Automatic monitoring data processing method for pipe network pressure

Abstract

The invention relates to the technical field of pipe network data processing, in particular to an automatic monitoring data processing method for pipe network pressure. The method comprises the following steps: acquiring pipe network structure data; constructing a pipeline topology network based on the pipe network structure data to generate the pipeline topology network; screening main pipelines and branch pipes of the pipeline topology network to obtain pipe network circulation data; carrying out pipe wall microwave resonator deployment on the main pipeline and the branch pipelines based on the pipe network circulation data, and capturing pipeline circumferential deformation harmonic waves in real time through the deployed microwave resonators; longitudinal wave propagation time delay of pipe network circulation data is analyzed, and a pipe body structure dynamic resonance atlas is constructed in combination with pipeline circumferential deformation harmonic waves; and carrying out pipe network internal pressure and pipe wall equivalent stress calculation on the pipeline topology network through a pipe body structure dynamic resonance map. By combining pipeline topology analysis, microwave resonator monitoring, dynamic resonance spectrum and bidirectional fluid-solid coupling analysis, the accuracy of pipe network pressure monitoring and identification is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of pipe network data processing, and in particular to a method for processing automatic monitoring data of pipe network pressure. Background Art

[0002] In the early days, pipeline pressure monitoring relied primarily on manual inspections and traditional mechanical instruments, resulting in low efficiency and prone to human error. This traditional approach was unable to monitor the operational status of the pipeline network in real time, and its data processing and analysis capabilities were limited, resulting in a delay in identifying safety hazards during pipeline operation. The emergence of intelligent sensors and data acquisition technologies has gradually automated pipeline pressure monitoring. Initial systems transmitted sensor data to a centralized control center via wired connections, but this approach still presented challenges such as wiring difficulties and data transmission delays. Leveraging big data analytics and artificial intelligence (AI) technologies, pipeline pressure monitoring systems not only monitor pressure changes in real time but also perform predictive analysis to proactively identify potential failures, thereby improving pipeline safety and reliability. However, current traditional systems are largely limited to pressure measurement and are unable to effectively calculate the pressure distribution within the pipeline and the stress distribution on the pipe wall. Furthermore, they are less able to analyze the complex interactions between flow and pressure changes within the pipeline network, resulting in low accuracy in pipeline pressure monitoring and identification. Summary of the Invention

[0003] Based on this, it is necessary to provide a method for automatically monitoring data processing of pipeline network pressure to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for automatically monitoring data processing of pipe network pressure is provided, the method comprising the following steps:

[0005] Step S1: Obtaining pipe network structure data; constructing a pipe topology network based on the pipe network structure data to generate a pipe topology network; screening the main pipes and branches in the pipe topology network to obtain pipe network flow data;

[0006] Step S2: Based on the pipeline network flow data, microwave resonators are deployed on the pipe walls of the main pipeline and branch pipes, and the deployed microwave resonators are used to capture the pipeline circumferential deformation harmonics in real time; the longitudinal wave propagation delay of the pipeline network flow data is analyzed, and the dynamic resonance spectrum of the pipe body structure is constructed in combination with the pipeline circumferential deformation harmonics;

[0007] Step S3: Calculating the internal pressure and the equivalent stress of the pipe wall of the pipe topology network using the dynamic resonance spectrum of the pipe structure to obtain the internal pressure value and the equivalent stress value of the pipe wall; and performing abnormal pressure determination on the pipe network flow data based on the internal pressure value and the equivalent stress value of the pipe wall to obtain abnormal pressure detection data of the pipe network;

[0008] Step S4: Screen the pipe fittings of the pipeline topology network based on the abnormal pressure detection data of the pipeline network to obtain the pipeline network pipe fitting data; analyze the bidirectional fluid-solid coupling of the pipeline network pipe fitting data to obtain the water hammer coupling pulse pressure peak; accurately locate the abnormal pipeline network pressure area in the pipeline topology network through the abnormal pressure detection data of the pipeline network and the water hammer coupling pulse pressure peak, so as to realize the automatic monitoring operation of the pipeline network pressure.

[0009] This invention utilizes microwave resonator deployment technology to capture the harmonics of the pipeline's circumferential deformation in real time, achieving highly sensitive detection of subtle structural changes within the pipe body and enhancing early warning capabilities for potential pipeline risks. Combining the longitudinal wave propagation delay in flow data with deformation harmonics to construct a dynamic resonance spectrum helps accurately reflect the pipeline's operating status, enabling precise calculation of internal pressure and equivalent stress on the pipe wall, providing a highly reliable basis for abnormal pressure determination. Combining pipe screening results with bidirectional fluid-structure interaction analysis, the peak pressure impulse caused by water hammer can be determined, significantly improving the ability to identify abnormal pressure under complex operating conditions. Combined analysis of abnormal pressure detection data with water hammer pulse peaks allows precise location of pipeline sections experiencing abnormal pressure, avoiding large-scale, blind investigations and improving maintenance efficiency. Based on a comprehensive data flow and structural mechanics model, the entire process, from data acquisition and status analysis to anomaly location, is fully automated, facilitating the development of intelligent urban pipeline network management systems. Early identification of abnormal pressure zones can effectively prevent major incidents such as pipeline bursts and leaks, reducing emergency repair and loss compensation costs. Therefore, the present invention improves the accuracy of pipeline network pressure monitoring and identification by combining pipeline topology analysis, microwave resonator monitoring, dynamic resonance spectrum and bidirectional fluid-solid coupling analysis.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: obtaining an original engineering drawing of the pipe network and extracting pipe network structure information in the original engineering drawing of the pipe network to obtain pipe network structure data;

