Repair analysis system of intelligent pipe network topological structure

Abstract

The invention discloses an intelligent pipe network topological structure restoration analysis system, and relates to the technical field of intelligent pipe network management, the intelligent pipe network topological structure restoration analysis system comprises a design management platform, and the design management platform is in communication connection with a topological structure data acquisition module, a topological structure analysis module, a pipe network fault diagnosis module, a restoration scheme generation module and a pipe network operation monitoring module. According to the method, the pipe network topological structure model is constructed by integrating various sensors and external data sources, branches, loops or special-shaped connection structures in a complex pipe network are accurately recognized, the judgment capacity of the pipe network connection relation and the flow direction is improved, and the fault diagnosis efficiency is improved by combining the pipe network topological structure model and the flow direction analysis result and utilizing the pre-constructed fault diagnosis model. According to the method, the pipe network fault can be quickly and accurately diagnosed, the fault type and position can be quickly identified by integrating the multi-source data, extracting the fault features and matching the fault features with the preset fault mode, the misdiagnosis rate is reduced, and the fault diagnosis efficiency and accuracy are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent pipe network management, and particularly relates to a repair analysis system for an intelligent pipe network topology structure. Background Art

[0002] With the continuous advancement of the global urbanization process, the urban scale continues to expand, and the population increases sharply. To meet the living needs of urban residents and the requirements of industrial production, the scale and complexity of the urban pipe network system are also continuously increasing. For such a huge and complex pipe network system, once there are problems with its topology structure, it will directly affect the normal operation of the city and the quality of life of residents. Moreover, the pipe network systems of many cities were built earlier, and after long-term use, problems such as pipeline aging, corrosion, and damage are becoming increasingly serious.

[0003] In the prior art, for pipe network topologies with a large number of branches, loops, or special-shaped connections, it is difficult to accurately identify and analyze their structural characteristics, resulting in unreasonable repair plans. Therefore, for complex pipe network topologies, how to use artificial intelligence technology to construct a pipe network topology structure model, accurately judge the connection relationship and flow direction of pipelines, and improve the ability to identify and analyze complex pipe network topologies is the problem to be solved by the present invention. For this purpose, a repair analysis system for an intelligent pipe network topology structure is proposed herein. Summary of the Invention

[0004] The purpose of the present invention is to provide a repair analysis system for an intelligent pipe network topology structure to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is as follows: A repair analysis system for an intelligent pipe network topology structure, including a design management platform, which is communicatively connected to a topology structure data acquisition module, a topology structure analysis module, a pipe network fault diagnosis module, a repair plan generation module, and a pipe network operation monitoring module; The topology structure data acquisition module is used to integrate various sensors and external data sources in the pipe network system, and collect and preprocess the pipe network operation data and spatial information; The topology structure analysis module is used to analyze the preprocessed pipe network operation data and spatial information by using artificial intelligence technology, construct a pipe network topology structure model, and then analyze the pipeline connection relationship and flow direction; The pipe network fault diagnosis module is used to combine the pipe network topology structure model and the flow direction analysis result, and use a pre-constructed fault diagnosis model to diagnose the pipe network fault, identify the fault type and fault location, quickly and accurately diagnose the pipe network fault, and reduce the misdiagnosis rate; The repair plan generation module is used to generate a repair plan based on the fault diagnosis results, in combination with the topological structure and flow direction information of the pipe network. By simulating the repair process, it analyzes the effects of different repair plans, optimizes the repair strategy, reduces the repair cost and construction risk, ensures the feasibility and efficiency of the repair plan, and improves the efficiency and quality of the repair work. The pipe network operation monitoring module is used to continuously monitor the repaired pipe network, collect the operation data of the pipe network, and adjust the repair plan according to the operation conditions of the pipe network, optimize the pipe network management, and ensure the stable operation and efficient management of the system.

[0006] A further improvement of the technical solution of the present invention lies in that: the topological structure data acquisition module specifically includes: In the pipe network system, according to the layout and key nodes of the pipe network, a variety of sensors including pressure sensors, flow sensors, liquid level sensors, etc. are deployed. Combining the topological structure of the pipe network and the monitoring focus, the sensor layout is planned, and the sensors are installed at the positions of pipe connection points, branch points, and loop nodes to continuously monitor the operation status of the pipe network, obtain the operation data of the pipe network, and ensure full coverage of key nodes and areas prone to problems. Integrate external data sources including geographic information system (GIS) and historical maintenance records, obtain GIS data, and at the same time, sort out the historical maintenance records of the pipe network covering the content of maintenance time, fault type, and treatment method. Integrate the collected operation data, GIS data, and historical maintenance records of the pipe network into the data preprocessing stage. Combining the GIS data and historical maintenance records, annotate and supplement the collected data to form complete operation data and spatial information of the pipe network, construct a complete data set, and then store the preprocessed data in the data warehouse.

[0007] A further improvement of the technical solution of the present invention lies in that: the topological structure identification and analysis module includes a topological feature extraction unit, a topological structure modeling unit, and a flow direction analysis unit; Among them, the topological feature extraction unit is used to extract the operation features and spatial features related to the topological structure of the pipe network from the preprocessed operation data and spatial information of the pipe network, and integrate them to obtain the topological structure feature sequence of the pipe network. The topological structure modeling unit is used to analyze the features in the collected topological structure feature sequence of the pipe network by using artificial intelligence technology based on graph neural networks, and construct a topological structure model of the pipe network to accurately represent the connection relationship of pipes, branch points, and loop structures. The flow direction analysis unit, based on the constructed topological structure model of the pipe network, analyzes the flow direction of the fluid in the pipe network, and determines the flow direction and flow distribution of the fluid in different pipe segments through computational fluid dynamics simulation.

