow rate and water demand, and is sensitive to outliers; These represent pressure weight, flow weight, and cost weight, respectively.

[0084] The non-dominated sorting genetic algorithm (NSGA) is used to solve the objective function and obtain the optimal solution to the objective function, namely, the optimal actual pressure vector, the optimal flow vector between nodes, the scheduling cost, and the change in opening degree.

[0085] Based on the valve opening change and valve status, the valve opening is optimized to achieve the optimal valve opening, thereby ensuring that the water delivery in the pipeline network reaches the optimal transmission state.

[0086] Step 2: Based on the water quality characteristics flowing through the target valve within the target area, optimize the target valve status acquisition strategy and valve coordination strategy; including the following steps:

[0087] Step 2.1: Obtain water quality characteristics of the target area and construct a water quality feature vector. ;in, These represent the normalized values ​​of turbidity, residual chlorine, pH, and conductivity, respectively.

[0088] Step 2.2: Using water quality feature vectors and a clustering algorithm, classify water quality into drinking water, reclaimed water, rainwater, and industrial water;

[0089] Step 2.3: Set the water quality risk index ;in, Indicates parameter weights, Indicates the pollutant weighting. Indicates the weighted sum of pollutants, Indicates the reference water quality vector;

[0090] Step 2.4: Set the valve status acquisition frequency according to water quality. ;in, Indicates the sensitivity coefficient; Indicates the basic sampling frequency of valve status; Indicates the valve status adaptive sampling frequency; water quality change rate. ;

[0091] Step 2.5: Based on the water quality risk index, optimize the valve status acquisition frequency, including:

[0092] when hour, ;in, Indicates the frequency weighting coefficient;

[0093] when hour, ;

[0094] when hour, ;

[0095] in, These represent the maximum risk index and the minimum risk index, respectively.

[0096] Step 2.6: Optimize valve coordination strategy, including:

[0097] Construct a valve collaborative optimization model:

[0098] Coordination objective function: ;

[0099] Constraints: ;in, ; Represents the target water quality feature vector; Indicates the difference in water quality characteristics due to mixing; This indicates the actual pressure at the node under the current water quality conditions; These represent the pressure weight, flow weight, and cost weight of the current water quality, respectively. This represents the dimension of the water quality feature vector.

[0100] The NSGA algorithm is used to solve the coordination objective function to obtain the optimal valve opening change under the current water quality. Specifically:

[0101] First, define chromosome encoding: use real number encoding, i.e. Each gene represents a change in the opening degree of a valve; the gene range is... ;

[0102] Population initialization: Randomly generate a set of aperture change vectors ;in, This represents the lower triangular Cholsky decomposition matrix; ; Represents the correction vector;

[0103] Calculate the scalar function value and constraint violation amount for each individual in the population (water quality and water pressure are known), and sort them according to non-dominance relations; within the same non-dominance relation level, calculate the crowding distance of individuals;

[0104] Parents are selected through a binary tournament process, and crossover mutation is performed to generate mutated offspring. Parents and offspring are then merged, and a non-dominated sorting comparison of crowding distance is performed. Within the same level, the individual with the largest crowding distance (change in opening degree) is selected. Then, n individuals are selected from the highest to lowest non-dominated levels to generate a new population. This process is repeated until the maximum number of iterations is reached to obtain the optimal opening degree change vector. .

[0105] like Figure 2As shown, this illustrates the optimal valve opening for different valves under varying water qualities. Reducing the valve opening lowers the valve operating cost. (e.g., time or energy consumption).

[0106] Step 3: During valve control strategy execution, based on scenario requirements and the pipeline topology of the target area, perceive the valve status under multiple water quality scenarios; including the following steps:

[0107] Constructing the topology-water quality coupled graph structure: ;in, Represents the water quality characteristic matrix. ;in, Indicates the number of water quality feature vectors;

[0108] Will The input is fed into a pre-trained convolutional network model, which outputs the scene type of the target region to identify the scene of the target region; the scene type of the target region includes: normal scheduling, emergency scheduling, and water pollution.

[0109] Based on the scene type of the target area, node sensing focus and edge sensing focus are set, and the sensing focus and acquisition frequency are dynamically adjusted, including:

[0110] In a normal scheduling scenario, the node's perception focus includes traffic and pressure; the edge's perception focus is the traffic gradient; and the basic sampling frequency can be 1Hz.

[0111] In emergency dispatch scenarios, the node sensing focus includes pressure change; the edge sensing focus is the pressure gradient; and the basic sampling frequency can be 10Hz.

