A method and system for dynamic identification of low-pressure areas in a water supply network

Abstract

The present application relates to the technical field of water supply network pressure identification, and particularly relates to a water supply network low-pressure area dynamic identification method and system. The method comprises the following steps: performing water supply network operation discrete monitoring data on water supply network operation monitoring topology analysis to generate water supply network operation monitoring topology data; performing data anomaly adjacent compensation optimization processing on the water supply network operation monitoring topology data to generate optimized water supply network operation monitoring topology data; performing dynamic propagation characteristic analysis on the water supply network pressure based on the optimized water supply network operation monitoring topology data to generate water supply network pressure dynamic propagation characteristic data; and performing water supply network low-pressure area dynamic identification processing based on the optimized water supply network operation monitoring topology data and the water supply network pressure dynamic propagation characteristic data to generate water supply network low-pressure area dynamic identification data. The present application realizes accurate and comprehensive water supply network low-pressure area dynamic identification.

Description

Technical Field

[0001] This invention relates to the field of water supply network pressure identification technology, and in particular to a method and system for dynamic identification of low-pressure areas in water supply networks. Background Technology

[0002] Water supply networks are a core component of urban infrastructure, and their operational stability directly affects the safety and convenience of residential and industrial water use. Accurate identification of low-pressure areas within the network is crucial for ensuring efficient operation and timely detection of potential water supply hazards. During network operation, factors such as water consumption fluctuations, network aging, pipe leaks, and pump station adjustments cause low-pressure areas to exhibit dynamic changes in location, extent, and intensity. However, existing low-pressure area identification technologies suffer from problems such as scattered monitoring points and incomplete data coverage. They fail to reflect the continuous spatial distribution of network pressure, and data anomalies at some monitoring points affect the accuracy of low-pressure area identification, making it difficult to achieve dynamic coverage of the entire network. This leads to missed or false low-pressure areas and fails to fully integrate the spatial relationships of the network topology, making it impossible to accurately capture the dynamic propagation patterns of pressure disturbances and the dynamic changes in network operation status. Consequently, these technologies struggle to meet the practical needs of refined operation and maintenance of water supply networks and timely handling of low-pressure hazards. Summary of the Invention

[0003] Based on this, the present invention provides a method and system for dynamic identification of low-pressure areas in water supply networks to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a method for dynamic identification of low-pressure areas in a water supply network includes the following steps: Step S1: Use multi-source monitoring sensors to perform discrete point operation monitoring and processing of the water supply network to generate discrete monitoring data of the water supply network operation; perform topology analysis of the water supply network operation monitoring data to generate topology data of the water supply network operation monitoring. Step S2: Perform adjacency compensation optimization processing on the water supply network operation monitoring topology data to generate optimized water supply network operation monitoring topology data; Step S3: Based on the optimized water supply network operation monitoring topology data, perform dynamic propagation characteristic analysis of water supply pressure in the network to generate dynamic propagation characteristic data of water supply pressure in the network; Step S4: Based on the optimized water supply network operation monitoring topology data and the dynamic propagation characteristic data of water supply pressure in the network, perform dynamic identification processing of low-pressure areas in the water supply network to generate dynamic identification data of low-pressure areas in the water supply network.

[0005] Furthermore, step S1 includes the following steps: Step S11: Obtain water supply network deployment design data; Step S12: Extract the characteristic point data of the water supply network deployment through the water supply network deployment design data, and perform monitoring adaptation analysis based on the characteristic point data of the water supply network deployment to generate monitoring adaptation data of the water supply network points; Step S13: Based on the water supply network point monitoring adaptation data, design the water supply network monitoring configuration analysis, obtain the water supply network monitoring configuration data, and use the multi-source monitoring sensors configured with the water supply network monitoring configuration data to perform discrete point operation monitoring processing of the water supply network, generating discrete monitoring data of water supply network operation. Step S14: Perform time-series unified processing on the discrete monitoring data of water supply network operation to generate time-series discrete monitoring data of water supply network operation; Step S15: Based on the water supply network deployment design data and the time-series discrete monitoring data of the water supply network operation, perform spatial continuous reconstruction processing of the water supply network operation monitoring to generate water supply network operation monitoring topology data.

[0006] Furthermore, step S15 includes the following steps: Step S151: Analyze the operating characteristics of the monitoring nodes based on the discrete monitoring data of the time-series water supply network operation, and generate operating characteristic data of the water supply network monitoring nodes; Step S152: Perform a topology analysis of the water supply network operation space based on the water supply network deployment design data to generate water supply network operation space topology data; Step S153: Map the time-series discrete monitoring data of water supply network operation corresponding to the operation characteristic data of water supply network monitoring nodes to the spatial topology data of water supply network operation, and perform spatial continuous reconstruction processing of water supply network operation monitoring to generate water supply network operation monitoring topology data.

[0007] Furthermore, step S2 includes the following steps: Step S21: Design the topology association relationship for the water supply network operation monitoring topology data to establish the operation monitoring topology association matrix; Step S22: Analyze the pressure drop characteristic relationship and mass conservation characteristic relationship of operation association based on the operation monitoring topology correlation matrix, and obtain the operation association pressure drop characteristic relationship data and operation association mass conservation characteristic relationship data respectively; Step S23: Based on the operational correlation pressure drop characteristic relationship data and the operational correlation mass conservation characteristic relationship data, perform anomaly characteristic analysis on the operational monitoring topology data of the water supply network to generate operational monitoring topology anomaly characteristic data; Step S24: Perform adjacency compensation optimization processing on the water supply network operation monitoring topology data by using the operation monitoring topology anomaly feature data to generate optimized water supply network operation monitoring topology data.

[0008] Furthermore, step S3 includes the following steps: Step S31: Based on the optimized water supply network operation monitoring topology data, perform propagation guidance topology feature analysis of water supply network operation, generate propagation guidance topology feature data, and design water supply network guidance propagation diagram structure data through propagation topology feature data; Step S32: Perform graph structure attribute feature analysis based on the water supply network guidance propagation graph structure data to generate water supply network graph structure attribute feature data; Step S33: Perform structural abstraction processing of the elastic waveguide network of the water supply network using the structural data of the water supply network directional propagation diagram and the structural attribute feature data of the water supply network diagram, and generate the structural data of the elastic waveguide network of the water supply network. Step S34: Analyze the characteristic points of pipeline pressure propagation based on the pipeline elastic waveguide network structure data, and generate pipeline pressure propagation characteristic point data; Step S35: Based on the optimized water supply network operation monitoring topology data and network pressure propagation characteristic point data, perform network propagation water supply pressure disturbance characteristic analysis to generate network propagation water supply pressure disturbance characteristic data; Step S36: Analyze the dynamic propagation characteristics of water supply pressure in the optimized water supply network operation monitoring topology data by using the network elastic waveguide network structure data, network pressure propagation characteristic point data, and network water supply pressure disturbance characteristic data, and generate network water supply pressure dynamic propagation characteristic data.

[0009] Furthermore, step S34 includes the following steps: Step S341: Analyze the pressure propagation influence characteristics of the pipeline distribution based on the pipeline elastic waveguide network structure data, and generate pipeline distribution pressure propagation influence characteristic data; Step S342: Based on the characteristic data of pressure propagation influence in the pipeline distribution area, perform relevant propagation behavior aggregation processing in the pipeline distribution neighborhood to generate pipeline distribution neighborhood relevant propagation behavior aggregation data; Step S343: Based on the aggregated data of pipeline distribution neighborhood related propagation behavior, filter and process pipeline pressure propagation feature points to generate pipeline pressure propagation feature point data.

[0010] Furthermore, step S35 includes the following steps: Step S351: Based on the optimized water supply network operation monitoring topology data, analyze the water supply pressure change trend of the network pressure propagation characteristic points and generate water supply pressure change trend data of the network propagation characteristic points; Step S352: Perform short-term fluctuation analysis on the water supply pressure change trend data of the propagation characteristic points of the pipeline network to generate short-term fluctuation data of the pressure trend of the propagation characteristic points; Step S353: Analyze the characteristics of water supply pressure disturbance propagation in the pipeline network based on the short-term fluctuation data of pressure trend at the propagation characteristic points, and generate characteristic data of water supply pressure disturbance propagation in the pipeline network.

[0011] Furthermore, step S4 includes the following steps: Step S41: Analyze the characteristics of the water supply network operation status based on the optimized water supply network operation monitoring topology data, and generate water supply network operation status characteristic data. Step S42: Analyze the dynamic propagation characteristic data of water supply pressure in the pipeline network by using the pipeline network operation status characteristic data, and generate pipeline network water supply pressure propagation response area data; Step S43: Perform propagation attenuation gradient attribute analysis on the propagation response area data of water supply pressure in the pipeline network to generate pipeline water supply pressure propagation response attribute area data; Step S44: Based on the regional data of water supply pressure propagation response attributes and the optimized water supply network operation monitoring topology data, perform water supply network pressure response characteristic analysis to generate water supply network pressure response characteristic data; Step S45: Based on the pressure response characteristic data of the water supply network, perform dynamic identification processing of the low-pressure area of ​​the water supply network to generate dynamic identification data of the low-pressure area of ​​the water supply network.

[0012] Furthermore, step S45 includes the following steps: Step S451: Based on the pressure response characteristic data of the water supply network, perform instability characteristic identification processing of the pressure response of the water supply network to generate instability characteristic data of the pressure response of the water supply network. Step S452: Based on the regional data of water supply pressure propagation response attributes and the water supply network pressure response instability characteristic data, perform dynamic instability characteristic analysis of water supply pressure propagation to generate dynamic instability characteristic data of water supply pressure propagation. Step S453: Dynamically identify low-pressure areas of the water supply network by using the pressure response instability characteristic data and the dynamic instability characteristic data of water supply pressure propagation, and generate dynamic identification data of low-pressure areas of the water supply network.

[0013] This specification provides a dynamic identification system for low-pressure areas in a water supply network, used to execute the dynamic identification method for low-pressure areas in a water supply network as described above. The dynamic identification system for low-pressure areas in a water supply network includes: The water supply network operation monitoring module is used to process discrete point operation monitoring data of the water supply network using multi-source monitoring sensors, and generate discrete monitoring data of the water supply network operation; and to perform operation monitoring topology analysis on the discrete monitoring data of the water supply network operation, and generate operation monitoring topology data of the water supply network. The operation monitoring and optimization module is used to perform adjacency compensation optimization on the water supply network operation monitoring topology data to generate optimized water supply network operation monitoring topology data. The pipeline water supply pressure dynamic propagation characteristic analysis module is used to perform dynamic propagation characteristic analysis of pipeline water supply pressure based on optimized pipeline network operation monitoring topology data, and generate pipeline water supply pressure dynamic propagation characteristic data. The low-pressure area dynamic identification module of the water supply network is used to perform dynamic identification processing of low-pressure areas of the water supply network based on optimized water supply network operation monitoring topology data and dynamic propagation characteristic data of water supply pressure in the network, and generate dynamic identification data of low-pressure areas of the water supply network.