[0008] A further improvement of the technical solution of the present invention lies in that: the topological feature extraction unit specifically includes: From the preprocessed pipeline network operation data, screen out the key feature points reflecting the topological structure of the pipeline network, and with reference to the spatial information, determine the positions of the key feature points in the spatial layout of the pipeline network, and preliminarily construct a set of feature points; For the screened key feature points, extract the operation features related to the operation state of the pipeline network, including pressure gradient, flow peak and valley values, and flow change frequency; According to the spatial information of the pipeline network, extract the spatial features between the key feature points. Among them, by calculating the Euclidean distance between the feature points, estimate the actual length of the pipeline, provide geometric parameters for pipeline network modeling, analyze the connection sequence and branch angle of the key feature points, and determine the pipeline orientation and branch situation; Integrate the extracted operation features and spatial features, and arrange and combine the operation features (pressure gradient, flow peak and valley values, flow change frequency) and spatial features (Euclidean distance, connection sequence, branch angle) of each key feature point according to the topological order of the pipeline network to form a comprehensive feature sequence, that is, the pipeline network topological structure feature sequence.

[0009] A further improvement of the technical solution of the present invention lies in that: the topological structure modeling unit specifically includes: According to the pipeline network topological structure, use the screened key feature points as the nodes of the graph. According to the actual connection situation of the pipeline network, establish edges between the nodes to represent the connection relationship of the pipelines, construct the graph structure representation of the pipeline network, clarify the attributes of each node and the attributes of each edge. Among them, each key feature point is used as a graph node, and the feature vector of the node includes its operation features and spatial features, and according to the actual connection situation of the pipeline network, establish edges between the nodes and initialize the weights of the edges. The weights are determined according to the physical attributes such as the length, material, and diameter of the pipeline, as well as the operation data such as historical flow and pressure; Use the aggregation mechanism of the graph neural network to aggregate the features of each node and its neighbor nodes, collect the feature information of the neighbor nodes of each node, determine the directly connected nodes of each node, that is, the neighbor nodes, by traversing the graph structure, obtain the feature vectors of the neighbor nodes, and fuse and update the collected neighbor node feature information with the features of the node itself; Train the constructed graph structure to learn the feature representations of the nodes and edges, define a loss function, calculate the loss by comparing the difference between the predicted topological structure and the actual topological structure, and use the gradient descent optimization algorithm to update the parameters of the model. During the training process, learn the mapping relationship between the node features and the topological structure; After training is completed, the learned feature representations of nodes and edges are used to generate the final pipeline network topology model. The pipeline network topology model represents the connection relationship, branch points and loop structure of the pipelines, and outputs the feature representation of each node, the connection weights between nodes, and the topology diagram of the entire pipeline network.

[0010] A further improvement of the technical solution of the present invention is that the flow direction analysis unit specifically includes: Based on the constructed pipe network topology model, the design parameters of the pipe network are initialized, the initial flow direction and flow distribution assumptions of the fluid in the pipe network are set, and at the same time, the type and boundary conditions of each node are clarified, and the inlet pressure and flow rate of the pipe network, as well as the pressure or free outflow conditions of the outlet are determined. Among them, the types of each node include water source node, user node, intersection node, etc. Select computational fluid dynamics (CFD) software, import the pipe network topology model into it, simulate the fluid flow in the pipe network, initialize the simulation environment in the computational fluid dynamics (CFD) software, set the parameters of the simulation time step and number of iterations, apply the CFD principle, calculate the pressure change and flow distribution of the fluid in different pipe sections by solving the continuity equation and energy equation, and use the finite difference method to discretize the continuous equation to form a solvable set of equations to predict the flow behavior of the fluid in the pipe network; The flow direction results obtained by simulation are compared with the actual pipe network operation data. The flow rate, flow direction and node pressure data of each pipe section in the actual pipe network are collected and compared with the simulation results one by one. The error between the predicted value and the actual value is calculated, and the parameters of the model are adjusted using the optimization algorithm of the gradient descent method. Through multiple iterations, the error is continuously reduced, so that the flow direction analysis results gradually approach the actual fluid flow situation. After multiple iterations of optimization, the flow direction and flow distribution results of the fluid in the pipeline network are output, and a pipeline network flow diagram is generated. The visualization function of the computational fluid dynamics (CFD) software is used to intuitively display the flow direction of the fluid in each pipeline section, provide a flow distribution table, and list the flow values ​​of each pipeline section.

[0011] A further improvement of the technical solution of the present invention is that the pipeline network fault diagnosis module specifically includes: Integrate the network topology model, flow analysis results, and real-time monitoring data to ensure that all data are aligned in terms of timestamp and spatial position, remove noise data and outliers, and extract fault features from the integrated data, where fault features include pressure change rate, flow mutation amplitude, node pressure deviation, and flow deviation; The extracted fault features are input into the pre-built fault diagnosis model, matched with the preset fault modes in the fault diagnosis model, and the similarity between the fault features and each fault mode is calculated to determine whether a fault exists; After determining the fault type, further locate the fault position. Combining with the pipe network topology structure model, analyze the propagation path and influence range of the fault characteristics in the pipe network, and generate a fault report. Output the diagnosed fault type and fault position in an intuitive way. The fault report details the fault type, occurrence location, and influence range information, and is accompanied by a pipe network topology structure diagram with the fault position marked on the diagram.