[0012] Step S12: performing node connectivity analysis on the pipe network structure data to generate pipe topology network data;

[0013] Step S13: clustering the flow paths of the pipeline topology network data to generate candidate trunk path data;

[0014] Step S14: performing path weight determination on the candidate trunk path data, and dividing the candidate trunk path data into trunk pipelines and branches according to the determination result, to obtain trunk and branch division data;

[0015] Step S15: extracting the circulation logic of the trunk and branch pipe division data, thereby generating pipe network circulation data.

[0016] The present invention eliminates a large amount of manual modeling work by automatically extracting pipeline network structure information (S11) from the original engineering drawing, reduces the risk of human error, and ensures the accuracy and completeness of the basic data. The node connectivity analysis (S12) is combined with the topology generation algorithm to quickly build a pipeline topology network that reflects the actual pipeline connection relationship, providing basic support for subsequent pressure analysis and simulation calculations. The use of flow path clustering technology (S13) can effectively identify the main circulation path, and the trunk / branch division is combined with the path weight determination (S14), which helps to highlight the core transportation path and enhance the monitoring and management capabilities of key areas. By extracting the circulation logic (S15) in the trunk and branch division results, structured "pipeline network circulation data" is generated, providing an efficient input data source for subsequent pressure modeling, anomaly detection and resonance analysis. The clear division of the trunk and branch enables subsequent layered processing such as pressure response analysis and water hammer wave propagation modeling according to different network levels, thereby improving the resolution and response efficiency of the overall system modeling. The generation of pipeline network circulation data marks the completion of the dual modeling of physical topology and circulation logic, providing a key support foundation for pipeline structure resonance analysis, equivalent stress solution and abnormal area identification.

[0017] Preferably, step S14 includes the following steps:

[0018] Step S141: performing a path weight determination on the candidate trunk path data to obtain a determination result, wherein the path weight includes the geometric length of the path, the flow demand on the path, and the pressure demand on the path;

[0019] Step S142: When the following conditions are simultaneously present, the candidate trunk path data is determined as trunk pipeline partition data: the geometric length of the path is between 500 meters and 5000 meters, the flow demand on the path is between 50 cubic meters / hour and 1000 cubic meters / hour, and the pressure demand on the path is between 0.5 MPa and 5 MPa;

[0020] Step S143: When any of the following conditions occurs, the candidate trunk path data is determined to be branch partitioning data: the geometric length of the path is less than 500 meters, the flow demand on the path is less than 50 cubic meters / hour, and the pressure demand on the path is less than 0.5 MPa or greater than 5 MPa;

[0021] Step S144: Integrate the trunk pipeline division data and the branch pipeline division data into trunk and branch pipeline division data.

[0022] The present invention constructs a path determination system based on real operating parameters by comprehensively considering the three key weight factors (S141) of geometric length, flow demand and pressure demand, which effectively improves the rationality and engineering applicability of trunk / branch division. 3 / h, pressure 0.5–5MPa) (S142–S143) are used as judgment criteria to avoid subjective judgment and ensure the consistency, reproducibility and engineering operability of the division process. For large-scale urban pipeline networks, automatic classification of candidate paths is achieved through procedural rule judgment (S142, S143), which greatly reduces the workload of manual identification and improves the efficiency of pipeline network modeling. Distinguishing between trunk and branch pipes and integrating them in a unified manner (S144) helps to build a pipeline network structure with clear hierarchy and logic, and provides visualization and controllability support for subsequent structural analysis, flow control and fault isolation. The precise division of trunk / branch pipes can provide precise deployment areas for subsequent flow logic modeling (S15) and microwave resonator layout (S2), thereby improving the diagnostic sensitivity and predictive ability of the entire system.

[0023] Preferably, in step S2, deploying microwave resonators on the main pipeline and branch pipes based on the pipe network flow data includes:

[0024] Screen key nodes of pipeline network circulation data;

[0025] Map key nodes into trunk and branch segments to generate segmented deployment unit data;

[0026] Analyze the waveguide adaptability of the segmented deployment unit data, and optimize the multi-point frequency distribution of the segmented deployment unit data based on the waveguide adaptability to generate resonator configuration solution data;

[0027] Performing position calibration on the resonator configuration scheme data to generate microwave resonator deployment parameter data;

[0028] The microwave resonator is deployed on the pipe wall according to the microwave resonator deployment parameter data, thereby obtaining the deployed microwave resonator.