[0014] The beneficial effects of this application are as follows: This invention acquires water supply network deployment design data, accurately extracts characteristic points of the water supply network deployment, and performs monitoring adaptation analysis. It enables the scientific configuration of multi-source monitoring sensors, avoids redundancy or missing monitoring points, and ensures accurate matching between monitoring points and the actual deployment characteristics of the network, resulting in discrete monitoring data reflecting the network's operational status. Time-series unified processing of the discrete monitoring data eliminates deviations in the time dimension of data from different monitoring points, ensuring data temporal consistency and laying the foundation for subsequent spatial continuous reconstruction. Furthermore, the spatial continuous reconstruction based on the water supply network deployment design data and time-series discrete monitoring data maps the operational characteristic data of monitoring nodes and their corresponding time-series data to the network's operational spatial topology, solving the problem that discrete monitoring data cannot reflect the spatial continuous distribution characteristics of network pressure. This fully presents the spatial correlation of network operation, overcoming the limitations of monitoring a single discrete point. Establishing an operational monitoring topology correlation matrix for water supply network operation monitoring topology data clearly identifies the topological relationships between various monitoring nodes and pipe segments, providing a clear basis for subsequent anomaly analysis. Combining the operational monitoring topology correlation matrix with in-depth analysis of pressure drop and mass conservation characteristics of operational correlations fully aligns with the actual operating patterns of the water supply network, effectively and accurately identifying anomalies in the operational monitoring topology data and avoiding distortion of subsequent analysis results due to data anomalies. Adjacency compensation optimization processing of the operational monitoring topology anomaly data allows for precise correction and supplementation of anomalies, ensuring the integrity and accuracy of the optimized water supply network operation monitoring topology data. Based on the optimized water supply network operation monitoring topology data, a directional propagation graph structure for the water supply network is designed through propagation guidance topology feature analysis, clearly identifying the directional relationships of pressure propagation in the network. Then, combining the graph structure attribute characteristics, the structure of the network's elastic waveguide network is abstracted, transforming the complex network structure into a precisely analyzable waveguide network model, providing a scientific analytical framework for pressure propagation characteristic analysis. In pressure propagation characteristic point analysis, by analyzing the impact characteristics of pressure propagation, aggregating neighborhood propagation behavior, and filtering characteristic points, it is possible to accurately locate key characteristic points that play a crucial role in pressure propagation and avoid interference from invalid points. In pressure disturbance characteristic analysis, by combining optimized topology data and characteristic point data, analyzing pressure change trends and short-term fluctuations, the dynamic characteristics of pipeline pressure disturbances can be accurately captured, achieving a refined decomposition of the pressure propagation process. By integrating waveguide network structure, characteristic points, and disturbance characteristic data, dynamic pressure propagation characteristic analysis is completed, comprehensively and accurately reflecting the dynamic propagation law of pipeline pressure and precisely capturing dynamic pressure propagation characteristics.Supported by optimized topology data and dynamic pressure propagation characteristic data, this method comprehensively grasps the overall operational status of the water supply network through operational status characteristic analysis, laying the foundation for pressure propagation response area analysis. Furthermore, by combining operational status characteristic data, response area analysis is performed on dynamic pressure propagation characteristic data to accurately delineate the impact range of pressure propagation. Then, through propagation attenuation gradient attribute analysis, the pressure attenuation pattern within the response area is clarified, clearly distinguishing the pressure state differences in different areas. In pressure response characteristic analysis, by combining response attribute area data and optimized topology data, the core characteristics of the network pressure response are further refined, providing precise guidance for low-pressure area identification. During the dynamic identification of low-pressure areas, instability feature identification and dynamic instability feature analysis accurately capture the instability characteristics and dynamic change patterns of low-pressure areas, achieving dynamic identification of the location, range, and intensity of low-pressure areas. This effectively solves the problems of inability to adapt to the dynamic operational status of the network, delayed identification results, and missed or misjudged cases, providing accurate basis for timely handling of low-pressure hazards in the water supply network and refined operation and maintenance.

[0015] Therefore, the dynamic identification method for low-pressure areas in water supply networks of this invention achieves comprehensive monitoring of discrete points in the water supply network through multi-source monitoring sensors, and completes spatial continuous reconstruction of operation monitoring by combining network deployment design data. This solves the problems of discrete and incomplete coverage of monitoring data at fixed points, significantly improving the integrity and comprehensiveness of monitoring data. By performing adjacency compensation optimization on the monitoring topology data, distortion of pressure analysis results is avoided. Simultaneously, by combining the analysis of the network's elastic waveguide network structure to determine the dynamic propagation characteristics of water supply pressure, and fully considering the spatial correlation of the network topology, the dynamic propagation law of pressure disturbances can be accurately captured, enabling dynamic tracking and identification of low-pressure areas. During the identification process, core factors such as pressure drop characteristics and mass conservation in network operation are fully considered, overcoming the limitations of static identification. This allows for real-time adaptation to dynamic changes in network operation status, effectively solving the problem of delayed identification results, and accurately identifying the location, range, and intensity of low-pressure areas. This meets the practical needs of refined operation and maintenance of water supply networks and timely handling of low-pressure hazards. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the steps of a method for dynamic identification of low-pressure areas in a water supply network according to the present invention. Figure 2 for Figure 1 A detailed flowchart illustrating the implementation steps of step S3. The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0018] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. Functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods. The term "and / or" as used herein includes any and all combinations of one or more of the associated items listed.

[0019] To achieve the above objectives, please refer to Figures 1 to 2 This invention provides a method for dynamic identification of low-pressure areas in water supply networks. In the embodiments of this invention, please refer to... Figure 1 The diagram shown is a flowchart illustrating the steps of a method for dynamically identifying low-pressure areas in a water supply network according to the present invention. The method includes the following steps: Step S1: Use multi-source monitoring sensors to perform discrete point operation monitoring and processing of the water supply network to generate discrete monitoring data of the water supply network operation; perform topology analysis of the water supply network operation monitoring data to generate topology data of the water supply network operation monitoring. In this embodiment of the invention, multi-source monitoring sensors are used to continuously monitor the operation of discrete points in the water supply network. The multi-source monitoring sensors are deployed at key hydraulic nodes in the water supply network, covering core points such as pump station outlets, pipe section intersections, and water supply area boundary nodes. The monitoring objects include core hydraulic parameters such as water supply pressure and flow rate. The monitoring process continuously collects real-time operation data of each discrete point at fixed time intervals. All collected data carries the monitoring point identifier and collection timestamp, thereby generating discrete monitoring data of the water supply network operation. Subsequently, a topological analysis of the discrete monitoring data of the water supply network was conducted. This involved clarifying the physical topology of the network, identifying the pipe segment connections, spatial relationships, and hydraulic transmission paths between discrete monitoring points, and then matching the discrete monitoring data with the network's physical topology to determine the pipe segment attributes and node relationships corresponding to each monitoring point. Simultaneously, the discrete monitoring data underwent time-series analysis to ensure consistency across time. Through this topological association and time-series analysis, the discrete monitoring data was integrated into a water supply network operation monitoring topological data system with spatial correlation and time-series characteristics. This data retains real-time monitoring information from all discrete points while fully presenting the topological structure and hydraulic relationships of the water supply network, providing fundamental support for subsequent data optimization and pressure propagation analysis, thus realizing the transformation from discrete monitoring to topological integration.

[0020] Step S2: Perform adjacency compensation optimization processing on the water supply network operation monitoring topology data to generate optimized water supply network operation monitoring topology data; In this embodiment of the invention, adjacency compensation optimization processing is performed on the water supply network operation monitoring topology data to identify data anomalies. Abnormal data in the topology data is identified and precisely corrected using valid adjacent data. A comprehensive investigation of all monitoring data and topology relationships within the water supply network operation monitoring topology data is conducted. Based on the hydraulic operation patterns of the water supply network, data exceeding normal operating ranges, data exhibiting significant contradictions with adjacent point data, and data with abnormal topology relationships are identified, clarifying the monitoring points and pipe segments corresponding to the abnormal data. Based on the topology relationships in the water supply network operation monitoring topology data, valid monitoring data from all adjacent monitoring points corresponding to the abnormal data are extracted. Adjacent points are defined as monitoring points directly connected to the abnormal point by a pipe segment and possessing the same hydraulic transmission attributes. Through comprehensive analysis of the valid data from adjacent points, combined with the hydraulic transmission patterns of the network, compensation and correction are performed on the abnormal data. The correction process fully relies on the real-time monitoring data of adjacent points and the strength of the topology relationship to ensure that the corrected data maintains hydraulic logic consistency with the adjacent point data and matches the overall operation status of the network. After the correction is completed, all valid data and the corrected data are integrated, and the complete pipeline topology relationship is preserved to generate optimized water supply pipeline network operation monitoring topology data. This data eliminates abnormal interference in the original topology data, improves the integrity and accuracy of the data, and ensures that subsequent pressure propagation characteristic analysis and low-pressure area identification can be carried out based on reliable data, avoiding abnormal data from causing the analysis results to be distorted.

[0021] Step S3: Based on the optimized water supply network operation monitoring topology data, perform dynamic propagation characteristic analysis of water supply pressure in the network to generate dynamic propagation characteristic data of water supply pressure in the network; In this embodiment of the invention, dynamic propagation characteristics of water supply pressure in the pipeline network are analyzed based on optimized water supply network operation monitoring topology data. This analysis uncovers the propagation patterns of pressure in the spatial and temporal dimensions, captures the dynamic changes in pressure propagation, and extracts time-series pressure data, pipeline topology information, and hydraulic transmission attributes of all monitoring points from the optimized water supply network operation monitoring topology data. This clarifies the pressure transmission capacity of each pipeline segment and the strength of the hydraulic correlation between nodes. Subsequently, propagation guidance topology feature analysis is conducted to identify the direction and path of pressure propagation, clarify the role of each node in the pressure propagation process, distinguish the starting point, intermediate point, and ending point of pressure propagation, and construct a guidance propagation graph structure for the water supply network, clearly presenting the guidance relationship of pressure propagation. Based on the guidance propagation graph structure, graph structure attribute analysis is performed to extract core structural attributes related to pressure propagation. Then, the pipeline network structure is abstracted into an elastic waveguide network, transforming the complex pipeline network structure into a waveguide network model that can accurately analyze the pressure propagation patterns. By using a waveguide network model, key feature points that play a crucial role in pressure propagation are identified. The pressure change trends and short-term fluctuations at these feature points are analyzed to capture the generation, propagation, and attenuation patterns of pressure disturbances. Finally, the steady-state pressure propagation characteristics, disturbance propagation characteristics, propagation paths, attenuation patterns, and the effects of feature points are integrated to generate dynamic propagation feature data of water supply pressure in the pipeline network. This data fully presents the dynamic propagation pattern of pressure in the pipeline network, providing core feature basis for subsequent dynamic identification of low-pressure areas.

[0022] Step S4: Based on the optimized water supply network operation monitoring topology data and the dynamic propagation characteristic data of water supply pressure in the network, perform dynamic identification processing of low-pressure areas in the water supply network to generate dynamic identification data of low-pressure areas in the water supply network.

[0023] In this embodiment of the invention, low-pressure areas of the water supply network are dynamically identified based on optimized water supply network operation monitoring topology data and dynamic propagation characteristic data of water supply pressure. This integrates network operation data and pressure propagation characteristics to accurately locate low-pressure areas and capture their dynamic changes. Based on the optimized water supply network operation monitoring topology data, a network water supply operation status characteristic analysis is conducted. Hydraulic operation status parameters of the entire network are comprehensively extracted, the operational stability of each node and pipe segment is quantified, and the distribution of stable and unstable areas, high-resistance and normal-resistance pipe segments is identified. The overall network operation load status and time-varying characteristics are then understood. Subsequently, combined with the network water supply operation status characteristic data, a pressure propagation response region analysis is performed on the dynamic propagation characteristic data of water supply pressure. The response range corresponding to different pressure propagation characteristics is delineated, and the response regions corresponding to steady-state pressure propagation and disturbed pressure propagation are distinguished. The coverage and operational characteristics of each response region are clarified. A propagation attenuation gradient attribute analysis is conducted on each response region to quantify the attenuation law of pressure propagation, clarify the spatial distribution characteristics of the attenuation gradient, and capture the correlation between pressure attenuation and pipe segment attributes and node distribution. Based on the attenuation gradient attribute analysis results and optimized water supply network operation monitoring topology data, pressure response characteristic analysis was conducted to extract core response characteristics related to low-pressure hazards, identify nodes with low pressure, and analyze their causes. Based on these pressure response characteristics, dynamic identification of low-pressure areas was carried out. This involved integrating low-pressure nodes, pressure attenuation patterns, and pressure propagation characteristics to delineate the range of low-pressure areas, classify them by type, and quantify their anomaly severity. Simultaneously, time-series data was used to track the occurrence time, duration, and trends of low-pressure areas. By integrating all relevant information on low-pressure areas, dynamic identification data for low-pressure areas in the water supply network was generated. This provides precise support for the handling of low-pressure hazards and refined operation and maintenance of the water supply network, achieving accurate and dynamic identification of low-pressure areas.