[0012] A further improvement of the technical solution of the present invention lies in that: the calculation process of the similarity between the fault characteristics and each fault mode is as follows: Integrate the pipe network topology structure model, the flow direction analysis result, and the real-time monitoring data to ensure that all data is aligned in terms of time stamp and spatial position. Extract fault characteristics including the pressure change rate, flow mutation amplitude, node pressure deviation, and flow direction deviation from the integrated data. For each fault characteristic, determine its current value and the corresponding characteristic typical value in the fault mode, and then calculate the relative difference between its current value and the corresponding characteristic typical value in the k-th fault mode. Sum the squares of the relative differences of all fault characteristics and take the square root to obtain the standardized difference function. Calculate the average value of the ratio of the fault characteristic to the fault mode characteristic, and substitute the calculated average value into the sine function to obtain the sensitivity adjustment function. Combine the standardized difference function and the sensitivity adjustment function to calculate the similarity of the k-th fault mode. When the standardized difference function is close to 1, it indicates a high degree of matching between the fault characteristics and the fault mode. When the sensitivity adjustment function is close to 1, it indicates that the overall trend of the fault characteristics is consistent with the fault mode. That is, when the similarity of the k-th fault mode is closer to 1, it indicates that the fault characteristics are more similar to the k-th fault mode, and the possibility of the fault is greater.

[0013] A further improvement of the technical solution of the present invention lies in that: the repair plan generation module specifically includes: According to the fault type, position, and influence range information output by the fault diagnosis module, combine with the pipe network topology structure and flow direction information to analyze the key pipe segments and nodes involved in the fault, and screen out a preliminary repair plan applicable to this fault type from the pre-set repair strategy library. Import the preliminary screened repair plans one by one, simulate the repair process, evaluate the impact of the repair on the operation of the pipe network, including the water supply interruption time, short-term fluctuations in water pressure in the surrounding area, etc. At the same time, calculate the cost and expected repair time of each plan, and then optimize the preliminary repair plan based on the simulation results. Compare the cost, construction difficulty, and influencing factors on the operation of the pipe network of different plans to select a better repair technology. Among them, for complex loop or branch faults, optimize the repair sequence to avoid secondary faults or construction conflicts, and finally generate one or more sets of optimized repair plans. Output the optimized repair plan in an intuitive way, including detailed construction steps, lists of required materials and equipment, cost budget, estimated repair time, and suggestions for temporary measures.

[0014] A further improvement of the technical solution of the present invention lies in that: the pipeline network operation monitoring module specifically includes: In the repaired pipeline network system, through integrated pressure sensors, flow sensors, and monitoring devices, the operation data of the pipeline network are collected in real time, including pipeline pressure, flow rate, liquid level, etc., reflecting the current operation state of the pipeline network, and the collected operation data are imported into the design management platform, compared and analyzed with the preset normal operation thresholds, monitor whether the pressure fluctuates abnormally, whether the flow rate meets the expectations, etc., to judge whether the pipeline network is in a normal operation state. If it is found that the data exceeds the preset normal operation threshold, an alarm is automatically triggered, the abnormal situation is recorded, and a preliminary analysis report is generated; According to the monitored abnormal situation, combined with the pipeline network topology structure and flow direction information, analyze the cause of the fault and the affected range. If it is found that there are new problems in the repaired pipeline network, adjust the repair plan to ensure the stable operation of the pipeline network; Re-implement the adjusted repair plan and continuously monitor the operation of the pipeline network. By comparing the operation data before and after the adjustment, evaluate the effect of the optimization plan. At the same time, regularly generate a pipeline network operation report, summarize the operation state, problems found, and solutions, providing a reference for the long-term management and maintenance of the pipeline network.

[0015] Due to the adoption of the above technical solution, the technical progress achieved by the present invention compared with the prior art is: The present invention provides a repair analysis system for an intelligent pipeline network topology structure. By integrating multiple sensors and external data sources to construct a pipeline network topology structure model, accurately identify branches, loops, or special-shaped connection structures in complex pipeline networks, improve the judgment ability of the connection relationship and flow direction of the pipeline network, and combine the pipeline network topology structure model and the flow direction analysis result, and use the pre-constructed fault diagnosis model to quickly and accurately diagnose pipeline network faults. And by integrating multi-source data and extracting fault features, matching with the preset fault patterns, the fault type and location can be quickly identified, reducing the misdiagnosis rate, and greatly improving the efficiency and accuracy of fault diagnosis.

[0016] The present invention provides a repair analysis system for an intelligent pipe network topology structure. According to the fault diagnosis results, combined with the topology structure and flow direction information of the pipe network, a repair plan is generated, and the effects of different plans are analyzed by simulating the repair process. It is possible to compare the costs, construction difficulties, and impacts on the operation of the pipe network of different plans, select the optimal repair strategy, thereby reducing the repair cost and construction risk, and continuously monitoring the repaired pipe network, collecting the operation data of the pipe network, and adjusting the repair plan according to the operation conditions. It can detect abnormal situations in the operation of the pipe network in real time, take measures to adjust in a timely manner, and ensure the stable operation and efficient management of the pipe network. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings.