[0029] The present invention intelligently screens out key nodes from the pipe network circulation data, accurately locates the key areas where the resonators are deployed, avoids waste of resources, and improves the coverage and response capability of the monitoring system in high-risk sections. The segmented deployment unit data is generated by using trunk and branch segment mapping (rationally partitioning the trunk and branches), laying the foundation for subsequent structure matching and frequency planning, and improving the consistency and topological coordination between the deployment structure and the pipe network structure. The waveguide structure adaptability analysis is performed on the segmented unit, and based on the result, multi-point frequency distribution optimization is performed to construct resonator configuration scheme data that meets the resonance characteristics of different pipeline sections, thereby improving the monitoring sensitivity under different materials, calibers and flow conditions. By performing precise position calibration on the resonator configuration scheme, high-precision microwave resonator deployment parameter data is generated to ensure the precise fit of the resonator on the physical pipe wall and the signal coupling quality, thereby improving the stability and accuracy of signal acquisition. The deployment parameter data finally generated has structured characteristics and can be used to guide intelligent deployment equipment or construction systems for automated installation, reduce the risk of manual operation, and improve construction efficiency. After deployment, the microwave resonator becomes the core device for monitoring the circumferential deformation of the pipeline, providing a high-quality harmonic data source for subsequent resonance spectrum construction and pipeline stress state assessment.

[0030] Preferably, analyzing the longitudinal wave propagation delay of the pipe network flow data in step S2 includes:

[0031] Perform segmented flow velocity fitting on the pipe network flow data to generate segment flow velocity data;

[0032] Couple the sound velocity of the flow velocity data within the calculation section to obtain the medium sound velocity distribution data;

[0033] Perform topological path mapping on the medium sound velocity distribution data based on the pipe network circulation data to generate sound wave propagation path diagram data;

[0034] Calculate the propagation delay integral of the acoustic wave propagation path diagram data to generate initial longitudinal wave propagation delay data;

[0035] Detect the drift anomaly of the longitudinal wave propagation delay data, and thus obtain the longitudinal wave propagation delay of the pipeline network flow data.

[0036] The present invention generates high-resolution intra-segment velocity data by performing segmented velocity fitting on the pipe network circulation data (such as by pipe segment, flow state or flow interval), significantly improving the local accuracy of sound velocity calculation and providing a solid foundation for sound wave propagation path modeling. Based on the segmented velocity data, sound velocity coupling calculation is performed, fully considering the influence of temperature, pressure, medium composition, etc. on sound velocity, generating medium sound velocity distribution data that is more adaptable to working conditions, and improving the physical authenticity of propagation delay calculation. The sound velocity distribution is mapped by using the pipe network topology structure to generate sound wave propagation path diagram data that truly reflects the sound wave propagation path, supporting accurate modeling and visual analysis of multi-path propagation phenomena in complex networks. The propagation delay integral method is used to accumulate and sum the propagation time of each segment in the path diagram to avoid the error caused by simple averaging, and generate high-precision initial longitudinal wave propagation delay data, which can be used for comparative detection and model verification. By detecting the drift anomaly of the propagation delay data, abnormal working conditions such as local blockage, pipe wall structure changes or atypical flow states in the pipe network are identified, providing a pre-warning mechanism for pipe network maintenance. The precisely acquired longitudinal wave propagation delay, as one of the dynamic response characteristics, can be jointly analyzed with microwave harmonic data to construct a dynamic resonance spectrum of the pipe structure that integrates time domain and frequency domain characteristics, thereby enhancing the system's global structural perception capability.

[0037] Preferably, in step S2, constructing a dynamic resonance spectrum of the pipe structure in combination with the harmonics of the circumferential deformation of the pipe includes:

[0038] Synchronously calibrate the longitudinal wave propagation delay data and the pipeline circumferential deformation harmonics to generate time-frequency joint benchmark data;

[0039] Extract the resonance response characteristics of the time-frequency joint benchmark data;

[0040] Map the pipeline structure through the resonance response characteristics to generate structural resonance distribution data;

[0041] Perform dynamic energy clustering analysis on the structural resonance distribution data to generate dynamic resonance clustering data;

[0042] The dynamic resonance spectrum of the pipe structure is constructed based on the structural resonance distribution data, dynamic resonance clustering data and resonance response characteristics.

[0043] The present invention synchronously calibrates longitudinal wave propagation delay data and pipeline circumferential deformation harmonics to form a unified time-frequency joint benchmark data at a unified time-frequency scale, effectively eliminating asynchronous sampling errors and providing a precise reference for subsequent feature extraction and map construction. Resonance response feature extraction based on the joint benchmark data can capture the response pattern of the structure under different frequencies and loading conditions, identify potential structural weaknesses and frequency coupling anomalies, and improve the reliability of structural health assessments. The resonance response characteristics are mapped back to the actual pipe segment location to form structural resonance distribution data, which can be used to locate areas of concentrated resonance anomalies and support pipe segment-level structural performance analysis and maintenance decisions. Dynamic energy clustering analysis is performed on the structural resonance distribution to identify pipe segments with similar dynamic resonance characteristics. Dynamic resonance clustering data is obtained, which can assist in the construction of a "resonance risk map" or "dynamic resonance mode spectrum." Based on the structural distribution data, clustering results, and response characteristics, a dynamic resonance map of the pipe structure is constructed, achieving a multi-dimensional fusion of time, frequency, and space, comprehensively reflecting the dynamic operating characteristics of the pipeline structure and possessing high interpretability and predictive capabilities. Dynamic resonance maps can be used to compare and identify risk locations such as abnormal pipeline operation conditions, structural relaxation, and stress concentration areas. They are the core basic data support for intelligent operation and maintenance, automatic monitoring, and fault warning.