[0112] In the case of water pollution, the node sensing focus includes pollutant concentration; the sensing focus changes to valve opening; and the basic sampling frequency can be 5Hz.

[0113] In the case of pipeline flushing, the node sensing focus is on the turbidity and flow rate of the water; the basic sampling frequency can be 3Hz.

[0114] After setting the node's sensing focus, the fusion state of the node is calculated and obtained based on the water quality type. ;in, Indicates the number of parameters included in the sensing focus; Indicates the parameters included in the perceived focus;

[0115] Kalman gain ;

[0116] For example, in a normal scheduling scenario, ; For traffic, For pressure;

[0117] After setting the edge-aware focus, the edge state is: ;

[0118] in, These represent the fusion state of the current node, the fusion state of the neighboring nodes, the water quality feature vector of the current node, and the water quality feature vector of the neighboring nodes, respectively.

[0119] Step 4: Based on the valve status under multiple water quality scenarios, predict the future state of the valve.

[0120] Based on water quality, construct a new node state vector. ;

[0121] New edge state vector ;in, Indicates the diffusion flux of pollutants;

[0122] A state prediction model is constructed using graph convolutional neural networks. and The input is fed into a pre-trained state prediction model, which outputs future node state vectors and edge state vectors.

[0123] State prediction models make state predictions in three stages: short-term, medium-term, and long-term. Short-term predictions, with a time step of 5 minutes, are specifically performed using an LSTM network.

[0124] Mid-term prediction, which has a prediction time step of 5-30 minutes, is specifically performed using a graph convolutional network (GCN).

[0125] Long-term prediction, i.e., prediction time step greater than 30 minutes, involves coupling a physical model into the graph convolutional network (GCN), i.e., adding a valve wear model. ;in, This indicates the initial maximum valve opening. This indicates the valve's maximum opening degree loss rate; Indicates the wear coefficient of the valve material; This represents the instantaneous wear rate, which can be calibrated experimentally. This indicates the maximum prediction time step. An increase in sediment content in the water flowing through the valve will lead to... An increase in the number of valve actuations will lead to Increased wear and tear on valves leads to reduced valve opening, decreased accuracy of valve flow control, and even valve failure.

[0126] By quantifying valve wear, not only can the probability of valve failure be predicted, but also by taking valve wear into account when executing valve control strategies, the system's perception of valve status (opening degree) becomes more accurate.

[0127] The present invention also includes an electronic device comprising a processor and a memory, a communication module, and a sensor module connected to the processor. The electronic device is used to execute the aforementioned real-time status sensing method for online monitoring of water valves.

[0128] The present invention also provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement the aforementioned real-time status sensing method for online monitoring of water valves.

[0129] The processes described above with reference to the flowcharts in the embodiments disclosed in this invention can be implemented as computer software programs. The embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the methods of this invention. It should be noted that the computer-readable medium described above in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical cables, RF, etc., or any suitable combination thereof.

[0130] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0131] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been shown and explained in the embodiments. Without departing from the principles described, the implementation of the present invention may have any changes or modifications.

Claims

1. A real-time status sensing method for online monitoring of water valves, characterized in that, The method includes: Develop a real-time valve status monitoring strategy to adapt to valve status monitoring in different application scenarios; including: Using valves as nodes, a valve-pipeline network diagram model is constructed, including: obtaining pipeline network information from the database; Constructing a pipeline network-valve diagram model, including: With valves as nodes, and pipeline scheduling and valve operation as composite edges; Then, the directed graph of the pipeline system ,in, Represents a set of nodes; Represents the set of edges; ； ； ； in, Indicates the target valve; Indicates the coordinates of the target valve. Indicate the type of the target valve; Represents the state vector of the target valve; Indicates the valves adjacent to the target valve; Represents the operation vector; ;in, This indicates the valve opening degree, flow rate, pressure, and temperature. operation vector ;in, Indicates from valve To valve The change in valve opening. Indicates valve and valves Operation time interval; Indicates from valve Switch to valve scheduling costs; Intelligent monitoring strategies are built based on valve-pipeline network diagram models; Based on the water quality characteristics flowing through the target valve within the target area, optimize the target valve status acquisition strategy and valve coordination strategy; In the execution of valve control strategies, the valve status under multiple water quality scenarios is perceived by combining scenario requirements and the pipeline topology of the target area. Based on the valve status under various water quality scenarios, predict the future state of the valve.