[0018] Figure 1 It is a schematic diagram of the working process of the present invention; Figure 2 It is a schematic diagram of the working process of the pipe network fault diagnosis module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0020] Embodiment 1, as Figure 1 、 Figure 2 shown, the present invention provides a repair analysis system for an intelligent pipe network topology structure, including a design management platform, and the design management platform is communicatively connected to a topology structure data collection module, a topology structure analysis module, a pipe network fault diagnosis module, a repair plan generation module, and a pipe network operation monitoring module; The topological structure data acquisition module is used to integrate various sensors (pressure sensors, flow sensors, liquid level sensors, etc.) and external data sources (geographic information system GIS data, historical maintenance records) in the pipe network system, collect and preprocess the pipe network operation data and spatial information. In the pipe network system, according to the layout of the pipe network and key nodes, various sensors including pressure sensors, flow sensors, liquid level sensors, etc. are deployed. Combining the pipe network topological structure and monitoring key points, the sensor layout is planned, and the sensors are installed at the positions of pipe connection points, branch points and loop nodes to monitor the operation status of the pipe network in real time, obtain the pipe network operation data, ensure full coverage of key nodes and areas prone to problems. Integrate external data sources including geographic information system (GIS) and historical maintenance records, obtain GIS data (spatial location information of the pipe network), including pipeline laying routes, node coordinates, etc. At the same time, sort out the pipe network historical maintenance records covering maintenance time, fault types and treatment methods, integrate the collected pipe network operation data, GIS data and historical maintenance records, enter the data preprocessing stage, clean the data, remove abnormal data caused by sensor failures or environmental interferences, format the data, unify the data format, combine GIS data and historical maintenance records, label and supplement the collected data to form complete pipe network operation data and spatial information, construct a complete data set, and then store the preprocessed data in the data warehouse; The topological structure analysis module is used to analyze the preprocessed pipe network operation data and spatial information by using artificial intelligence technology, construct a pipe network topological structure model, and then analyze the pipe connection relationship and flow direction. The topological structure identification and analysis module includes a topological feature extraction unit, a topological structure modeling unit and a flow direction analysis unit; Among them, the topological feature extraction unit is used to extract the operation features and spatial features related to the pipe network topological structure from the preprocessed pipe network operation data and spatial information, and integrate them to obtain the pipe network topological structure feature sequence. From the preprocessed pipe network operation data, key feature points reflecting the pipe network topological structure are screened out, and with reference to the spatial information, the positions of the key feature points in the pipe network spatial layout are determined, and a set of feature points is initially constructed. Among them, in the pressure data, nodes with obvious pressure changes at the pipe branches or joints are found as key feature points. In the flow data, points with uneven flow distribution corresponding to the intersection points or loop entrances of the pipe network are identified as key feature points. For the selected key feature points, operation features related to the pipe network operation state are extracted, including pressure gradient, flow peak and valley values, and flow change frequency. Among them, the pressure gradient of each key feature point is calculated to reflect the resistance characteristics of the pipe section, and the flow peak and valley values and flow change frequency are statistically analyzed to reflect the water use patterns and pipe network load fluctuations at different times, and capture the dynamic operation characteristics of the pipe network in the time dimension. According to the spatial information of the pipe network, the spatial features between the key feature points are extracted. Among them, by calculating the Euclidean distance between the feature points, the actual length of the pipe is estimated to provide geometric parameters for pipe network modeling. The connection order and branch angle of the key feature points are analyzed to determine the pipe orientation and branch situation, and help identify the topological structure of the pipe network. Combining with the geographic coordinate data, the distribution form of the pipe network in the geographical space is further depicted. The extracted operation features and spatial features are integrated, and according to the topological order of the pipe network, the operation features (pressure gradient, flow peak and valley values, flow change frequency) and spatial features (Euclidean distance, connection order, branch angle) of each key feature point are arranged and combined to form a comprehensive feature sequence, which is the pipe network topological structure feature sequence. The pipe network topological structure feature sequence not only contains the dynamic features of the pipe network in the operation state, but also incorporates the spatial layout information of the pipe network, and can comprehensively characterize the topological structure of the pipe network; A topological structure modeling unit is used to analyze the features in the collected pipeline network topological structure feature sequence by using artificial intelligence technology based on graph neural networks, construct a pipeline network topological structure model to accurately represent the connection relationships, branch points, and loop structures of pipelines. According to the pipeline network topological structure, the selected key feature points are used as the nodes of the graph, and edges are established