[0044] Preferably, step S3 includes the following steps:

[0045] Step S31: performing frequency inversion on the dynamic resonance spectrum of the pipe structure to generate resonance frequency-structure coupling data;

[0046] Step S32: Calculate the stress of the resonance frequency-structure coupling data to obtain the equivalent stress value of the pipe wall;

[0047] Step S33: performing stress distribution mapping on the pipeline topology network according to the equivalent stress value of the pipe wall to generate pipeline node stress diagram data;

[0048] Step S34: performing internal pressure inversion calculation on the pipeline node stress diagram data in combination with the pipeline network flow data to generate the pipeline internal pressure value;

[0049] Step S35: Perform time series comparison analysis on the internal pressure value data of the pipeline and the pipe network flow data to generate pressure time series deviation data; perform joint threshold discrimination processing on the pressure time series deviation data and the pipe wall equivalent stress value to generate pipe network abnormal pressure detection data.

[0050] The present invention performs frequency inversion on the dynamic resonance spectrum of the pipe structure, establishes a coupling relationship between frequency characteristics and structural properties, generates resonance frequency-structure coupling data, and realizes non-destructive perception and precise modeling of the structural health status. Equivalent stress calculation is performed based on the coupling relationship between resonance frequency and structure. The obtained equivalent stress value of the pipe wall can fully reflect the stress response of the structure under operation, providing a basis for subsequent safety evaluation and remaining life prediction. The equivalent stress value of the pipe wall is mapped to a topological network to generate pipeline node stress diagram data, which can be used to identify stress abnormality concentration areas and realize precise positioning of structural safety risks of the pipeline network. Based on the stress diagram data and the pipeline network circulation data, the internal pressure inversion calculation is performed to obtain the internal pressure value of the pipeline, which supplements the dynamic change characteristics of the operating pressure that are difficult to reflect by flow or structural observation alone. By performing a time series comparative analysis of the internal pressure value and the historical circulation data, the pressure change trend is identified, and pressure time series deviation data is formed to promptly discover atypical flow patterns caused by blockage, leakage or air resistance. By jointly analyzing pressure time-series deviation data with pipe wall equivalent stress values, a multi-factor joint discrimination model is constructed to output abnormal pressure detection data for the pipeline network, enhancing the system's ability to respond to sudden pressure changes and fatigue hazards. This step completes the closed-loop process of "structural response → stress calculation → pressure inversion → anomaly identification," providing theoretical and data support for intelligent diagnosis and online monitoring of pipeline network health.

[0051] Preferably, step S33 includes the following steps:

[0052] Step S331: reconstructing the mesh of the pipe wall equivalent stress data to generate meshed pipe wall stress data;

[0053] Step S332: performing spatial projection on the pipe wall gridded stress data to generate stress space mapping data;

[0054] Step S333: performing node fusion on the stress space mapping data and the pipeline topology network to generate initial node stress data; performing directional tensor decomposition on the initial node stress data to generate node principal stress vector data;

[0055] Step S334: Perform full-graph fusion and connectivity weighting on the node principal stress vector data to generate pipeline node stress graph data.

[0056] The present invention reconstructs the grid of the pipe wall equivalent stress data to generate gridded stress data, which converts the original irregularly distributed stress information into a high-resolution data structure with geometric consistency, facilitating subsequent calculation and visualization. The gridded stress data is spatially projected to obtain stress space mapping data, ensuring that the stress distribution is spatially consistent with the actual geometric shape and layout environment of the pipeline, which helps to accurately restore the physical stress field distribution. The initial node stress data generated by the fusion of the stress space mapping data and the pipeline topology network realizes the direct coupling between the physical stress field and the topological structure nodes, facilitating the formation of the subsequent node-level structural response model. By performing directional tensor decomposition on the initial node stress data, the node principal stress vector data obtained contains the principal stress magnitude and direction information, which significantly enhances the ability to judge the force directionality and potential instability risk of the pipeline. Based on the principal stress vector, full-graph fusion and connectivity weighting are performed to generate pipeline node stress graph data that not only maintains the local stress change characteristics, but also reflects the stress conduction link of the overall network, which helps to identify structural vulnerabilities or hidden danger paths caused by stress concentration. The final output node stress diagram provides basic input for subsequent internal pressure inversion, fatigue analysis and pipeline network anomaly diagnosis, and has the advantages of high structural accuracy, high spatial resolution and high physical consistency.