2. The real-time status sensing method for online monitoring of water valves according to claim 1, characterized in that, The intelligent monitoring strategy based on the valve-pipeline network diagram model includes: Constructing the scheduling objective function ; This represents the actual pressure vector of the node. Represents the target pressure vector; Represents the L2 norm; This represents the vector of valve opening change. ,in, Indicates the number of valve scheduling operations; Represents the flow vector between nodes; Represents the water demand vector; Represents the L1 norm; These represent pressure weight, flow weight, and cost weight, respectively. The non-dominated sorting genetic algorithm (NSGA) is used to solve the objective function and obtain the optimal solution to the objective function, namely, the optimal actual pressure vector, the optimal flow vector between nodes, the scheduling cost, and the change in opening degree. Based on the valve opening change and valve status, the valve opening is optimized to achieve the optimal valve opening, thereby ensuring that the water delivery in the pipeline network reaches the optimal transmission state.

3. The real-time status sensing method for online monitoring of water valves according to claim 2, characterized in that, The strategy for obtaining the target valve status and the valve coordination strategy based on the water quality characteristics flowing through the target valve within the target area include: Obtain water quality characteristics of the target area and construct a water quality feature vector. ;in, These represent the normalized values ​​of turbidity, residual chlorine, pH, and conductivity, respectively. Using water quality feature vectors and a clustering algorithm, water quality is classified into drinking water, reclaimed water, rainwater, and industrial water. Set water quality risk index ;in, Indicates parameter weights, Indicates the pollutant weighting. Indicates the weighted sum of pollutants; Indicates the reference water quality vector; Valve status collection frequency is set according to water quality. ;in, Indicates the sensitivity coefficient; Indicates the basic sampling frequency of valve status; Indicates the valve status adaptive sampling frequency; water quality change rate. ; Based on the water quality risk index, optimize the valve status acquisition frequency, including: when hour, ;in, Indicates the frequency weighting coefficient; when hour, ; when hour, ; in, These represent the maximum risk index and the minimum risk index, respectively.

4. The real-time status sensing method for online monitoring of water valves according to claim 3, characterized in that, The strategy for obtaining the state of the target valve and the valve coordination strategy based on the water quality characteristics flowing through the target valve within the target area also includes: Optimize valve coordination strategies, including: Construct a valve collaborative optimization model: Coordination objective function: ; Constraints: ;in, ; Represents the target water quality feature vector; Indicates the difference in water quality characteristics due to mixing; This indicates the actual pressure at the node under the current water quality conditions; These represent the pressure weight, flow weight, and cost weight of the current water quality, respectively. The dimension of the water quality feature vector; The NSGA algorithm is used to solve the coordination objective function to obtain the optimal valve opening change under the current water quality.

5. A real-time status sensing method for online monitoring of water valves according to claim 4, characterized in that, In the execution of the valve control strategy, the valve status under multiple water quality scenarios is perceived by combining scenario requirements and the pipeline topology of the target area, including: Constructing the topology-water quality coupled graph structure: ;in, Represents the water quality characteristic matrix. ;in, Indicates the number of water quality feature vectors; Will The input is fed into a pre-trained convolutional network model, which outputs the scene type of the target region to identify the scene of the target region; the scene type of the target region includes: normal scheduling, emergency scheduling, and water pollution. Based on the scene type of the target area, set the node perception focus and edge perception focus, including: In a normal scheduling scenario, the node's perception focus includes traffic and pressure; the edge's perception focus is the traffic gradient. In emergency dispatch scenarios, the node's perception focus includes the pressure change; the edge's perception focus is the pressure gradient. In the case of water pollution, the node's sensing focus includes pollutant concentration; the sensing focus changes to valve opening. After setting the node's sensing focus, the fusion state of the node is calculated and obtained based on the water quality type. ;in, Indicates the number of parameters included in the sensing focus; Indicates the parameters included in the perceived focus; Kalman gain ; After setting the edge-aware focus, the edge state is: ; in, These represent the fusion state of the current node, the fusion state of the neighboring nodes, the water quality feature vector of the current node, and the water quality feature vector of the neighboring nodes, respectively.

6. A real-time status sensing method for online monitoring of water valves according to claim 5, characterized in that, Also includes: Based on node and edge states, predict the future state of the valve, including: Based on water quality, construct a new node state vector. ; New edge state vector ;in, Indicates the diffusion flux of pollutants; A state prediction model is constructed using graph convolutional neural networks. and The input is fed into a pre-trained state prediction model, which outputs future node state vectors and edge state vectors.

7. An electronic device, comprising a processor and a memory, a communication module, and a sensor module connected to the processor, characterized in that, The electronic device is used to execute the real-time status sensing method for online monitoring of water valves as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement a real-time status sensing method for online monitoring of water valves as described in any one of claims 1-6.

Images