[0024] Furthermore, step S1 includes the following steps: Step S11: Obtain water supply network deployment design data; In this embodiment of the invention, the as-built drawings generated during the construction phase of the urban water supply network and the updated network attribute files during the operation and maintenance phase are retrieved. The obtained water supply network deployment design data includes three core categories: the first category is network topology data, covering the direction, length, diameter, material, and connection method of pipe sections, as well as the type, location coordinates, and connection relationships between nodes; the second category is network ancillary facility data, including the location and design parameters of pump stations, pressure reducing valves, check valves, and fire hydrants, wherein the design head of the pump station is set to 35m, and the pressure reducing threshold of the pressure reducing valve is set to 0.25MPa; the third category is network zoning data, including the boundaries of water supply areas, water supply levels, and the division of main and backup supply paths, ensuring that the obtained deployment design data completely covers all network elements of the target water supply area, providing a basis for subsequent point extraction and monitoring configuration.

[0025] Step S12: Extract the characteristic point data of the water supply network deployment through the water supply network deployment design data, and perform monitoring adaptation analysis based on the characteristic point data of the water supply network deployment to generate monitoring adaptation data of the water supply network points; In this embodiment of the invention, based on the pipeline topology data and ancillary facility data in the water supply pipeline network deployment design data, feature point data of the water supply pipeline network deployment is extracted. For example, according to the principles of mandatory selection of key nodes, densification of main pipeline sections, and balanced branch pipeline sections, the extracted feature points include pump station outlets, pressure reducing valve inlets and outlets, intersections of main and branch pipelines, water supply area boundary nodes, and midpoints of long-distance pipeline sections. The criteria for determining long-distance pipeline sections are pipeline sections with a length exceeding 500 meters. The number of extracted feature points is determined according to the target pipeline network scale, covering all key hydraulic nodes in the target area. Based on the extracted feature point data, monitoring adaptation analysis is carried out. The analysis dimensions include the installation space conditions, hydraulic characteristics, and interference factors of the points. The installation space conditions determine whether the point has the physical space for sensor installation. The hydraulic characteristics analyze the design pressure range and flow range of the point. The interference factors check whether there are factors such as strong electromagnetic interference and severe vibration that may affect the monitoring. The monitoring adaptation data of the water supply network points are generated by combining the three types of analysis results. This data clarifies the adapted monitoring type and sensor installation method for each feature point. The adapted monitoring type is divided into two categories: pressure monitoring and flow monitoring. The installation method is divided into two categories: flange connection installation and threaded connection installation. This directly determines the monitoring implementation plan for each feature point.

[0026] Step S13: Based on the water supply network point monitoring adaptation data, design the water supply network monitoring configuration analysis, obtain the water supply network monitoring configuration data, and use the multi-source monitoring sensors configured with the water supply network monitoring configuration data to perform discrete point operation monitoring processing of the water supply network, generating discrete monitoring data of water supply network operation. In this embodiment of the invention, the water supply network monitoring configuration analysis is carried out based on the water supply network point monitoring adaptation data. The resulting water supply network monitoring configuration data includes three core contents: sensor selection, installation parameters, and monitoring frequency. In terms of sensor selection, pressure sensors are configured for pressure monitoring points with a measurement range of 0-1.6MPa, and flow sensors are configured for flow monitoring points with a measurement range of 0-50m³ / h. In terms of installation parameters, the installation torque of the flange-connected sensor is set to 280N·m, and the installation depth of the threaded-connected sensor is set to 12mm. The monitoring frequency is set to collect data once every 5 seconds. After the on-site installation and parameter debugging of the multi-source monitoring sensors are completed based on the monitoring configuration data, the sensors continuously monitor the discrete characteristic points of the water supply network. The pressure sensor collects the water supply pressure value of the point in real time, and the flow sensor collects the water supply flow value of the point in real time. All sensors continuously generate discrete monitoring data of the water supply network operation, including the monitoring point identifier, pressure value, flow value, and collection timestamp, according to the set monitoring frequency, so as to realize the accurate acquisition of hydraulic parameters of discrete points of the target network.

[0027] Step S14: Perform time-series unified processing on the discrete monitoring data of water supply network operation to generate time-series discrete monitoring data of water supply network operation; In this embodiment of the invention, time-series unified processing is performed on discrete monitoring data of water supply network operation. The processing logic is based on a standard time axis, with the time interval of the standard time axis set to 5 seconds to match the sensor monitoring frequency. The acquisition timestamps of all discrete monitoring data are extracted, and each timestamp is matched to the corresponding time node on the standard time axis. For monitoring data that perfectly matches the standard time node, its original value and location identifier are directly retained. For monitoring data that deviates from the standard time node, they are merged according to the time difference between the acquisition timestamp and the standard time node. Monitoring data with a time difference of less than 2.5 seconds are merged to the previous standard time node, and monitoring data with a time difference of 2.5 seconds or more are merged to the next standard time node. After merging, when multiple data points appear at the same standard time node and the same monitoring point, an arithmetic average is used to calculate a single value. Through this unified time-series processing, the monitoring data of all monitoring points are aligned to a standard time axis with a uniform interval, generating discrete monitoring data of the water supply network operation in time series. This data is indexed by a standard time node, and each index contains the pressure and flow values ​​of all monitoring points, realizing the time-series synchronization of monitoring data from different points.

[0028] Step S15: Based on the water supply network deployment design data and the time-series discrete monitoring data of the water supply network operation, perform spatial continuous reconstruction processing of the water supply network operation monitoring to generate water supply network operation monitoring topology data.

[0029] In this embodiment of the invention, spatial continuous reconstruction processing of water supply network operation monitoring is carried out based on the network topology data in the water supply network deployment design data and the discrete monitoring data of the time-series water supply network operation. First, based on the pipe segment connection relationships and node location coordinates in the network deployment design data, a spatial topology framework containing all pipe segments and nodes is constructed. The framework clearly defines the spatial direction of the pipe segments, the spatial coordinates of the nodes, and their relationship. Then, the discrete monitoring data of the time-series water supply network operation is mapped to the corresponding nodes in the spatial topology framework according to the monitoring point identifiers, so that each node corresponds to time-series pressure and flow monitoring data. For pipe segments without deployed monitoring sensors, based on the monitoring data of the nodes at both ends, combined with the pipe segment length and hydraulic propagation laws, the hydraulic parameter estimates for the middle region of the pipe segment are calculated. These estimates are then added to the spatial topology framework, achieving spatial coverage of monitoring data from discrete points to the entire network. Through this spatial continuous reconstruction process, topological data for water supply network operation monitoring is generated. This data not only preserves the complete spatial topological relationship of the network but also includes time-series hydraulic monitoring data covering the entire region, providing accurate and comprehensive basic data support for subsequent steps such as anomaly optimization and pressure propagation analysis.

[0030] Furthermore, step S15 includes the following steps: Step S151: Analyze the operating characteristics of the monitoring nodes based on the discrete monitoring data of the time-series water supply network operation, and generate operating characteristic data of the water supply network monitoring nodes; In this embodiment of the invention, discrete monitoring data of time-series water supply network operation is used as the basis for analysis. The analysis focuses on all nodes where monitoring sensors are deployed and conducts analysis of the operating characteristics of the monitoring nodes. The core analysis logic is constructed around three dimensions: pressure characteristics, flow characteristics, and fluctuation characteristics. Pressure characteristic analysis calculates the average pressure, extreme pressure, and pressure change per unit time for each monitoring node using 72 consecutive hours of time-series pressure data. The unit time is set to 1 hour. The average pressure reflects the node's basic water supply pressure level, the extreme pressure defines the upper and lower limits of the node's operating pressure, and the pressure change measures the hourly fluctuation amplitude of the node's pressure. Flow characteristic analysis simultaneously calculates the average and peak flow per unit time for each monitoring node using 72 consecutive hours of time-series flow data. Combined with the pressure characteristic data, it establishes the correlation between node pressure and flow, clarifying the coupling law of the node's hydraulic parameters. Fluctuation characteristic analysis calculates the pressure fluctuation coefficient for each monitoring node using pressure change data over 3 consecutive hours. The fluctuation coefficient is calculated as the ratio of the difference in pressure change over 3 hours to the reference pressure, which is the 72-hour average pressure of the node. When the fluctuation coefficient is greater than 0.08, the node is marked as a pressure-sensitive node. The data on the operational characteristics of the water supply network monitoring nodes comprehensively includes the average pressure, extreme pressure, pressure change, average flow, peak flow, and fluctuation coefficient of all monitoring nodes. It also marks pressure-sensitive nodes, accurately depicting the hydraulic operation patterns of each monitoring node and providing characteristic basis for subsequent spatial mapping and reconstruction.

[0031] Step S152: Perform a topology analysis of the water supply network operation space based on the water supply network deployment design data to generate water supply network operation space topology data; In this embodiment of the invention, based on the water supply network deployment design data, a topological analysis of the water supply network's operational space is conducted, with the core objective of transforming the physical spatial structure of the network into an operational topological structure. The connection relationships of pipe segments, node coordinates, and the distribution information of ancillary facilities are extracted from the water supply network deployment design data. A topological node set is constructed with nodes as the core, and a topological edge set is constructed with pipe segments as the core. The topological edge set clearly defines the topological nodes connecting both ends of a pipe segment, the pipe segment length, and the hydraulic transmission attributes of the pipe segment. The hydraulic transmission attributes are determined based on the pipe segment material and diameter, reflecting the resistance characteristics of the pipe segment to water flow. Subsequently, combined with the water supply hierarchy and primary / backup supply path division in the water supply network deployment design data, transmission direction identifiers are added to the topological edge set, clarifying the main flow direction and backup flow direction within the pipe segment. The flow direction is defined by labeling the topological edges of the main supply path as the primary transmission direction and the topological edges of the backup supply path as the secondary transmission direction. Finally, the topological node set, topological edge set, and transmission direction identifiers are integrated to construct a complete topological structure that includes the spatial location of nodes, pipe segment connection relationships, hydraulic transmission attributes, and water flow transmission direction. This structure covers all pipe segments and nodes within the target water supply area without omissions or redundancies. The generated water supply network operation spatial topology data accurately restores the spatial association and hydraulic transmission logic of the water supply network, laying a basic framework for the spatial mapping of subsequent monitoring data.

[0032] Step S153: Map the time-series discrete monitoring data of water supply network operation corresponding to the operation characteristic data of water supply network monitoring nodes to the spatial topology data of water supply network operation, and perform spatial continuous reconstruction processing of water supply network operation monitoring to generate water supply network operation monitoring topology data.

[0033] In this embodiment of the invention, based on the operational characteristic data of water supply network monitoring nodes and the spatial topology data of water supply network operation, spatial continuous reconstruction processing of water supply network operation monitoring is performed to achieve deep fusion and full coverage of monitoring data and physical topology. The processing first maps the discrete time-series water supply network operation monitoring data corresponding to the operational characteristic data of the monitoring nodes to the corresponding topological nodes in the spatial topology data of the water supply network operation, according to the monitoring node identifiers. This ensures that each topological node with deployed monitoring sensors is bound to complete time-series pressure data, time-series flow data, and operational characteristic parameters, including pressure-sensitive node identifiers. For topological nodes in the spatial topology data of the water supply network operation that do not have deployed monitoring sensors, based on the operational characteristic data of their neighboring monitoring nodes, and combined with the pipe segment length and hydraulic transmission attributes of the topological edge set, a hydraulic interpolation algorithm is used to calculate the estimated time-series hydraulic parameters of the node. The interpolation algorithm uses the average pressure of neighboring monitoring nodes as a benchmark and allocates pressure attenuation values ​​according to the pipe segment length ratio. The pressure attenuation coefficient is set to 0.002 based on the hydraulic transmission attributes of the pipe segment. For each meter, the flow rate estimate is calculated based on the law of conservation of mass, using the difference in flow rate data between adjacent nodes. After filling in the hydraulic data of all nodes, the time-series data of adjacent nodes are correlated based on the transmission direction identifier of the topology edge set, clarifying the relationship between the pressure gradient and flow transmission at both ends of the pipe segment. This ultimately forms a water supply network operation monitoring topology data that includes a complete spatial topology structure, time-series hydraulic data of all nodes, node operating characteristics, and hydraulic correlation relationships of pipe segments. This solves the problem that discrete monitoring data cannot reflect the continuous operating status of the pipe network space, providing comprehensive and accurate topology data support for subsequent steps such as anomaly compensation and pressure dynamic propagation analysis.