[0057] Preferably, the combined threshold discrimination processing of the pressure time series deviation data and the pipe wall equivalent stress value in step S35 includes:

[0058] When any of the following conditions occurs, it is determined to be a sudden pressure fluctuation abnormality and the sudden pressure fluctuation abnormality data will be obtained: the pressure change rate exceeds 0.5MPa / min within any 5 minutes; the single point pressure value increases or decreases by more than 1.2MPa within 10 minutes; the pressure fluctuation frequency is greater than 0.8Hz and lasts for more than 15 minutes;

[0059] When the following conditions occur simultaneously, it is determined to be a periodic abnormal pressure fluctuation and the periodic pressure fluctuation abnormal data is obtained: the pressure peak deviation within adjacent monitoring cycles exceeds ±20%; the peak / trough time interval change rate within three consecutive cycles exceeds ±25%; after comparison with the historical baseline waveform, the dynamic time regularization deviation exceeds 10%;

[0060] When the following conditions are met at the same time, it is determined that the pipe wall equivalent stress exceeds the limit abnormality and the equivalent stress exceedance abnormality data is obtained: the pipe wall equivalent stress value exceeds 80% of the design material yield strength, that is, exceeds 160MPa, where the design material yield strength limit is 200MPa; the stress concentration factor is higher than 2.5; the equivalent stress sudden increase rate exceeds 15MPa / 10min within any 30-minute window, and the abnormal section length exceeds 20 meters;

[0061] Integrate the abnormal data of sudden pressure fluctuation, abnormal data of periodic pressure fluctuation and abnormal data of equivalent stress exceeding the limit, align the spatial position and time stamp, and generate abnormal pressure detection data of the pipeline network.

[0062] The present invention monitors indicators such as the rate of pressure change, the sharp fluctuation of single-point pressure values, and the frequency of pressure fluctuations, and this step can accurately identify sudden pressure fluctuation anomalies. The rapid capture of sudden pressure fluctuation anomalies can effectively warn of sudden accident risks in the system, such as pipeline rupture or burst, and provide timely response at critical moments. By analyzing the periodic changes in pressure fluctuations and monitoring indicators such as pressure peak deviation, peak / trough interval change rate, and dynamic time regularization deviation, it is possible to issue an alarm in a timely manner when periodic pressure fluctuations occur, and effectively detect regular fluctuation anomalies caused by pipeline fatigue, equipment aging, etc. This provides strong support for the diagnosis of hidden dangers in long-term system operation. Combined with the comparison of the equivalent stress of the pipe wall with the yield limit, it is possible to timely discover the potential damage risk caused by excessive stress on the pipeline, especially at locations with high stress concentration (such as elbows, joints, etc.) and changes in the stress sudden increase rate, which can effectively prevent accidents such as rupture and leakage caused by pipeline overload. This move can accurately identify the overload state in the pipeline by analyzing the equivalent stress sudden increase rate and stress overlimit conditions. By integrating data on sudden pressure fluctuation anomalies, periodic pressure fluctuation anomalies, and pipe wall equivalent stress exceeding the limit, and aligning the spatial location with the timestamp, a complete abnormal data map of the pipeline system at different time periods and spatial locations can be provided, providing data support for system operation optimization, maintenance decisions, and equipment replacement. For complex pipeline systems, identifying potential pressure and stress anomalies in advance can provide managers with clear decision-making support, especially before sudden failures occur, effectively reducing the risks brought by sudden failures in the pipeline network and achieving more intelligent preventive maintenance. Joint threshold discrimination processing can classify different types of anomalies, reduce false alarms and missed alarms, improve the accuracy and efficiency of pipeline network monitoring, make anomaly judgments more detailed, and ensure the long-term stable operation of the pipeline network.

[0063] Preferably, step S4 includes the following steps:

[0064] Step S41: Analyze the spatial coupling of abnormal pressure detection data of the pipe network to generate abnormal node screening data; extract topological paths from the abnormal node screening data;

[0065] Step S42: identifying components of the pipeline topology network according to the extracted topological path to generate pipeline network fitting data; performing bidirectional fluid-structure coupling modeling on the pipeline network fitting data to generate water hammer effect structural response data;

[0066] Step S43: extracting the time domain characteristics of the water hammer effect structural response data to obtain the water hammer coupled pulse pressure peak; performing joint positioning processing on the water hammer coupled pulse pressure peak and the abnormal node screening data to generate abnormal pressure area data of the pipeline network;

[0067] Step S44: Adaptive monitoring deployment processing is performed based on the abnormal pressure area data of the pipeline network to realize automatic monitoring of the pipeline network pressure.

[0068] By analyzing the spatial coupling of abnormal pressure detection data in a pipeline network, the present invention accurately identifies abnormal nodes. This process effectively locates the source of pressure anomalies, providing precise target areas for subsequent pipeline maintenance and repair, thereby reducing the risk of pipeline damage. Through topological path extraction and pipeline component identification, key components in the pipeline system can be systematically identified and detailed modeled. This process provides a comprehensive understanding of the health of the pipeline structure and supports accurate diagnosis. Bidirectional fluid-structure interaction modeling enables a comprehensive analysis of the impact of water hammer on the pipeline structure, thereby obtaining structural response data for water hammer. This analysis is crucial for understanding water hammer caused by sudden flow changes, valve operation, and other factors in the pipeline network, effectively predicting and controlling the risk of structural damage caused by water hammer. By extracting the peak pressure pulse of the water hammer effect and combining it with abnormal node screening data, abnormal pressure areas in the pipeline network can be accurately identified. This process enables real-time monitoring of abnormal conditions in the pipeline system and provides timely feedback to operation and maintenance personnel, preventing incidents from escalating. Based on the analysis of abnormal pressure area data in the pipeline network, the system can implement adaptive monitoring deployment and adjust monitoring strategies based on actual conditions. This flexible monitoring approach automatically adjusts monitoring priorities based on pipeline operating conditions, ensuring pipeline network safety at every stage of operation. Automated monitoring significantly reduces the burden and workload of manual monitoring while ensuring accurate real-time monitoring. Automated monitoring, particularly in dynamic pipeline network situations with significant pressure fluctuations, enables rapid response and action, improving pipeline network reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A schematic flow chart of the steps of a method for automatically monitoring data processing of pipe network pressure;