between the nodes according to the actual connection situation of the pipeline network to represent the connection relationships of pipelines, constructing a graph structure representation of the pipeline network, clarifying the attributes of each node and each edge. Among them, each key feature point is used as a graph node, and the feature vector of the node contains its operation features and spatial features, and edges are established between the nodes according to the actual connection situation of the pipeline network, and the weights of the edges are initialized. The weights are determined according to the physical attributes such as the length, material, and diameter of the pipeline, as well as the operation data such as historical flow rate and pressure. Using the aggregation mechanism of the graph neural network, the features of each node and its neighbor nodes are aggregated, collecting the feature information of the neighbor nodes of each node. By traversing the graph structure, the directly connected nodes of each node, that is, the neighbor nodes, are determined, the feature vectors of the neighbor nodes are obtained, and the collected neighbor node feature information is fused and updated with the features of the node itself, so that the feature vector of each node not only contains its own information but also fuses the features of the surrounding nodes, thereby capturing the local topological structure information and enhancing the node's perception ability of the surrounding environment. The constructed graph structure is trained to learn the feature representations of the nodes and edges, define a loss function, calculate the loss by comparing the predicted topological structure with the actual topological structure, and use the gradient descent optimization algorithm to update the parameters of the model. During the training process, the mapping relationship between the node features and the topological structure is learned, so that the feature representation of the node can reflect its position and role in the pipeline network topological structure. Through continuous iteration and optimization, the model gradually masters the feature patterns of the pipeline network topological structure. After the training is completed, using the learned feature representations of the nodes and edges, the final pipeline network topological structure model is generated, representing the connection relationships, branch points, and loop structures of the pipelines through the pipeline network topological structure model, and outputting the feature representation of each node, the connection weights between the nodes, and the topological structure diagram of the entire pipeline network; The flow direction analysis unit analyzes the flow direction of the fluid in the pipe network based on the constructed pipe network topology model. Through computational fluid dynamics simulation, the flow direction and flow distribution of the fluid in different pipe sections are determined. Based on the constructed pipe network topology model, the design parameters of the pipe network are initialized, and the initial flow direction and flow distribution assumptions of the fluid in the pipe network are set. At the same time, the type and boundary conditions of each node are clarified, and the inlet pressure and flow rate of the pipe network, as well as the pressure or free outflow conditions of the outlet are determined. Among them, the types of each node include water source nodes, user nodes, intersection nodes, etc. The computational fluid dynamics (CFD) software is selected, and the pipe network topology model is imported into it to simulate the fluid flow in the pipe network. The simulation environment is initialized in the computational fluid dynamics (CFD) software, and the parameters of the simulation time step and number of iterations are set. Using the CFD principle, by solving the continuity equation and energy equation, Calculate the pressure change and flow distribution of the fluid in different pipeline sections, and use the finite difference method to discretize the continuous equations to form a solvable set of equations, predict the flow behavior of the fluid in the pipeline network, compare the simulated flow direction results with the actual pipeline network operation data, collect the flow, flow direction and node pressure data of each pipeline section in the actual pipeline network, compare them one by one with the simulation results, calculate the error between the predicted value and the actual value, and use the optimization algorithm of the gradient descent method to adjust the parameters of the model. Through multiple iterations, the error is continuously reduced so that the flow direction analysis results gradually approach the actual fluid flow situation. After multiple iterations and optimization, the flow direction and flow distribution results of the fluid in the pipeline network are output, and the pipeline network flow diagram is generated. The visualization function of the computational fluid dynamics (CFD) software is used to intuitively display the flow direction of the fluid in each pipeline section, provide a flow distribution table, and list the flow values ​​of each pipeline section; The pipeline network fault diagnosis module is used to combine the pipeline network topology model and flow direction analysis results, use the pre-built fault diagnosis model to diagnose pipeline network faults, identify fault types and fault locations, and diagnose pipeline network faults quickly and accurately to reduce the misdiagnosis rate; The repair plan generation module is used to generate repair plans based on the fault diagnosis results, combined with the topological structure and flow direction information of the pipeline network, and analyze the effects of different repair plans through simulation of the repair process, optimize the repair strategy, reduce the repair cost and construction risk, ensure the feasibility and efficiency of the repair plan, and improve the efficiency and quality of the repair work; The pipeline operation monitoring module is used to continuously monitor the repaired pipeline network, collect the operation data of the pipeline network, adjust the repair plan according to the operation status of the pipeline network, optimize the pipeline network management, and ensure the stable operation and efficient management of the system.