[0034] Furthermore, step S2 includes the following steps: Step S21: Design the topology association relationship for the water supply network operation monitoring topology data to establish the operation monitoring topology association matrix; In this embodiment of the invention, topological association relationships are designed based on the spatial locations of nodes, pipe segment connections, and hydraulic transmission attributes contained in the water supply network operation monitoring topology data. The rows and columns of the matrix are indexed by the topological node numbers, and the matrix elements are defined as the direct topological association strength between corresponding topological nodes. For two topological nodes with direct pipe segment connections, the matrix element values ​​are determined based on the hydraulic transmission attributes of the pipe segments; the stronger the hydraulic transmission attributes, the greater the association strength, with a value range of 0.8-1.0. For two topological nodes without direct pipe segment connections but with indirect hydraulic associations, the matrix element values ​​are determined based on the number and length of the indirect pipe segments; the more indirect pipe segments and the longer the total length, the smaller the association strength, with a value range of 0.3-0.7. For topological nodes with no hydraulic associations, the matrix element value is 0. Simultaneously, the diagonal elements of the matrix are 1, representing the complete association between the topological node and itself. Through the above design logic, the generated operation monitoring topology correlation matrix has the same dimension as the number of topology nodes, accurately quantifying the direct and indirect hydraulic correlations between all topology nodes, and providing clear correlation structure support for subsequent pressure drop and mass conservation characteristic analysis.

[0035] Step S22: Analyze the pressure drop characteristic relationship and mass conservation characteristic relationship of operation association based on the operation monitoring topology correlation matrix, and obtain the operation association pressure drop characteristic relationship data and operation association mass conservation characteristic relationship data respectively; In this embodiment of the invention, based on the operational monitoring topology correlation matrix, operational correlation pressure drop characteristic relationship analysis and operational correlation mass conservation characteristic relationship analysis are performed respectively. The implementation logic of the operational correlation pressure drop characteristic relationship analysis is as follows: traverse the off-diagonal elements in the correlation matrix with values ​​greater than 0.5, filter out topology node pairs with direct hydraulic correlation, and for each pair of nodes, extract their corresponding time-series pressure data in the water supply network operational monitoring topology data. Calculate the pressure difference between the two nodes per unit time, where the pressure difference reflects the pressure drop between the nodes, and the unit time is set to 1 hour. Combined with the correlation strength of the corresponding elements in the correlation matrix, a weighted average is performed on the pressure difference per unit time, with the weighting coefficient being the correlation strength value. Finally, the operational correlation pressure drop characteristic value of each pair of directly correlated nodes is obtained. The characteristic values ​​of all node pairs constitute the operational correlation pressure drop characteristic relationship data, which clearly defines the pressure drop variation pattern and the influence of correlation strength between different topology nodes. The implementation logic of the operational correlation mass conservation characteristic relationship analysis is as follows: Each topological node is selected as the analysis center. All directly related nodes of that node are filtered out using the correlation matrix. Time-series flow data of the analysis center and all directly related nodes are extracted. Based on the law of mass conservation, the difference between the flow rate of the analysis center node per unit time and the sum of the flows of all directly related nodes is calculated. This flow difference characterizes the degree of flow conservation deviation at each node. The unit time is set to 1 hour. The flow differences of all topological nodes are statistically analyzed to generate operational correlation mass conservation characteristic relationship data. This data comprehensively presents the flow conservation status and deviation distribution of each node during the operation of the water supply network, providing a core hydraulic law basis for subsequent anomaly feature identification.

[0036] Step S23: Based on the operational correlation pressure drop characteristic relationship data and the operational correlation mass conservation characteristic relationship data, perform anomaly characteristic analysis on the operational monitoring topology data of the water supply network to generate operational monitoring topology anomaly characteristic data; In this embodiment of the invention, anomaly feature analysis of the operation monitoring topology is performed by combining operation-related pressure drop characteristic relationship data and operation-related mass conservation characteristic relationship data. The core function is to identify abnormal nodes and abnormal pipe segments in the water supply network operation monitoring topology data. The implementation logic of the anomaly feature analysis is divided into two dimensions: node anomaly identification and pipe segment anomaly identification. For node anomaly identification, each topology node is traversed, and the flow difference value in its corresponding operation-related mass conservation characteristic relationship data is extracted. The flow difference threshold is set to 15% of the node's average flow per unit time. When the flow difference value of a node exceeds this threshold, the node is marked as a flow anomaly node. At the same time, the pressure drop characteristic value in the operation-related pressure drop characteristic relationship data between the node and all directly related nodes is extracted. The pressure drop characteristic value fluctuation threshold is set to 0.08. When the pressure drop characteristic value fluctuation of a node exceeds this threshold, the node is marked as a pressure drop anomaly node. For pipe segment anomaly identification, each topology node and its directly associated nodes are selected, and the corresponding pressure drop characteristic value is extracted. Combined with the design hydraulic transmission attributes of this pipe segment in the water supply network deployment design data, a theoretical pressure drop reference value is calculated. When the deviation between the actual pressure drop characteristic value and the theoretical pressure drop reference value exceeds 20%, the pipe segment is marked as a pressure drop anomaly segment. The identification information, anomaly type, and anomaly value of all anomaly nodes and pipe segments are integrated to generate operational monitoring topology anomaly characteristic data. This data accurately locates anomaly points and pipe segments in the water supply network operational monitoring topology data, providing clear target objects for subsequent data compensation and optimization.

[0037] Step S24: Perform adjacency compensation optimization processing on the water supply network operation monitoring topology data by using the operation monitoring topology anomaly feature data to generate optimized water supply network operation monitoring topology data.

[0038] In this embodiment of the invention, based on the anomaly characteristic data of the operation monitoring topology, adjacency compensation optimization processing is performed on the water supply network operation monitoring topology data to accurately correct and supplement the abnormal data through the effective data of adjacent nodes. The implementation logic of the adjacency compensation optimization processing adopts differentiated compensation strategies for different types of abnormal data. For nodes with abnormal flow, the time-series flow data of all directly related nodes of the node are extracted, and the average flow value after weighting by the correlation strength in the operation monitoring topology correlation matrix is ​​calculated. The weighting average coefficient is taken as the correlation strength value, and this average flow value is used as the corrected flow data of the abnormal node, replacing the original abnormal flow data. For nodes with abnormal pressure drop, the pressure drop characteristic values ​​of the node and all directly related nodes are extracted, and the arithmetic mean of all normal pressure drop characteristic values ​​is calculated. This average value is used as the corrected pressure drop data of the abnormal node, replacing the original abnormal pressure drop data; at the same time, the pressure drop correlation characteristic values ​​of the node and each directly related node are updated synchronously to maintain the consistency of the correlation relationship. For pipe sections with abnormal pressure drop, based on the time-series pressure data of normal nodes at both ends of the pipe section, combined with the pipe section length and hydraulic transmission attributes, the theoretical pressure drop value of the pipe section is calculated using a hydraulic compensation formula. This theoretical pressure drop value is used as the corrected pressure drop data for the abnormal pipe section, replacing the original abnormal pressure drop data. Simultaneously, the pressure drop correlation characteristic values ​​of the nodes at both ends are updated to ensure the logical consistency of the topological correlation. After completing the compensation and correction of all abnormal data, the normal node and normal pipe section data in the water supply network operation monitoring topology data are retained. The corrected abnormal data and the uncorrected normal data are integrated to generate optimized water supply network operation monitoring topology data. This data eliminates abnormal interference in the original topology data, improves the integrity and accuracy of the topology data, and provides a high-quality data foundation for subsequent analysis of the dynamic propagation characteristics of water supply pressure in the network.

[0039] Furthermore, as an embodiment of the present invention, reference is made to... Figure 2 As shown, Figure 1 A detailed flowchart illustrating the implementation steps of step S3 is provided in this embodiment. Step S3 includes: Step S31: Based on the optimized water supply network operation monitoring topology data, perform propagation guidance topology feature analysis of water supply network operation, generate propagation guidance topology feature data, and design water supply network guidance propagation diagram structure data through propagation topology feature data; In this embodiment of the invention, optimized water supply network operation monitoring topology data is used as the core analytical basis to conduct propagation guidance topology feature analysis of water supply network operation, and then design water supply network guidance propagation diagram structure data to achieve accurate extraction and structured presentation of network pressure propagation guidance. Focusing on the hydraulic transmission attributes of pipe segments, water flow transmission direction, and node pressure time-series data in the optimized water supply network operation monitoring topology data, the pressure transmission efficiency and transmission direction characteristics of each pipe segment are extracted. The pressure transmission efficiency is calculated based on the pipe segment length and hydraulic resistance characteristics. The transmission direction follows the main supply and backup supply transmission directions already marked in the optimized topology data, clarifying the pressure propagation priority of each pipe segment. For each topology node, its continuous 24-hour time-series pressure data is extracted, the peak pressure occurrence time of the node is calculated, and combined with the pipe segment transmission direction, the node's attribute as a pressure propagation start point, intermediate node, or end point is determined. The start point node is marked as the pressure output end, the end point node as the pressure receiving end, and the intermediate node as the pressure transfer end. The pressure transmission efficiency and transmission direction of all pipe segments and the pressure propagation attributes of all nodes are integrated to generate propagation guidance topology feature data. Based on this characteristic data, a directional propagation graph structure data for the water supply network was designed. The graph structure uses nodes as core nodes and pipe segments as connecting edges. Core nodes are labeled with pressure propagation attributes, connecting edges are labeled with pressure transmission efficiency and transmission direction, and pressure transmission delay between nodes is also labeled. The transmission delay is set according to the pipe segment length, with 0.1 seconds of transmission delay corresponding to every 100 meters of pipe segment. This fully presents the directional relationship and basic characteristics of pressure propagation in the network, laying the foundation for subsequent graph structure attribute analysis.

[0040] Step S32: Perform graph structure attribute feature analysis based on the water supply network guidance propagation graph structure data to generate water supply network graph structure attribute feature data; In this embodiment of the invention, based on the directional propagation graph structure data of the water supply pipeline network, the graph structure attribute feature analysis is carried out to extract the core attributes related to pressure propagation in the graph structure, providing attribute support for the structural abstraction of the pipeline network's elastic waveguide network. The analysis revolves around four core dimensions of the graph structure: node degree, edge weight, path length, and connectivity. Node degree analysis counts the number of connecting edges for each core node, i.e., the number of directly associated nodes for each node. Nodes with a degree greater than 5 are marked as core hub nodes, and those with a degree less than 2 are marked as terminal nodes. Edge weight analysis is based on the pressure transmission efficiency in the directional propagation graph structure data of the water supply pipeline network, converting the transmission efficiency into edge weights. The higher the transmission efficiency, the larger the edge weight, with a value range set from 0.6 to 1.0. The edge weight directly reflects the pressure transmission capacity of the pipe segment. Path length analysis calculates the shortest propagation path between any two core hub nodes. The path length is calculated by summing the total length of the pipe segment, and combined with the transmission delay, the total pressure propagation delay of each shortest path is obtained. Connectivity analysis checks for isolated nodes or isolated pipe segments in the graph structure to ensure the connectivity of the graph structure. Isolated nodes are marked as abnormally connected nodes, and their attributes are recorded separately. By integrating all node degree, edge weight, path length, connectivity, and anomaly labeling information, structural attribute feature data of the water supply network map is generated. This data accurately quantifies the structural features of the water supply network's guided propagation map and clarifies the role and priority of different nodes and pipe segments in pressure propagation.

[0041] Step S33: Perform structural abstraction processing of the elastic waveguide network of the water supply network using the structural data of the water supply network directional propagation diagram and the structural attribute feature data of the water supply network diagram, and generate the structural data of the elastic waveguide network of the water supply network. In this embodiment of the invention, by combining the structural data of the water supply network directional propagation diagram with the structural attribute feature data of the water supply network diagram, the structural abstraction processing of the network elastic waveguide network is carried out, transforming the complex water supply network directional propagation diagram into an elastic waveguide network model that can accurately analyze the pressure propagation law. The structural abstraction process follows the logic of "preserving core features and simplifying redundant structures." First, core hub nodes and high-weight pipe segments are selected from the water supply network's directional propagation graph structural data. Nodes with no pressure propagation contribution and pipe segments with edge weights less than 0.6 are removed from the terminal nodes, retaining the core propagation paths and key nodes. Then, the selected core nodes are abstracted into nodes of the waveguide network, and high-weight pipe segments are abstracted into waveguide channels. The transmission characteristics of the waveguide channels are determined based on the edge weights and transmission delays in the water supply network graph's structural attribute data. Larger edge weights result in higher waveguide channel transmission efficiency, and transmission delay is positively correlated with waveguide channel length. Simultaneously, combining the path lengths in the graph's structural attributes, the spatial spacing and propagation paths of each node in the waveguide network are determined, clarifying the pressure propagation attenuation law of the waveguide channels. The attenuation coefficient is set to 0.001 per meter based on the hydraulic transmission attributes of the pipe segments. Through the above abstraction process, a pipeline elastic waveguide network structure data is constructed with waveguide nodes and waveguide channels as the core, including transmission efficiency, transmission delay, and attenuation law. This data simplifies the complexity of the pipeline structure while retaining the core characteristics of pressure propagation, providing accurate network model support for subsequent pressure propagation characteristic point analysis.