[0070] Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0071] Figure 3 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0072] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0073] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0074] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0075] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0076] To achieve this, please refer to Figures 1 to 3 A method for processing automatic monitoring data of pipe network pressure, the method comprising the following steps:

[0077] Step S1: Obtaining pipe network structure data; constructing a pipe topology network based on the pipe network structure data to generate a pipe topology network; screening the main pipes and branches in the pipe topology network to obtain pipe network flow data;

[0078] Step S2: Based on the pipeline network flow data, microwave resonators are deployed on the pipe walls of the main pipeline and branch pipes, and the deployed microwave resonators are used to capture the pipeline circumferential deformation harmonics in real time; the longitudinal wave propagation delay of the pipeline network flow data is analyzed, and the dynamic resonance spectrum of the pipe body structure is constructed in combination with the pipeline circumferential deformation harmonics;

[0079] Step S3: Calculating the internal pressure and the equivalent stress of the pipe wall of the pipe topology network using the dynamic resonance spectrum of the pipe structure to obtain the internal pressure value and the equivalent stress value of the pipe wall; and performing abnormal pressure determination on the pipe network flow data based on the internal pressure value and the equivalent stress value of the pipe wall to obtain abnormal pressure detection data of the pipe network;

[0080] Step S4: Screen the pipe fittings of the pipeline topology network based on the abnormal pressure detection data of the pipeline network to obtain the pipeline network pipe fitting data; analyze the bidirectional fluid-solid coupling of the pipeline network pipe fitting data to obtain the water hammer coupling pulse pressure peak; accurately locate the abnormal pipeline network pressure area in the pipeline topology network through the abnormal pressure detection data of the pipeline network and the water hammer coupling pulse pressure peak, so as to realize the automatic monitoring operation of the pipeline network pressure.

[0081] This invention utilizes microwave resonator deployment technology to capture the harmonics of the pipeline's circumferential deformation in real time, achieving highly sensitive detection of subtle structural changes within the pipe body and enhancing early warning capabilities for potential pipeline risks. Combining the longitudinal wave propagation delay in flow data with deformation harmonics to construct a dynamic resonance spectrum helps accurately reflect the pipeline's operating status, enabling precise calculation of internal pressure and equivalent stress on the pipe wall, providing a highly reliable basis for abnormal pressure determination. Combining pipe screening results with bidirectional fluid-structure interaction analysis, the peak pressure impulse caused by water hammer can be determined, significantly improving the ability to identify abnormal pressure under complex operating conditions. Combined analysis of abnormal pressure detection data with water hammer pulse peaks allows precise location of pipeline sections experiencing abnormal pressure, avoiding large-scale, blind investigations and improving maintenance efficiency. Based on a comprehensive data flow and structural mechanics model, the entire process, from data acquisition and status analysis to anomaly location, is fully automated, facilitating the development of intelligent urban pipeline network management systems. Early identification of abnormal pressure zones can effectively prevent major incidents such as pipeline bursts and leaks, reducing emergency repair and loss compensation costs. Therefore, the present invention improves the accuracy of pipeline network pressure monitoring and identification by combining pipeline topology analysis, microwave resonator monitoring, dynamic resonance spectrum and bidirectional fluid-solid coupling analysis.

[0082] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart showing the steps of a method for automatically monitoring data processing of pipe network pressure according to the present invention. In this example, the method for automatically monitoring data processing of pipe network pressure includes the following steps:

[0083] Step S1: Obtaining pipe network structure data; constructing a pipe topology network based on the pipe network structure data to generate a pipe topology network; screening the main pipes and branches in the pipe topology network to obtain pipe network flow data;

[0084] Step S2: Based on the pipeline network flow data, microwave resonators are deployed on the pipe walls of the main pipeline and branch pipes, and the deployed microwave resonators are used to capture the pipeline circumferential deformation harmonics in real time; the longitudinal wave propagation delay of the pipeline network flow data is analyzed, and the dynamic resonance spectrum of the pipe body structure is constructed in combination with the pipeline circumferential deformation harmonics;

[0085] Step S3: Calculating the internal pressure and the equivalent stress of the pipe wall of the pipe topology network using the dynamic resonance spectrum of the pipe structure to obtain the internal pressure value and the equivalent stress value of the pipe wall; and performing abnormal pressure determination on the pipe network flow data based on the internal pressure value and the equivalent stress value of the pipe wall to obtain abnormal pressure detection data of the pipe network;

[0086] Step S4: Screen the pipe fittings of the pipeline topology network based on the abnormal pressure detection data of the pipeline network to obtain the pipeline network pipe fitting data; analyze the bidirectional fluid-solid coupling of the pipeline network pipe fitting data to obtain the water hammer coupling pulse pressure peak; accurately locate the abnormal pipeline network pressure area in the pipeline topology network through the abnormal pressure detection data of the pipeline network and the water hammer coupling pulse pressure peak, so as to realize the automatic monitoring operation of the pipeline network pressure.