[0021] Embodiment 2, as Figure 1 , Figure 2As shown, based on Embodiment 1, the present invention provides a technical solution: Preferably, the pipeline network fault diagnosis module specifically includes: Integrate the pipeline network topology structure model, the flow direction analysis result, and the real-time monitoring data to ensure that all data are aligned in terms of timestamp and spatial position, remove noise data and outliers, and extract fault features from the integrated data. Among them, the fault features include the pressure change rate, the flow rate mutation amplitude, the node pressure deviation, and the flow direction deviation. Input the extracted fault features into a pre-constructed fault diagnosis model, match them with the preset fault modes in the fault diagnosis model, calculate the similarity between the fault features and each fault mode, and determine whether there is a fault. Among them, collect information such as the connection relationship, length, diameter, and material of the pipelines in the pipeline network, obtain data such as the position coordinates and types of nodes, collect historical monitoring data such as the pressure and flow rate of each node in the pipeline network, record the relevant data when a fault occurs, including the fault type, the fault occurrence time, the fault location, the changes in pressure and flow rate before and after the fault, etc., deploy a sensor network to obtain the pressure, flow rate, etc. data of each node in the pipeline network in real time, and preprocess the collected data, divide it into a training set, a validation set, and a test set. The training set is used to train the model, the validation set is used to adjust the hyperparameters of the model, and the test set is used to evaluate the final performance of the model. Use the training set to train the neural network model, use the extracted fault features as the model input, and whether there is a fault as the model output. By continuously adjusting the parameters of the model, minimize the loss function of the model on the training set. Use the validation set to evaluate the model during the training process, adjust the hyperparameters of the model according to the evaluation results, and select the optimal model configuration. Use the test set to evaluate the trained model, and the evaluation indicators include accuracy, recall rate, F1 value, confusion matrix, etc. The accuracy reflects the proportion of correct classifications of the model, the recall rate reflects the ability of the model to identify positive examples (fault samples), the F1 value is the harmonic mean of the accuracy and the recall rate, comprehensively considering the performance of both, and the confusion matrix can intuitively display the classification situation of the model for different fault types. Finally, obtain the trained fault diagnosis model. After determining the fault type, further locate the fault location, combine the pipeline network topology structure model, analyze the propagation path and influence range of the fault features in the pipeline network, and generate a fault report. Output the diagnosed fault type and fault location in an intuitive way. The fault report details the fault type, occurrence location, and influence range information, and is accompanied by a pipeline network topology structure diagram with the fault location marked on the diagram; In addition, the calculation process of the similarity between the fault features and each fault mode is as follows: Integrate the pipeline network topology structure model, flow analysis results, and real-time monitoring data to ensure that all data is aligned in terms of timestamp and spatial location. Extract fault features including pressure change rate, flow mutation amplitude, node pressure deviation, and flow direction deviation from the integrated data. For each fault feature, determine its current value and the corresponding characteristic typical value in the fault mode, and then calculate the relative difference between its current value and the corresponding characteristic typical value in the k-th fault mode. Sum the squares of the relative differences of all fault features, take the square root to obtain the standardized difference function. Calculate the average value of the ratio of the fault feature to the fault mode feature, and substitute the calculated average value into the sine function to obtain the sensitivity adjustment function. Combine the standardized difference function and the sensitivity adjustment function to calculate the similarity of the k-th fault mode. When the standardized difference function is close to 1, it indicates a high degree of matching between the fault feature and the fault mode. When the sensitivity adjustment function is close to 1, it indicates that the overall trend of the fault feature is consistent with the fault mode. That is, when the similarity of the k-th fault mode is closer to 1, it means that the fault feature is more similar to the k-th fault mode, and the possibility of the fault is greater; The calculation expression for the similarity between the fault feature and each fault mode is: ; In the formula, is the similarity between the k-th fault mode and the current fault feature, is the current value of the i-th fault feature extracted, is the typical value of the j-th fault feature in the k-th fault mode, is the current value of the i-th fault feature extracted, is the k-th, is the i-th, in the k-th fault mode, is the number of fault features, The closer the value of is to 1, the more similar the fault feature is to the k-th fault mode, and the more likely the fault represented by this fault mode exists; The closer the value of is to 1, the more similar the fault feature is to the k-th fault mode, and the more likely the fault represented by this fault mode exists; The repair plan generation module specifically includes: According to the fault type, location and scope of influence information output by the fault diagnosis module, combined with the pipe network topology structure and flow direction information, analyze the key pipeline segments and nodes involved in the fault, and screen out the preliminary repair plans applicable to this fault type from the pre-set repair strategy library. Import the preliminary screened repair plans one by one, simulate the repair process, evaluate the impact of the repair on the operation of the pipe network, including the interruption time of water supply, short-term fluctuations in water pressure in the surrounding area, etc. At the same time, calculate the cost and expected repair time of each plan, and then optimize the preliminary repair plan based on the simulation results. Compare the cost, construction difficulty and influencing factors of the pipe network operation of different plans to select a better repair technology. Among them, for complex loop or branch faults, optimize the repair sequence to avoid secondary faults or construction conflicts. Finally, generate one or more sets of optimized repair plans to ensure that the plans achieve the best balance among cost, construction risk and operation impact. Output the optimized repair plan in an intuitive way, including detailed construction steps, list of required materials and equipment, cost budget, estimated repair time and suggestions for temporary measures to ensure the smooth progress of the repair work, improve the repair efficiency and quality, and ensure the rapid restoration of stable operation of the pipe network; The pipe network operation monitoring module specifically includes: In the repaired pipe network system, through the integrated pressure sensors, flow sensors and monitoring equipment, collect the operation data of the pipe network in real time, including pipeline pressure, flow rate, liquid level, etc., to reflect the current operation state of the pipe network, and import the collected operation data into the design management platform for comparison and analysis with the pre-set normal operation thresholds, monitor whether the pressure fluctuates abnormally, whether the flow rate meets the expectations, etc., and judge whether the pipe network is in a normal operation state. If it is found that the data exceeds the set normal operation threshold, automatically trigger an alarm, record the abnormal situation and generate a preliminary analysis report. According to the monitored abnormal situation, combined with the pipe network topology structure and flow direction information, analyze the cause and scope of influence of the fault. If it is found that there are new problems in the repaired pipe network, adjust the repair plan to ensure the stable operation of the pipe network. Re-implement the adjusted repair plan and continuously monitor the operation of the pipe network. By comparing the operation data before and after the adjustment, evaluate the effect of the optimized plan. At the same time, generate a pipe network operation report regularly to summarize the operation state, problems found and solutions, providing a reference for the long-term management and maintenance of the pipe network.