[0042] Step S34: Analyze the characteristic points of pipeline pressure propagation based on the pipeline elastic waveguide network structure data, and generate pipeline pressure propagation characteristic point data; In this embodiment of the invention, the characteristic points of pressure propagation in the pipeline network are analyzed based on the structural data of the pipeline network elastic waveguide network, and characteristic nodes that play a key role in pressure propagation and can reflect the law of pressure propagation are selected. The analysis process consists of three core steps. First, based on the waveguide node attributes in the pipeline elastic waveguide network structure data, core hub nodes and turning points of the pressure propagation path are selected. The turning point is determined by nodes where the waveguide channel transmission direction changes, as these nodes directly affect the direction and range of pressure propagation. Second, the waveguide channel transmission efficiency and pressure propagation attenuation data corresponding to each candidate node are extracted, and the pressure propagation influence coefficient of each node is calculated. The influence coefficient is calculated as the product of the node degree and the edge weight. Nodes with an influence coefficient greater than 3.0 are marked as core feature points, and nodes with an influence coefficient between 1.5 and 3.0 are marked as secondary feature points. Finally, the selected core and secondary feature points are verified. The time-series pressure data of these nodes in the optimized water supply network operation monitoring topology data are extracted, and the pressure fluctuation amplitude over 12 consecutive hours is calculated. Nodes with fluctuation amplitudes greater than 10% of the benchmark pressure are retained as feature points, while nodes with too small fluctuation amplitudes and no significant propagation contribution are removed. By integrating all retained feature point identifiers, node attributes, influence coefficients, and pressure fluctuation characteristics, pipeline pressure propagation feature point data is generated. This data accurately identifies key nodes in the pipeline network that affect pressure propagation, providing core analysis objects for subsequent pressure disturbance feature analysis.

[0043] Step S35: Based on the optimized water supply network operation monitoring topology data and network pressure propagation characteristic point data, perform network propagation water supply pressure disturbance characteristic analysis to generate network propagation water supply pressure disturbance characteristic data; In this embodiment of the invention, the characteristics of water supply pressure disturbance propagation in the pipeline network are analyzed based on optimized water supply network operation monitoring topology data and pipeline pressure propagation characteristic point data to capture the generation, propagation, and attenuation patterns of pressure disturbances. Time-series pressure data of all core and secondary characteristic points in the pipeline network pressure propagation characteristic point data are extracted, with a continuous 24-hour analysis period. A pressure disturbance judgment threshold of 0.05 MPa is set. When the pressure value of a certain characteristic point changes beyond this threshold within 10 seconds, it is determined that the node has generated a pressure disturbance. The disturbance occurrence time, initial disturbance pressure value, and disturbance intensity are recorded. The disturbance intensity is calculated as the ratio of the pressure change to the reference pressure. Subsequently, combining the pipe segment connection relationships and hydraulic transmission attributes in the optimized water supply network operation monitoring topology data, the propagation process of the disturbance from the generating node to surrounding nodes is tracked. The time for the disturbance to propagate to each adjacent characteristic point and the pressure attenuation during the propagation process are recorded. The attenuation is calculated based on the pipe segment length and the waveguide network attenuation coefficient. Simultaneously, the propagation range of each disturbance is statistically analyzed, i.e., the number of feature points the disturbance can reach. Disturbances with a propagation range exceeding five feature points are marked as large-scale disturbances, while those with fewer than five feature points are marked as local disturbances. By integrating the occurrence time, initial pressure, disturbance intensity, propagation path, propagation time, attenuation, and propagation range of all disturbances, characteristic data of water supply pressure disturbances propagating in the pipeline network are generated. This data comprehensively presents the dynamic propagation pattern of pressure disturbances in the pipeline network, providing core disturbance information for subsequent comprehensive analysis of pressure dynamic propagation characteristics.

[0044] Step S36: Analyze the dynamic propagation characteristics of water supply pressure in the optimized water supply network operation monitoring topology data by using the network elastic waveguide network structure data, network pressure propagation characteristic point data, and network water supply pressure disturbance characteristic data, and generate network water supply pressure dynamic propagation characteristic data.

[0045] In this embodiment of the invention, the structural data of the pipeline network elastic waveguide, the characteristic point data of pipeline pressure propagation, and the characteristic data of pipeline water supply pressure disturbance are integrated to conduct dynamic propagation characteristic analysis of pipeline water supply pressure based on the optimized pipeline network operation monitoring topology data, providing core feature support for subsequent dynamic identification of low-pressure areas. The analysis process first uses the pipeline network elastic waveguide structural data as a foundation to clarify the overall framework and transmission law of pipeline pressure propagation. Combined with the characteristic point data of pipeline pressure propagation, key nodes and core paths of pressure propagation are identified, and the priority of the roles of different characteristic points in pressure propagation is determined. Subsequently, the characteristic data of pipeline water supply pressure disturbance are integrated to analyze the propagation law of different types of disturbances on the core path, calculating the propagation speed and attenuation rate of disturbances in different waveguide channels. The propagation speed is set according to the transmission efficiency of the waveguide channel; the higher the transmission efficiency, the faster the propagation speed. The maximum propagation speed is set to 1.2 m / s. Simultaneously, by combining the full-domain time-series pressure data from the optimized water supply network operation monitoring topology data, the steady-state propagation characteristics of network pressure under undisturbed conditions are analyzed. The differences in pressure propagation between disturbed and steady-state conditions are compared to clarify the degree of influence of disturbances on pressure propagation. Finally, by integrating the steady-state pressure propagation characteristics, disturbance dynamic propagation characteristics, propagation velocity, attenuation rate, and the effects of feature points, dynamic propagation characteristic data of water supply pressure in the network is generated. This data comprehensively and accurately reflects the dynamic propagation law of water supply pressure in the network, including full-scenario characteristics of both steady-state and disturbance propagation.

[0046] Furthermore, step S34 includes the following steps: Step S341: Analyze the pressure propagation influence characteristics of the pipeline distribution based on the pipeline elastic waveguide network structure data, and generate pipeline distribution pressure propagation influence characteristic data; In this embodiment of the invention, the structural data of the pipeline elastic waveguide network is used as the core analytical basis to conduct an analysis of the pressure propagation influence characteristics of the pipeline distribution, and to explore the degree of influence of each node and waveguide channel in the waveguide network on pressure propagation, providing a foundation for subsequent aggregation of neighborhood propagation behavior. The analysis process focuses on the transmission efficiency, transmission delay, and attenuation coefficient of waveguide nodes and waveguide channels in the pipeline elastic waveguide network structural data. Taking each waveguide node as an analysis unit, a node influence range determination logic is constructed. The influence range extends from the node as the center to the surrounding waveguide channels, with the extension distance set at 500 meters, covering all connected waveguide nodes and waveguide channels within this range. For each analysis unit, the corresponding waveguide channel transmission efficiency and attenuation coefficient are extracted, and the pressure propagation influence intensity of the node is calculated. The influence intensity is calculated as the ratio of transmission efficiency to attenuation coefficient. Nodes with a ratio greater than 1.2 are marked as high-influence nodes, nodes with a ratio between 0.8 and 1.2 are marked as medium-influence nodes, and nodes with a ratio less than 0.8 are marked as low-influence nodes. Simultaneously, the pressure transmission loss of each waveguide channel is analyzed. The transmission loss is calculated based on the channel length and attenuation coefficient, with a fixed loss value corresponding to every 100 meters of channel. Combined with the transmission efficiency, the influence weight of each channel on pressure propagation is determined, with the weight value set between 0.5 and 1.0. The higher the transmission efficiency, the greater the weight. The influence intensity, influence range, and influence level of all waveguide nodes, as well as the transmission loss and influence weight of all waveguide channels, are integrated to generate pipeline network distribution pressure propagation influence characteristic data. This data accurately quantifies the differences in the influence of different areas of the pipeline network on pressure propagation, clarifies the distribution of high-influence and low-influence areas, and locks in the core range for neighborhood aggregation processing.

[0047] Step S342: Based on the characteristic data of pressure propagation influence in the pipeline distribution area, perform relevant propagation behavior aggregation processing in the pipeline distribution neighborhood to generate pipeline distribution neighborhood relevant propagation behavior aggregation data; In this embodiment of the invention, based on the pressure propagation influence characteristic data of the pipeline network distribution, relevant propagation behavior aggregation processing is carried out in the pipeline network distribution neighborhood. Nodes and channels with similar pressure propagation influence characteristics are classified and aggregated, simplifying the complexity of subsequent feature point selection. The aggregation processing takes high-influence nodes as the core and divides the neighborhood range. Each neighborhood range is centered on the high-influence node and includes medium-influence nodes, low-influence nodes, and all connected waveguide channels within its extended range. The neighborhood radius is set to 300 meters to ensure that the nodes and channels in each neighborhood have similar pressure propagation influence characteristics. For each neighborhood, the influence intensity of all nodes, the transmission loss of all channels, and the influence weight are extracted. The average influence intensity and average transmission loss in the neighborhood are calculated. The average influence intensity is calculated using an arithmetic mean, and the average transmission loss is calculated using a weighted average based on the channel length, with the weighting coefficient taken as the channel influence weight. Simultaneously, the pressure propagation coordination among nodes within the neighborhood is analyzed. Coordination is determined based on the fluctuation range of the influence intensity of each node within the neighborhood. Neighborhoods with a fluctuation range less than 0.2 are marked as highly coordinated neighborhoods, while those with a fluctuation range greater than or equal to 0.2 are marked as weakly coordinated neighborhoods. For highly coordinated neighborhoods, all nodes and channels within them are integrated into a single aggregation unit. For weakly coordinated neighborhoods, they are further subdivided according to their influence level, with high-influence nodes forming a separate aggregation unit, and medium- and low-influence nodes integrated into another aggregation unit. Each aggregation unit is labeled with its average influence intensity, average transmission loss, coordination level, and the identifiers of the nodes and channels it contains. By integrating all aggregation unit information, aggregated data on the propagation behavior related to the pipeline network distribution neighborhood is generated. This data enables the classification and integration of the influence characteristics of pipeline pressure propagation, providing accurate aggregation unit support for subsequent feature point selection.

[0048] Step S343: Based on the aggregated data of pipeline distribution neighborhood related propagation behavior, filter and process pipeline pressure propagation feature points to generate pipeline pressure propagation feature point data.

[0049] In this embodiment of the invention, based on aggregated data of pipeline network distribution neighborhood related propagation behavior, a pipeline pressure propagation feature point screening process is carried out. Nodes that play a key role in pressure propagation and can accurately reflect the pressure propagation law are selected from the aggregated units, providing core analysis objects for subsequent pressure disturbance feature analysis and low-pressure area identification. Priority is given to screening high-impact and high-coordination nodes, and this is carried out in three steps. First, high-impact node aggregated units are screened from all aggregated units, and core nodes are extracted from these units. Core nodes are determined to be the nodes with the highest influence intensity in the aggregated unit, and one core node is selected as a candidate feature point for each high-impact aggregated unit. Second, for medium and low-impact aggregated units, nodes with an average influence intensity greater than 0.9 are extracted. Although the overall influence level of these nodes is not high, they still play an important role in pressure propagation within their local neighborhood and are used as secondary candidate feature points. Finally, all candidate feature points were validated. Time-series pressure data of these nodes in the optimized water supply network operation monitoring topology data were extracted. Using a continuous 12-hour analysis period, the pressure fluctuation amplitude of each node was calculated. Nodes with fluctuation amplitudes greater than 10% of the baseline pressure were retained as final feature points, while nodes with excessively small fluctuation amplitudes or no significant contribution to pressure propagation were removed. Simultaneously, each retained feature point was labeled with its associated aggregation unit, influence intensity, coordination level, and corresponding waveguide channel information, clarifying the role of each feature point in pressure propagation. The identifiers, attributes, and association information of all final feature points were integrated to generate network pressure propagation feature point data. This data accurately identifies key nodes affecting pressure propagation in the network, solving the problem that the screening method could not accurately locate core feature points.