[0087] In an embodiment of the present invention, complete pipe network structure data, including information such as pipe diameter, pipe length, pipe material, installation year, interface type, and pressure level, is obtained through a SCADA system, BIM model, or GIS platform. Historical operating data is also obtained from flow meters, pressure sensors, and the like. Data preprocessing is performed using Python or MATLAB to remove missing values ​​and outliers. Next, a graph theory library such as NetworkX is used to construct a pipeline topology network based on the information of pipeline nodes and pipe segments. Each pipeline segment is treated as an edge of a directed graph, and each node as a vertex of the graph, with attribute weights such as flow rate and pipe diameter assigned. The network is then segmented using a maximum flow minimum cut algorithm. Combined with the K-means clustering method, pipeline segments with dense flow and wide connectivity are classified as trunk pipelines, while the rest are classified as branches, thereby obtaining pipeline network circulation data that reflects the true flow status of the pipeline network. Microwave resonators are evenly distributed on the outer walls of the selected trunk pipelines and key branches. The specific method is to select high-sensitivity microwave resonators with an operating frequency of 5-10 GHz, set one every 5-20 meters, and wirelessly connect the resonators to the monitoring center. The resonator transmits microwave signals and detects the frequency drift of the reflected wave, capturing harmonic changes caused by pipe wall deformation. A reference resonator simultaneously collects ambient noise and de-noises the data from other nodes. The collected data undergoes a Fast Fourier Transform (FFT) to extract the primary harmonic components. The longitudinal wave propagation delay in the flow data is calculated by calculating the propagation time difference of the water hammer signal between nodes, using a cross-correlation algorithm to improve delay measurement accuracy. The circumferential deformation data and the longitudinal wave propagation delay are aligned on the time axis, and empirical mode decomposition (EMD) is used to eliminate seasonal and periodic interference. Finally, a highly dynamic resonance spectrum of the pipe structure is constructed using methods such as agile spectrum analysis and the Hilbert-Huang transform. The resonance spectrum is then used to invert the internal pressure and equivalent stress. The specific method is to establish a resonant frequency-stress-pressure parameter equation based on material mechanics. Basic parameters such as the pipe's material properties, thickness, and diameter are input, and the frequency drift is substituted into the model to solve for the internal pressure. Finite element simulation software (such as ANSYS) is then used to discretize the pipe segments and apply loads. The equivalent stress field distribution for each monitored pipe segment is solved through multi-physics field coupling. Pressure and stress values ​​form time-series data. Using ARIMA prediction models and LSTM neural networks, the expected pressure predictions are compared with the current values. Abnormal fluctuations are identified as abnormal pressure detection data, and alert thresholds are set for immediate warnings. Using this abnormal pressure detection data, the pipeline network topology is compared to identify pipe fittings within the abnormal area. This creates a list of pipe fittings, and valves, elbows, tees, brackets, and other components are categorized and labeled.Based on these abnormal areas, a bidirectional fluid-structure interaction model encompassing both the fluid and solid domains was constructed. Fluent and other CFD software were used to simulate fluid impact, combined with ANSYS Motion to simulate pipe wall response. The peak pressure impulse caused by the water hammer effect, as well as its propagation rate and attenuation along the pipe wall, were calculated. A pulse pressure backpropagation algorithm was used to trace the abnormal point and precisely locate the source of the abnormal pressure. Finally, the specific location and type of abnormality were communicated to the pipeline network monitoring system, enabling automated monitoring and maintenance recommendations.

[0088] Preferably, step S1 includes the following steps:

[0089] Step S11: obtaining an original engineering drawing of the pipe network and extracting pipe network structure information in the original engineering drawing of the pipe network to obtain pipe network structure data;

[0090] Step S12: performing node connectivity analysis on the pipe network structure data to generate pipe topology network data;

[0091] Step S13: clustering the flow paths of the pipeline topology network data to generate candidate trunk path data;

[0092] Step S14: performing path weight determination on the candidate trunk path data, and dividing the candidate trunk path data into trunk pipelines and branches according to the determination result, to obtain trunk and branch division data;

[0093] Step S15: extracting the circulation logic of the trunk and branch pipe division data, thereby generating pipe network circulation data.