[0022] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A repair analysis system for the topology of an intelligent pipe network, including a design management platform, characterized in that: The described design management platform is communicatively connected to a topology structure data acquisition module, a topology structure analysis module, a pipe network fault diagnosis module, a repair plan generation module, and a pipe network operation monitoring module; The topology structure data acquisition module is used to integrate various sensors and external data sources in the pipe network system, collect and preprocess the pipe network operation data and spatial information; The topology structure analysis module is used to analyze the preprocessed pipe network operation data and spatial information, construct a pipe network topology structure model, and further analyze the pipe connection relationship and flow direction; The pipe network fault diagnosis module is used to combine the pipe network topology structure model and the flow direction analysis result, and use the pre-constructed fault diagnosis model to diagnose the pipe network fault and identify the fault type and fault location; The repair plan generation module is used to generate a repair plan according to the fault diagnosis result, combine the topology structure and flow direction information of the pipe network, simulate the repair process, analyze the effects of different repair plans, and optimize the repair strategy; The pipe network operation monitoring module is used to continuously monitor the repaired pipe network, collect the operation data of the pipe network, and adjust the repair plan according to the operation condition of the pipe network.

2. The repair analysis system for an intelligent pipe network topology structure according to claim 1, wherein: The topology structure data acquisition module specifically includes: In the pipe network system, according to the layout and key nodes of the pipe network, deploy various sensors including pressure sensors, flow sensors, and liquid level sensors, plan the sensor layout in combination with the pipe network topology structure and monitoring key points, install the sensors at the positions of pipe connection points, branch points, and loop nodes, and monitor the operation state of the pipe network in real time to obtain the pipe network operation data; Integrate external data sources including geographic information systems and historical maintenance records, obtain GIS data, and at the same time, sort out the pipe network historical maintenance records covering the content of maintenance time, fault type, and treatment method; Integrate the collected pipe network operation data, GIS data, and historical maintenance records, enter the data preprocessing stage, annotate and supplement the collected data in combination with GIS data and historical maintenance records to form complete pipe network operation data and spatial information, construct a complete data set, and then store the preprocessed data in the data warehouse.

3. The repair analysis system for an intelligent pipe network topology structure according to claim 1, wherein: The topology structure identification and analysis module includes a topology feature extraction unit, a topology structure modeling unit, and a flow direction analysis unit; Among them, the topology feature extraction unit is used to extract the operation features and spatial features related to the pipe network topology structure from the preprocessed pipe network operation data and spatial information, and integrate them to obtain the pipe network topology structure feature sequence; The topology structure modeling unit is used to analyze the features in the collected pipe network topology structure feature sequence by using artificial intelligence technology based on graph neural networks, and construct a pipe network topology structure model to represent the pipe connection relationship, branch points, and loop structure; The flow direction analysis unit, based on the constructed pipe network topology structure model, analyzes the flow direction of the fluid in the pipe network, and determines the flow direction and flow rate distribution of the fluid in different pipe segments through computational fluid dynamics simulation.

4. The repair analysis system for an intelligent pipe network topology structure according to claim 3, characterized in that: The topology feature extraction unit specifically includes: From the preprocessed pipeline network operation data, screen out the key feature points reflecting the pipeline network topology structure, and with reference to the spatial information, determine the positions of the key feature points in the spatial layout of the pipeline network, and preliminarily construct a set of feature points; For the screened key feature points, extract the operation features related to the pipeline network operation status, including pressure gradient, flow peak and valley values, and flow change frequency; According to the spatial information of the pipeline network, extract the spatial features between the key feature points. Among them, by calculating the Euclidean distance between the feature points, estimate the actual length of the pipeline, analyze the connection sequence and branch angle of the key feature points, and determine the pipeline orientation and branch situation; Integrate the extracted operation features and spatial features, and according to the topological order of the pipeline network, arrange and combine the operation features and spatial features of each key feature point to form a comprehensive feature sequence, which is the pipeline network topology structure feature sequence.

5. The repair analysis system for an intelligent pipe network topology structure according to claim 4, characterized in that: The topology structure modeling unit specifically includes: According to the pipeline network topology structure, use the screened key feature points as the nodes of the graph. According to the actual connection situation of the pipeline network, establish edges between the nodes to represent the connection relationship of the pipelines, construct the graph structure representation of the pipeline network, clarify the attributes of each node and each edge, and according to the actual connection situation of the pipeline network, establish edges between the nodes and initialize the weights of the edges; Use the aggregation mechanism of the graph neural network to aggregate the features of each node and its neighbor nodes, collect the feature information of the neighbor nodes of each node, determine the directly connected nodes of each node, that is, the neighbor nodes, by traversing the graph structure, obtain the feature vectors of the neighbor nodes, and fuse and update the collected neighbor node feature information with the features of the node itself; Train the constructed graph structure to learn the feature representations of the nodes and edges, define a loss function, calculate the loss by comparing the difference between the predicted topology structure and the actual topology structure, and use the gradient descent optimization algorithm to update the parameters of the model. During the training process, learn the mapping relationship between the node features and the topology structure; After the training is completed, use the learned feature representations of the nodes and edges to generate the final pipeline network topology structure model. Represent the connection relationship, branch points and loop structure of the pipelines through the pipeline network topology structure model, and output the feature representation of each node, the connection weights between the nodes, and the topology structure diagram of the entire pipeline network.