[0050] Furthermore, step S35 includes the following steps: Step S351: Based on the optimized water supply network operation monitoring topology data, analyze the water supply pressure change trend of the network pressure propagation characteristic points and generate water supply pressure change trend data of the network propagation characteristic points; In this embodiment of the invention, the pressure change trend of the characteristic points of the water supply network is analyzed based on the optimized water supply network operation monitoring topology data. Through trend fitting and stage division of time-series pressure data, the pressure change pattern of each characteristic point is accurately depicted. For each characteristic point, its time-series pressure data over a continuous 48 hours is extracted, with the time granularity consistent with the sensor monitoring frequency, at one data point every 5 seconds. Using time as the horizontal axis and pressure value as the vertical axis, linear segmented fitting is performed on the time-series pressure data. The fitting interval is divided into three stages according to the daily water consumption peak, off-peak, and trough: the morning peak stage is set from 6:00 to 10:00, the off-peak stage from 10:00 to 18:00, and the trough stage from 18:00 to 6:00 the next day. For each stage, the pressure change slope is calculated: a positive slope indicates an upward pressure trend, a negative slope indicates a downward pressure trend, and a zero slope indicates stable pressure. Simultaneously, the mean pressure and pressure range within each stage are calculated. The mean pressure reflects the baseline pressure level of that stage, while the pressure range reflects the pressure fluctuation range within that stage. The three-stage fitting slope, stage mean pressure, stage pressure range, and overall 48-hour pressure change trend of each feature point are integrated. The overall trend is determined by the weighted sum of the three-stage slopes, with weighting coefficients set to 0.4 for morning peak, 0.3 for off-peak, and 0.3 for trough. The resulting pipeline propagation feature point water supply pressure change trend data fully records the pressure change characteristics of each feature point in different water usage stages, providing a clear trend benchmark for subsequent short-term fluctuation analysis.

[0051] Step S352: Perform short-term fluctuation analysis on the water supply pressure change trend data of the propagation characteristic points of the pipeline network to generate short-term fluctuation data of the pressure trend of the propagation characteristic points; In this embodiment of the invention, based on the water supply pressure change trend data of characteristic points in the pipeline network, short-term fluctuation analysis of the change trend is carried out to identify the short-term deviation of each characteristic point under a given pressure change trend, and to quantify the degree and frequency of deviation. For the three water use stages of each characteristic point, the fitted straight line of each stage is used as the baseline trend line, and all time-series pressure data points within that stage are extracted. The pressure deviation value between each data point and the baseline trend line is calculated. The deviation value is the difference between the actual pressure of the data point and the theoretical pressure at the corresponding time point of the trend line. The time window for short-term fluctuation is set to 30 seconds, i.e., six consecutive 5-second data points. A sliding window is used to traverse the deviation value. The mean deviation and standard deviation of the deviation are calculated within each window. The mean deviation reflects the overall deviation direction within the window, and the standard deviation reflects the degree of deviation dispersion within the window. When the absolute value of the mean deviation of a certain window is greater than 8% of the average pressure of the stage, and the standard deviation of the deviation is greater than 5% of the pressure range of the stage, it is determined that a short-term fluctuation has occurred within that window. The system statistically analyzes the number of short-term fluctuations, the duration of each fluctuation window, the mean of the maximum deviation, and the standard deviation of the maximum deviation for each feature point at each stage. It also records the start and end times of each fluctuation. By integrating the stage fluctuation statistics, fluctuation time information, and deviation characteristics of all feature points, it generates short-term fluctuation data on the pressure trend of propagating feature points. This data accurately captures abnormal short-term pressure fluctuations for each feature point under a stable trend, eliminating normal pressure fluctuations caused by trend changes and focusing on short-term anomalies that may be caused by pressure disturbances. This identifies the core analysis objects for subsequent disturbance characteristic analysis.

[0052] Step S353: Analyze the characteristics of water supply pressure disturbance propagation in the pipeline network based on the short-term fluctuation data of pressure trend at the propagation characteristic points, and generate characteristic data of water supply pressure disturbance propagation in the pipeline network.

[0053] In this embodiment of the invention, based on short-term fluctuation data of pressure trends at propagation feature points, the characteristics of water supply pressure disturbances propagating in the pipeline network are analyzed to distinguish the types of short-term fluctuations, determine the intensity of disturbances, and trace the associated feature points. For each feature point, short-term fluctuations are classified into types based on the direction and duration of the fluctuation deviation: decreasing disturbances and increasing disturbances. Decreasing disturbances are defined as fluctuations with a negative mean deviation and a duration window greater than 3; increasing disturbances are defined as fluctuations with a positive mean deviation and a duration window greater than 3. Fluctuations with a duration window less than or equal to 3 are considered random fluctuations and are discarded. For fluctuations identified as disturbances, the disturbance intensity is calculated. The intensity of decreasing disturbances is the ratio of the absolute value of the maximum mean deviation during the fluctuation period to the average pressure during that period; the intensity of increasing disturbances is the ratio of the maximum mean deviation during the fluctuation period to the average pressure during that period. Disturbances with an intensity greater than 0.12 are marked as strong disturbances, those between 0.08 and 0.12 are marked as medium disturbances, and those less than 0.08 are marked as weak disturbances. Subsequently, by combining the pipe segment connection relationships in the optimized water supply network operation monitoring topology data, the propagation-related characteristic points of disturbances are traced. Centered on the disturbance initiation characteristic point, adjacent characteristic points exhibiting the same type of disturbance within the next 5 minutes are investigated according to the pipe segment transmission direction. The 5-minute time threshold is set based on the network pressure propagation speed and pipe segment length. If the disturbance initiation time difference between adjacent characteristic points is less than 5 minutes and the disturbance type is consistent, they are determined to be propagation nodes of the same disturbance. By integrating all disturbance characteristic point identifiers, disturbance types, disturbance intensity, start and end times, duration, and propagation-related characteristic point lists, network-propagated water supply pressure disturbance characteristic data are generated. This data accurately defines the core attributes and propagation paths of pressure disturbances in the network, thoroughly distinguishing between random fluctuations and real pressure disturbances. It provides core disturbance quantification basis for the comprehensive analysis of pressure dynamic propagation characteristics in step S36, and simultaneously identifies and locks down the source of low-pressure hazards caused by pressure disturbances in subsequent low-pressure areas.

[0054] Furthermore, step S4 includes the following steps: Step S41: Analyze the characteristics of the water supply network operation status based on the optimized water supply network operation monitoring topology data, and generate water supply network operation status characteristic data. In this embodiment of the invention, optimized water supply network operation monitoring topology data serves as the core data support. The analysis of the network's water supply operation status characteristics is conducted, comprehensively extracting hydraulic operation status parameters across the entire network and quantifying operational stability, laying the foundation for subsequent pressure propagation response area analysis. The analysis process focuses on the time-series pressure data, flow data, and hydraulic transmission attributes of all nodes in the optimized water supply network operation monitoring topology data. A continuous 72-hour analysis period is used, with the time granularity consistent with the sensor monitoring frequency, resulting in one data point every 5 seconds. For each node, the average pressure, extreme pressure, average flow, and peak flow are calculated over 72 hours. Simultaneously, the pressure fluctuation coefficient and flow fluctuation coefficient are calculated. The fluctuation coefficient is calculated as the ratio of the difference between the extreme value and the average value to the average value. Nodes with a fluctuation coefficient greater than 0.1 are marked as unstable nodes, while nodes with a fluctuation coefficient less than or equal to 0.1 are marked as stable nodes. For each pipe segment, the pressure gradient is calculated by combining the pressure data from both ends and the segment length. The pressure gradient is the ratio of the pressure difference between the two ends to the segment length. Segments with a pressure gradient greater than 0.0005 are marked as high-resistance segments, and those with a pressure gradient less than or equal to 0.0005 are marked as normal-resistance segments. Simultaneously, the overall network operating load rate is calculated. The operating load rate is the ratio of the actual average flow rate to the design flow rate. Periods with a load rate greater than 0.8 are marked as high-load periods, periods with a load rate between 0.5 and 0.8 are marked as normal-load periods, and periods with a load rate less than 0.5 are marked as low-load periods. By integrating the operational stability, pressure, and flow parameters of all nodes, the pressure gradient and resistance level of all pipe segments, and the overall network load rate and time period division, characteristic data of the network's water supply operation status is generated. This data comprehensively presents the differences in the operating status of the entire network, clearly defining the distribution of stable and unstable areas, and high-resistance and normal-resistance segments, providing a clear state benchmark for subsequent response area analysis.

[0055] Step S42: Analyze the dynamic propagation characteristic data of water supply pressure in the pipeline network by using the pipeline network operation status characteristic data, and generate pipeline network water supply pressure propagation response area data; In this embodiment of the invention, based on the characteristic data of the water supply network operation status, the response area analysis of the water supply network pressure dynamic propagation characteristic data is carried out, the response range corresponding to different pressure propagation characteristics is delineated, and the influence area of ​​pressure propagation is clarified. The steady-state propagation law, disturbance propagation law, and propagation speed of pressure are extracted from the water supply network pressure dynamic propagation characteristic data. Combined with the node operation stability, pipe section resistance level, and load period division in the water supply network operation status characteristic data, a response area determination logic is constructed. Starting from the pressure propagation characteristic point, the effective response range of pressure propagation is delineated according to the pressure propagation speed. The effective response range is set as the area where the propagation time does not exceed 10 minutes. The 10-minute time threshold is determined based on the maximum pipe section length and the propagation speed. For steady-state pressure propagation, based on node operational stability, areas with concentrated stable nodes and pipe sections exhibiting normal resistance are designated as steady-state response zones. Pressure propagation in these zones is stable with no significant fluctuations. For disturbed pressure propagation, based on disturbance intensity and propagation path, areas covered by the disturbance and where node operation is unstable are designated as disturbed response zones. The radius of the response zone corresponding to strong disturbances is set at 800 meters, medium disturbances at 500 meters, and weak disturbances at 300 meters. Simultaneously, the response zones are time-specific, categorized according to network load periods, clarifying the range variation under different load periods. The response zone range expands by 20% during high load periods and shrinks by 20% during low load periods. Each response zone is labeled with its type, the identified nodes and pipe sections it covers, its response range, corresponding pressure propagation characteristics, and load period attributes. Integrating all response zone information generates network water supply pressure propagation response zone data. This data accurately defines the influence range of different pressure propagation characteristics, pinpointing the core area for subsequent attenuation gradient attribute analysis.

[0056] Step S43: Perform propagation attenuation gradient attribute analysis on the propagation response area data of water supply pressure in the pipeline network to generate pipeline water supply pressure propagation response attribute area data; In this embodiment of the invention, propagation attenuation gradient attribute analysis is performed on the pressure propagation response area data of the pipeline water supply network to quantify the attenuation law of pressure propagation in each response area and clarify the distribution characteristics of the attenuation gradient. For each response area, time-series pressure data of all nodes and pressure gradient data of pipe segments within that area are extracted. Taking the pressure propagation starting point of the response area as the benchmark, multiple attenuation analysis segments are divided according to the propagation path. The length of each analysis segment is set to 200 meters to ensure accurate capture of the pressure attenuation change law. For each analysis segment, the pressure attenuation amount and attenuation gradient within that segment are calculated. The attenuation amount is the pressure difference between the start and end points of the analysis segment, and the attenuation gradient is the ratio of the attenuation amount to the length of the analysis segment. Simultaneously, the average attenuation gradient within that segment is calculated using an arithmetic mean. Combining the pipe segment resistance level in the pipeline water supply operation status characteristic data, the attenuation gradient is classified. The attenuation gradient corresponding to high-resistance pipe segments is greater than 0.0006, while the attenuation gradient corresponding to normal-resistance pipe segments is between 0.0003 and 0.0006. Simultaneously, the spatial distribution pattern of the attenuation gradient was analyzed. Taking the center of the response area as the origin, concentric circles were drawn outwards, each with a width of 100 meters. The average attenuation gradient of each circle was calculated, clarifying the trend of attenuation gradient variation with distance. Regions where the attenuation gradient increases with distance were marked as gradient-increasing regions, while regions where the attenuation gradient remains stable were marked as gradient-stable regions. Each response area was labeled with its attenuation gradient distribution, the attenuation amount and gradient of each analysis segment, the attenuation level corresponding to the pipe segment resistance, and the spatial trend of gradient variation. The attenuation attribute information of all response areas was integrated to generate regional data on the pressure propagation response attributes of the pipeline network. This data accurately quantifies the attenuation pattern of pressure propagation, providing core attenuation parameter support for subsequent pressure response characteristic analysis.

[0057] Step S44: Based on the regional data of water supply pressure propagation response attributes and the optimized water supply network operation monitoring topology data, perform water supply network pressure response characteristic analysis to generate water supply network pressure response characteristic data; In this embodiment of the invention, by combining regional data of water supply pressure propagation response attributes with optimized water supply network operation monitoring topology data, pressure response characteristics of the water supply network are analyzed. The pressure propagation attenuation law is integrated with the network topology and operating status to extract core response characteristics that reflect potential low-pressure issues. The attenuation gradient, attenuation amount, and gradient spatial variation trend are extracted from the regional data of water supply pressure propagation response attributes. Combined with node locations, pipe segment connections, and hydraulic transmission attributes from the optimized water supply network operation monitoring topology data, a pressure response characteristic analysis framework is constructed. For each response region, the pressure response characteristics of nodes within the region are analyzed. The difference between the node pressure and the regional average pressure is calculated. Nodes with a negative difference and an absolute value greater than 15% of the regional average pressure are marked as low-pressure nodes. Based on the attenuation gradient, the distribution pattern of low-pressure nodes is analyzed. Low-pressure nodes in regions with increasing gradients are marked as attenuating low-pressure nodes, and low-pressure nodes in regions with stable gradients are marked as stable low-pressure nodes. Simultaneously, by combining the node operational stability and pipe section resistance levels in the pipeline water supply operation status characteristic data, the causes of low-pressure nodes are analyzed. Low-pressure nodes around high-resistance pipe sections are identified as resistance-induced, while unstable nodes are identified as fluctuation-induced. Furthermore, the pressure response uniformity of each response area is calculated. Uniformity is the ratio of the standard deviation of pressure at all nodes within the area to the average pressure of the area. Areas with a uniformity greater than 0.15 are marked as areas of uneven pressure distribution, while areas with a uniformity less than or equal to 0.15 are marked as areas of uniform pressure distribution. By integrating the pressure response characteristics, low-pressure node information, causes of low pressure, and pressure distribution uniformity of all response areas, pressure response characteristic data of the water supply network is generated. This data accurately captures the pressure response characteristics related to low pressure in the pipeline network, providing a basis for dynamic identification and targeting of core low-pressure areas.

[0058] Step S45: Based on the pressure response characteristic data of the water supply network, perform dynamic identification processing of the low-pressure area of ​​the water supply network to generate dynamic identification data of the low-pressure area of ​​the water supply network.

[0059] In this embodiment of the invention, based on the pressure response characteristic data of the water supply network, dynamic identification and processing of low-pressure areas in the water supply network are carried out. The core function is to accurately locate the position, range, and type of low-pressure areas, providing a precise basis for handling potential low-pressure hazards in the water supply network. Taking the low-pressure nodes in the water supply network pressure response characteristic data as the core, and combining the pipe segment connection relationships in the optimized water supply network operation monitoring topology data, the low-pressure area range is delineated. Adjacent low-pressure nodes and the pipe segments connecting these nodes are integrated into a single low-pressure area. The boundary of the low-pressure area is set at the location of the nearest non-low-pressure node, ensuring that the low-pressure area accurately covers all areas with abnormal pressure. Secondly, each low-pressure area is classified. Combining the causes and attenuation patterns of low pressure in the pressure response characteristic data, low-pressure areas with a concentration of attenuation-type low-pressure nodes are marked as attenuation-type low-pressure areas, low-pressure areas with a concentration of fluctuation-type nodes are marked as fluctuation-type low-pressure areas, and low-pressure areas around high-resistance pipe segments are marked as resistance-type low-pressure areas. Finally, the degree of anomaly in each low-pressure area is quantified. The average pressure drop value of all nodes within the low-pressure area is calculated. Areas with an average pressure drop value greater than 20% of the regional average pressure are marked as severe low-pressure areas, those with an average pressure drop value between 10% and 20% are marked as moderate low-pressure areas, and those with an average pressure drop value less than 10% are marked as mild low-pressure areas. Simultaneously, the identification, type, degree of anomaly, and cause of formation of each low-pressure area are recorded. Combined with time-series data, the occurrence time, duration, and trend of low-pressure areas are marked, enabling dynamic tracking of low-pressure areas. By integrating the identification, range, type, degree of anomaly, cause, and time-series change information of all low-pressure areas, dynamic identification data of low-pressure areas in the water supply network is generated. This accurately presents the dynamic distribution characteristics of low-pressure areas in the water supply network, providing comprehensive and reliable technical support for refined operation and maintenance of the water supply network and timely handling of low-pressure hazards.

[0060] Furthermore, step S45 includes the following steps: Step S451: Based on the pressure response characteristic data of the water supply network, perform instability characteristic identification processing of the pressure response of the water supply network to generate instability characteristic data of the pressure response of the water supply network. In this embodiment of the invention, Using water supply network pressure response characteristic data as the core analytical basis, this study identifies and processes instability characteristics of water supply network pressure response. The core objective is to accurately capture instability phenomena occurring during the pressure response process and quantify instability characteristic parameters, laying the foundation for subsequent dynamic instability characteristic analysis. The study focuses on low-pressure nodes, pressure distribution uniformity, pressure response characteristics, and time-series pressure data within the water supply network pressure response characteristic data. An analysis period of 24 consecutive hours is used, with the time granularity consistent with the sensor monitoring frequency (one data point every 5 seconds). For each low-pressure node, its time-series pressure data is extracted, and the pressure change rate within one hour is calculated. The pressure change rate is the ratio of the pressure difference between two adjacent data points to the time interval. An instability judgment threshold is set; when the absolute value of the pressure change rate is greater than 0.001, the node is judged to have experienced pressure instability. Simultaneously, combined with the pressure distribution uniformity in the pressure response characteristic data, the spatial clustering of unstable nodes is analyzed. The number of unstable nodes in each response area is counted. When the proportion of unstable nodes to the total number of nodes in the area is greater than 30%, regional pressure instability is judged to have occurred in that area. In addition, the instability onset time, duration, maximum pressure change rate, and pressure extreme values ​​during instability are recorded for each instability node, and the type of instability node (attenuation type, fluctuation type, resistance type) is labeled. The extent of regional instability areas, the density of instability node clusters, and the duration of instability are also recorded. By integrating the instability parameters and types of all instability nodes, as well as relevant information on regional instability areas, pressure response instability characteristic data for the water supply network is generated. This data accurately pinpoints the instability points and regions during the pressure response process, clarifies the core characteristics of instability, and provides accurate basic data for subsequent dynamic instability analysis.

[0061] Step S452: Based on the regional data of water supply pressure propagation response attributes and the water supply network pressure response instability characteristic data, perform dynamic instability characteristic analysis of water supply pressure propagation to generate dynamic instability characteristic data of water supply pressure propagation. In this embodiment of the invention, dynamic instability characteristic analysis of water supply pressure propagation is conducted by combining regional data of water supply network pressure propagation response attributes with data of water supply network pressure response instability characteristics. The core focus is on tracing the propagation path of instability phenomena, quantifying the propagation law of instability, and clarifying the impact range and development trend of dynamic instability. The attenuation gradient, attenuation amount, gradient spatial change trend, and response area range are extracted from the regional data of water supply network pressure propagation response attributes. Combined with the instability nodes, instability areas, and instability timing information from the data of water supply network pressure response instability characteristics, a dynamic instability propagation analysis logic is constructed. Taking the first node exhibiting instability as the instability source, the propagation process of instability to surrounding nodes is tracked by combining the pressure propagation path and attenuation law from the regional data of water supply network pressure propagation response attributes. The time it takes for instability to propagate to each adjacent node and the pressure attenuation during the propagation process are recorded. Nodes with a propagation time difference of less than 30 seconds and consistent instability types are identified as propagation nodes of the same dynamic instability. Simultaneously, the propagation velocity of dynamic instability is calculated, which is the ratio of the propagation distance to the propagation time. Combined with the attenuation gradient, the intensity change during the instability propagation process is analyzed. Instability propagation where the absolute value of the pressure change rate decreases is labeled as attenuating dynamic instability; where the absolute value of the pressure change rate remains stable is labeled as stable dynamic instability; and where the absolute value of the pressure change rate increases is labeled as enhancing dynamic instability. Furthermore, based on the gradient distribution characteristics of the response area, the propagation range of dynamic instability is defined: 500 meters in areas with increasing gradients and 800 meters in areas with stable gradients. The propagation duration, number of propagation nodes, and maximum instability intensity during the propagation process are recorded. By integrating all propagation sources, paths, velocities, ranges, intensity trends, and time-series information of dynamic instability, dynamic instability characteristic data of water supply pressure propagation is generated. This data comprehensively presents the propagation patterns and development trends of dynamic instability, providing core evidence for subsequent dynamic identification in low-pressure areas.

[0062] Step S453: Dynamically identify low-pressure areas of the water supply network by using the pressure response instability characteristic data and the dynamic instability characteristic data of water supply pressure propagation, and generate dynamic identification data of low-pressure areas of the water supply network.

[0063] In this embodiment of the invention, relying on the pressure response instability characteristic data and the dynamic instability characteristic data of water supply network propagation, dynamic identification and processing of low-pressure areas in the water supply network are carried out. The core of this method integrates instability characteristics and instability propagation patterns to accurately locate the position, range, type, and dynamic changes of low-pressure areas, providing precise and comprehensive technical support for handling low-pressure hazards in the water supply network. Using the instability nodes and regions in the pressure response instability characteristic data of the water supply network as the core, and combining the instability propagation path and range in the dynamic instability characteristic data of water supply pressure propagation, the initial range of the low-pressure area is delineated. The instability nodes, all nodes on the instability propagation path, and the pipe segments connecting these nodes are integrated into a single low-pressure area. The boundary of the low-pressure area is set as the location of the outermost node in the dynamic instability propagation range, ensuring that the low-pressure area accurately covers all pressure anomaly areas related to instability. Secondly, each low-pressure area is classified. Combining the type of dynamic instability and the type of instability node, low-pressure areas corresponding to attenuating dynamic instability are marked as attenuating low-pressure areas, those corresponding to stable dynamic instability are marked as stable low-pressure areas, and those corresponding to enhanced dynamic instability are marked as enhanced low-pressure areas. Simultaneously, the causes of the low-pressure areas (resistance-induced, fluctuation-induced) are supplemented by indicating the formation reasons of the instability nodes. Finally, the degree and trend of dynamic anomalies in each low-pressure area are quantified. The average pressure change rate and average pressure underestimation value of all instability nodes within the low-pressure area are calculated. Areas with an average pressure underestimation value greater than 20% of the regional average pressure and an absolute value of the average pressure change rate greater than 0.0015 are marked as severe dynamic low-pressure areas; areas with an average pressure underestimation value between 10% and 20% and an absolute value of the average pressure change rate between 0.001 and 0.0015 are marked as moderate dynamic low-pressure areas; and areas with an average pressure underestimation value less than 10% and an absolute value of the average pressure change rate less than 0.001 are marked as mild dynamic low-pressure areas. Simultaneously, by combining time-series data, the occurrence time, duration, instability propagation progress, and pressure change trend of each low-pressure area are marked, enabling dynamic tracking of low-pressure areas and clarifying whether the low-pressure area is expanding, shrinking, or stable. All low-pressure area identification, range, type, cause, degree of anomaly, and time-series dynamic change information are integrated to generate dynamic identification data for low-pressure areas in the water supply network.