6. The repair analysis system for an intelligent pipe network topology structure according to claim 5, characterized in that: The flow direction analysis unit specifically includes: Based on the constructed pipeline network topology structure model, initialize according to the design parameters of the pipeline network, set the initial flow direction and flow distribution assumption of the fluid in the pipeline network, and at the same time, clarify the types and boundary conditions of each node, and determine the inlet pressure, flow rate, and outlet pressure or free outflow condition of the pipeline network; Select a computational fluid dynamics software, import the pipe network topology structure model into it, simulate the fluid flow in the pipe network, initialize the simulation environment in the computational fluid dynamics software, set the parameters of the simulation time step and the number of iterations, calculate the pressure changes and flow rate distributions of the fluid in different pipe segments by solving the continuity equation and the energy equation, and discretize the continuous equations using the finite difference method to form a solvable system of equations to predict the flow behavior of the fluid in the pipe network; Compare the flow direction results obtained from the simulation with the actual pipe network operation data. Collect the flow rate, flow direction of each pipe segment and the pressure data of the nodes in the actual pipe network, compare them one by one with the simulation results, calculate the error between the predicted value and the actual value, and use the optimization algorithm of the gradient descent method to adjust the parameters of the model. Through multiple iterations, make the flow direction analysis results gradually approach the actual fluid flow situation; After multiple iterations of optimization, output the flow direction and flow rate distribution results of the fluid in the pipe network, generate a pipe network flow direction map, and use the visualization function provided by the computational fluid dynamics software to intuitively display the flow direction of the fluid in each pipe segment and provide a flow rate distribution table listing the flow rate values of each pipe segment.

7. The repair analysis system for an intelligent pipe network topology structure according to claim 3, wherein: The pipe network fault diagnosis module specifically includes: Integrate the pipe network topology structure model, the flow direction analysis results and the real-time monitoring data, and extract the fault features from the integrated data. Among them, the fault features include the pressure change rate, the flow rate mutation amplitude, the node pressure deviation and the flow direction deviation; Input the extracted fault features into a pre-constructed fault diagnosis model, match them with the preset fault modes in the fault diagnosis model, calculate the similarity between the fault features and each fault mode, and determine whether there is a fault; After determining the fault type, further locate the fault location. Combine the pipe network topology structure model, analyze the propagation path and influence range of the fault features in the pipe network, and generate a fault report. Output the diagnosed fault type and fault location in an intuitive manner, accompanied by a pipe network topology structure diagram with the fault location marked on the diagram.

8. The repair analysis system for an intelligent pipe network topology structure according to claim 7, wherein: The calculation process of the similarity between the fault features and each fault mode is as follows: Integrate the pipe network topology structure model, the flow direction analysis results and the real-time monitoring data to ensure that all data are aligned in terms of time stamp and spatial position. Extract the fault features including the pressure change rate, the flow rate mutation amplitude, the node pressure deviation and the flow direction deviation from the integrated data; For each fault feature, determine its current value and the corresponding characteristic typical value in the fault mode, and then calculate the relative difference between its current value and the corresponding characteristic typical value in the k-th fault mode. Sum the squares of the relative differences of all fault features and take the square root to obtain the standardized difference function; Calculate the average value of the ratio of the fault feature to the fault mode feature, and substitute the calculated average value into the sine function to obtain the sensitivity adjustment function; Combine the standardized difference function and the sensitivity adjustment function to calculate the similarity of the k-th fault mode.

9. The repair analysis system for an intelligent pipe network topology structure according to claim 1, wherein: The repair plan generation module specifically includes: According to the fault type, location, and scope of influence information output by the fault diagnosis module, combined with the pipe network topology and flow direction information, analyze the key pipe segments and nodes involved in the fault, and screen out a preliminary repair plan applicable to this fault type from the pre-set repair strategy library; Import the preliminarily screened repair plans one by one, simulate the repair process, evaluate the impact of the repair on the operation of the pipe network. At the same time, calculate the cost and expected repair time of each plan, and then optimize the preliminary repair plan based on the simulation results to select a better repair technology, and finally generate one or more optimized repair plans; Output the optimized repair plan in an intuitive way, including detailed construction steps, list of required materials and equipment, cost budget, estimated repair time, and suggestions for temporary measures.

10. The repair analysis system for an intelligent pipe network topology structure according to claim 9, characterized in that: The pipe network operation monitoring module specifically includes: In the repaired pipe network system, through the integrated pressure sensors, flow sensors, and monitoring devices, collect the operation data of the pipe network in real time, and import the collected operation data into the design management platform, and compare and analyze it with the pre-set normal operation threshold to determine whether the pipe network is in a normal operation state. If it is found that the data exceeds the set normal operation threshold, an alarm will be automatically triggered, the abnormal situation will be recorded, and a preliminary analysis report will be generated; According to the monitored abnormal situation, combined with the pipe network topology and flow direction information, analyze the cause of the fault and the scope of influence. If it is found that there are new problems in the repaired pipe network, adjust the repair plan; Re-implement the adjusted repair plan, and continuously monitor the operation of the pipe network. By comparing the operation data before and after the adjustment, evaluate the effect of the optimization plan. At the same time, generate a pipe network operation report regularly to summarize the operation status, problems found, and solutions.

Images