[0064] This specification provides a dynamic identification system for low-pressure areas in a water supply network, used to execute the dynamic identification method for low-pressure areas in a water supply network as described above. The dynamic identification system for low-pressure areas in a water supply network includes: The water supply network operation monitoring module is used to process discrete point operation monitoring data of the water supply network using multi-source monitoring sensors, and generate discrete monitoring data of the water supply network operation; and to perform operation monitoring topology analysis on the discrete monitoring data of the water supply network operation, and generate operation monitoring topology data of the water supply network. The operation monitoring and optimization module is used to perform adjacency compensation optimization on the water supply network operation monitoring topology data to generate optimized water supply network operation monitoring topology data. The pipeline water supply pressure dynamic propagation characteristic analysis module is used to perform dynamic propagation characteristic analysis of pipeline water supply pressure based on optimized pipeline network operation monitoring topology data, and generate pipeline water supply pressure dynamic propagation characteristic data. The low-pressure area dynamic identification module of the water supply network is used to perform dynamic identification processing of low-pressure areas of the water supply network based on optimized water supply network operation monitoring topology data and dynamic propagation characteristic data of water supply pressure in the network, and generate dynamic identification data of low-pressure areas of the water supply network.

[0065] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0066] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A method for dynamic identification of low-pressure areas in a water supply network, characterized in that, Includes the following steps: Step S1: Use multi-source monitoring sensors to perform discrete point operation monitoring and processing of the water supply network to generate discrete monitoring data of the water supply network operation; perform topology analysis of the water supply network operation monitoring data to generate topology data of the water supply network operation monitoring. Step S1 includes the following steps: Step S11: Obtain water supply network deployment design data; Step S12: Extract the characteristic point data of the water supply network deployment through the water supply network deployment design data, and perform monitoring adaptation analysis based on the characteristic point data of the water supply network deployment to generate monitoring adaptation data of the water supply network points; Step S13: Based on the water supply network point monitoring adaptation data, design the water supply network monitoring configuration analysis, obtain the water supply network monitoring configuration data, and use the multi-source monitoring sensors configured with the water supply network monitoring configuration data to perform discrete point operation monitoring processing of the water supply network, generating discrete monitoring data of water supply network operation. Step S14: Perform time-series unified processing on the discrete monitoring data of water supply network operation to generate time-series discrete monitoring data of water supply network operation; Step S15: Based on the water supply network deployment design data and the time-series discrete monitoring data of water supply network operation, perform spatial continuous reconstruction processing of water supply network operation monitoring to generate water supply network operation monitoring topology data; Step S15 includes: Step S151: Analyze the operating characteristics of the monitoring nodes based on the discrete monitoring data of the time-series water supply network operation, and generate operating characteristic data of the water supply network monitoring nodes; Step S152: Perform a topology analysis of the water supply network operation space based on the water supply network deployment design data to generate water supply network operation space topology data; Step S153: Map the time-series discrete monitoring data of water supply network operation corresponding to the operational characteristic data of the water supply network monitoring nodes to the corresponding topological nodes in the spatial topology data of the water supply network operation; for topological nodes without deployed monitoring sensors, calculate the estimated time-series hydraulic parameters of the node based on the operational characteristic data of adjacent monitoring nodes combined with the pipe length and hydraulic transmission attributes using a hydraulic interpolation algorithm; based on the time-series data of adjacent nodes associated with the transmission direction of the pipe segment, clarify the pressure gradient and flow transmission relationship at both ends of the pipe segment, complete the spatial continuous reconstruction processing of water supply network operation monitoring, and generate water supply network operation monitoring topology data; Step S2: Perform adjacency compensation optimization processing on the water supply network operation monitoring topology data to generate optimized water supply network operation monitoring topology data; Step S3: Based on the optimized water supply network operation monitoring topology data, perform dynamic propagation characteristic analysis of water supply pressure in the network to generate dynamic propagation characteristic data of water supply pressure in the network; Step S3 includes the following steps: Step S31: Based on the optimized water supply network operation monitoring topology data, perform propagation guidance topology feature analysis of water supply network operation, integrate the pressure transmission efficiency, transmission direction and pressure propagation attributes of all pipe sections and all nodes, generate propagation guidance topology feature data, and design water supply network guidance propagation diagram structure data through propagation topology feature data; Step S32: Perform graph structure attribute feature analysis based on the water supply network guidance propagation graph structure data to generate water supply network graph structure attribute feature data; Step S33: Perform structural abstraction of the water supply network elastic waveguide network using the water supply network guide propagation diagram structure data and the water supply network diagram structure attribute feature data. Select the core hub nodes and high-weight pipe segments in the water supply network guide propagation diagram structure data. Abstract the selected core nodes into nodes of the waveguide network and the high-weight pipe segments into waveguide channels of the waveguide network to generate the water supply network elastic waveguide network structure data. Step S34: Analyze the characteristic points of pipeline pressure propagation based on the pipeline elastic waveguide network structure data, and generate pipeline pressure propagation characteristic point data; Step S34 includes: Step S341: Based on the pipeline elastic waveguide network structure data, calculate the pressure propagation influence intensity of each waveguide node as the analysis unit and classify the influence level. At the same time, calculate the pressure transmission loss and influence weight of each waveguide channel to generate pipeline distribution pressure propagation influence characteristic data. Step S342: Based on the pressure propagation influence characteristics data of the pipeline network distribution, divide the neighborhood range with high-influence nodes as the center, calculate the average influence intensity and average transmission loss within the neighborhood, and integrate the nodes and waveguide channels into aggregation units by combining the neighborhood propagation synergy to generate pipeline network distribution neighborhood related propagation behavior aggregation data; Step S343: Based on the aggregated data of the propagation behavior of the pipeline distribution neighborhood, core nodes are selected from each aggregated unit as candidate feature points. After verification by combining the node time-series pressure fluctuation amplitude, the final feature points are determined, and pipeline pressure propagation feature point data is generated. Step S35: Based on the optimized water supply network operation monitoring topology data and network pressure propagation characteristic point data, perform network propagation water supply pressure disturbance characteristic analysis to generate network propagation water supply pressure disturbance characteristic data; Step S35 includes: Step S351: Based on the optimized water supply network operation monitoring topology data, analyze the water supply pressure change trend of the network pressure propagation characteristic points and generate water supply pressure change trend data of the network propagation characteristic points; Step S352: Perform short-term fluctuation analysis on the water supply pressure change trend data of the propagation characteristic points of the pipeline network to generate short-term fluctuation data of the pressure trend of the propagation characteristic points; Step S353: Analyze the characteristics of water supply pressure disturbance propagation in the pipeline network based on the short-term fluctuation data of pressure trend at the propagation characteristic points, and generate characteristic data of water supply pressure disturbance propagation in the pipeline network. Step S36: Analyze the dynamic propagation characteristics of water supply pressure in the optimized water supply network operation monitoring topology data by using the network elastic waveguide network structure data, network pressure propagation characteristic point data, and network water supply pressure disturbance characteristic data to generate dynamic propagation characteristic data of network water supply pressure. Step S4: Based on the optimized water supply network operation monitoring topology data and the dynamic propagation characteristic data of water supply pressure in the network, perform dynamic identification processing of low-pressure areas in the water supply network to generate dynamic identification data of low-pressure areas in the water supply network.

2. The method for dynamic identification of low-pressure areas in water supply networks according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Design the topology association relationship for the water supply network operation monitoring topology data. Use the topology node number as the matrix row and column index, and define the matrix element as the hydraulic association strength between two corresponding topology nodes. For topology nodes with direct pipe segment connections, determine the association strength value based on the hydraulic transmission properties of the pipe segment. For topology nodes with indirect hydraulic association, determine the association strength value based on the number and length of the indirect pipe segments. Establish the operation monitoring topology association matrix. Step S22: Based on the operational monitoring topology correlation matrix, filter the topology node pairs with direct hydraulic correlation, extract the corresponding time-series pressure data, calculate the pressure drop characteristic value between nodes, and obtain the operational correlation pressure drop characteristic relationship data; select each topology node as the analysis center, extract the time-series flow data of the analysis center and all its directly related nodes, calculate the difference between the flow rate of the analysis center node and the sum of the flow rates of all directly related nodes according to the law of mass conservation to characterize the degree of conservation deviation, and obtain the operational correlation mass conservation characteristic relationship data; Step S23: Based on the operational correlation pressure drop characteristic relationship data and the operational correlation mass conservation characteristic relationship data, perform anomaly characteristic analysis on the operational monitoring topology data of the water supply network to generate operational monitoring topology anomaly characteristic data; Step S24: Perform adjacency compensation optimization processing on the water supply network operation monitoring topology data by using the operation monitoring topology anomaly feature data to generate optimized water supply network operation monitoring topology data.

3. The method for dynamic identification of low-pressure areas in water supply networks according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Analyze the characteristics of the water supply network operation status based on the optimized water supply network operation monitoring topology data, and generate water supply network operation status characteristic data. Step S42: Using the characteristic data of the water supply operation status of the pipeline network, the effective response range is delineated starting from the pressure propagation characteristic point and combined with the pressure propagation speed. The response areas corresponding to steady-state pressure propagation and disturbance pressure propagation are distinguished, and the pressure propagation response area data of the water supply network is generated. Step S43: Perform propagation attenuation gradient attribute analysis on the propagation response area data of water supply pressure in the pipeline network to generate pipeline water supply pressure propagation response attribute area data; Step S44: Based on the regional data of water supply pressure propagation response attributes and the optimized water supply network operation monitoring topology data, identify nodes with low pressure and analyze the causes of low pressure, statistically analyze the uniformity of regional pressure distribution, extract the core features of pressure response, and generate water supply network pressure response feature data. Step S45: Based on the pressure response characteristic data of the water supply network, the low-pressure area is defined by adjacent low-pressure nodes and connecting pipe sections, the low-pressure area type is classified and the degree of abnormality is quantified, and the dynamic changes of the low-pressure area are tracked by combining time series data to generate dynamic identification data of low-pressure area of ​​water supply network.

4. The method for dynamic identification of low-pressure areas in water supply networks according to claim 3, characterized in that, Step S45 includes the following steps: Step S451: Based on the pressure response characteristic data of the water supply network, identify node pressure instability phenomena using the pressure change rate as the judgment threshold, determine regional pressure instability by combining the spatial clustering of unstable nodes, quantify the instability characteristic parameters, and generate pressure response instability characteristic data of the water supply network. Step S452: Based on the regional data of water supply pressure propagation response attributes and the instability characteristic data of water supply network pressure response, trace the propagation path of instability, calculate the trend of instability propagation speed and intensity, delineate the dynamic instability propagation range, and generate dynamic instability characteristic data of water supply pressure propagation. Step S453: By integrating the unstable nodes and propagation paths of the water supply network pressure response instability characteristic data and the water supply pressure propagation dynamic instability characteristic data, the low-pressure area range is delineated, the dynamic type of the low-pressure area is classified and the degree of anomaly is quantified, the dynamic change trend of the low-pressure area is tracked, and dynamic identification data of the low-pressure area of ​​the water supply network is generated.

5. A dynamic identification system for low-pressure areas in a water supply network, characterized in that, For executing the dynamic identification method for low-pressure areas in a water supply network as described in claim 1, the dynamic identification system for low-pressure areas in a water supply network includes: The water supply network operation monitoring module is used to process discrete point operation monitoring data of the water supply network using multi-source monitoring sensors, and generate discrete monitoring data of the water supply network operation; and to perform operation monitoring topology analysis on the discrete monitoring data of the water supply network operation, and generate operation monitoring topology data of the water supply network. The operation monitoring and optimization module is used to perform adjacency compensation optimization on the water supply network operation monitoring topology data to generate optimized water supply network operation monitoring topology data. The pipeline water supply pressure dynamic propagation characteristic analysis module is used to perform dynamic propagation characteristic analysis of pipeline water supply pressure based on optimized pipeline network operation monitoring topology data, and generate pipeline water supply pressure dynamic propagation characteristic data. The low-pressure area dynamic identification module of the water supply network is used to perform dynamic identification processing of low-pressure areas of the water supply network based on optimized water supply network operation monitoring topology data and dynamic propagation characteristic data of water supply pressure in the network, and generate dynamic identification data of low-pressure areas of the water supply network.

Images