[0094] In an embodiment of the present invention, the original engineering drawings of the pipe network are obtained, which include CAD drawings, PDF format pipe layout drawings, BIM models or GIS data. An image recognition algorithm (such as OpenCV combined with a deep learning model) is used to perform structured extraction of key elements such as pipe segments, nodes, manhole covers, valves, etc. in the drawings. For CAD drawings, line segment and text object information can be obtained through DWG / DXF parsing tools and parsed into node-pipe segment models; for BIM data, the corresponding pipe segment component information is directly extracted from the IFC structure. After processing, structured pipe network structure data is formed, including fields such as node number, pipe segment number, pipe diameter, length, material, node type, etc. Node connectivity analysis is performed based on the above-mentioned pipe segment and node data, and a directed graph structure is constructed. Each pipe segment is regarded as an edge, and the node is the vertex of the graph. The direction attribute is assigned to the edge according to the flow direction information. A graph traversal algorithm (such as depth-first search DFS or breadth-first search BFS) is used to identify isolated nodes and ring structures, and automatically repair broken segments. The resulting pipeline topology network data, with spatial and directional attributes, can be visualized and analyzed using graph analysis tools such as NetworkX or Gephi. Flow paths are clustered within the constructed topology network. First, real-time or historical flow data is obtained, and the average flow per unit time for each edge is calculated and normalized. Based on the shortest path algorithm on the graph and multi-source flow weights, a density-based clustering algorithm (such as DBSCAN or SpectralClustering) is used to cluster high-flow, continuous path segments into candidate trunk path data. This process can be supplemented with information such as historical water supply and supply area planning for correction. Path weights are determined for the candidate trunk path data. A path weight calculation formula is defined, for example: Wi = α·Fi + β·Li + γ·Di; where Wi is the path weight, Fi is the total path flow, Li is the total path length, Di is the average pipe diameter, and α, β, and γ are adjustable empirical weight coefficients. By setting a threshold, paths with weights above the threshold are selected as trunks, and the rest are branches. Ultimately, trunk and branch demarcation data is generated, and each pipe segment is labeled with the main / branch attributes. The flow logic relationships within this trunk and branch demarcation data are extracted, recording topological logic such as each path's starting point, end point, passing nodes, and whether it connects to other trunks / branches. Combining directional attributes, historical hydraulic data, and scheduling strategies, a directed flow graph model is constructed and output as standard network flow data for subsequent hydraulic simulation and dynamic monitoring.

[0095] Preferably, step S14 includes the following steps:

[0096] Step S141: performing a path weight determination on the candidate trunk path data to obtain a determination result, wherein the path weight includes the geometric length of the path, the flow demand on the path, and the pressure demand on the path;

[0097] Step S142: When the following conditions are simultaneously present, the candidate trunk path data is determined as trunk pipeline partition data: the geometric length of the path is between 500 meters and 5000 meters, the flow demand on the path is between 50 cubic meters / hour and 1000 cubic meters / hour, and the pressure demand on the path is between 0.5 MPa and 5 MPa;

[0098] Step S143: When any of the following conditions occurs, the candidate trunk path data is determined to be branch partitioning data: the geometric length of the path is less than 500 meters, the flow demand on the path is less than 50 cubic meters / hour, and the pressure demand on the path is less than 0.5 MPa or greater than 5 MPa;

[0099] Step S144: Integrate the trunk pipeline division data and the branch pipeline division data into trunk and branch pipeline division data.

[0100] In this embodiment of the present invention, a path weight parameter is calculated for each path in the candidate trunk path data. This includes: using the geographic coordinates between nodes to calculate the total length of the path using a geodesic distance formula or a GIS measurement function (such as ST_Length in PostGIS); combining real-time flow monitoring data or historical flow records from the SCADA system to calculate the average flow rate of each pipe segment in the path and determine the total demand value; and analyzing the pressure fluctuation range of the path during different operating periods based on hydraulic model simulation (such as EPANET or a self-developed hydraulic calculation module) or measured pressure data to extract the average or peak pressure required for operation. A set of multi-condition joint judgment criteria is set. The system sequentially retrieves the candidate path data and determines whether it simultaneously meets the following three conditions: geometric length ∈ [500 meters, 5000 meters]: reflecting the path's large-scale, cross-regional transmission capacity; flow demand ∈ [50 cubic meters / hour, 1000 cubic meters / hour]: indicating that the path is at a medium-to-high flow level and has a main transmission function; pressure demand ∈ [0.5 MPa, 5 MPa]: falling within the conventional water supply pressure range and meeting the trunk's stable supply pressure requirements. If all three conditions are met simultaneously, the system explicitly classifies the path as trunk pipeline demarcation data and labels it "trunk pipeline." The system also records the reason for the determination and key parameter values ​​for subsequent traceability. The system then determines whether any of the following conditions hold true: geometric length <500 meters: typically represents a local connection or terminal branch line; flow demand <50 cubic meters / hour: indicates low daily flow and cannot support large-scale transmission; pressure demand <0.5MPa or >5MPa: indicates abnormal pressure and is unsuitable for stable trunk operation. If any of the above conditions is met, the path is directly identified as branch pipeline demarcation data and labeled "branch pipeline." The labeled paths are then integrated, and the system merges the "trunk pipeline" path with the "branch pipeline" path to form the final trunk and branch pipeline demarcation data. Each path is accompanied by a determination label, original weight parameter, classification basis, and determination confidence indicator for reference and verification by upstream modules or operation and maintenance personnel.

[0101] Preferably, in step S2, deploying microwave resonators on the main pipeline and branch pipes based on the pipe network flow data includes:

[0102] Screen key nodes of pipeline network circulation data;

[0103] Map key nodes into trunk and branch segments to generate segmented deployment unit data;

[0104] Analyze the waveguide adaptability of the segmented deployment unit data, and optimize the multi-point frequency distribution of the segmented deployment unit data based on the waveguide adaptability to generate resonator configuration solution data;

[0105] Performing position calibration on the resonator configuration scheme data to generate microwave resonator deployment parameter data;

[0106] The microwave resonator is deployed on the pipe wall according to the microwave resonator deployment parameter data, thereby obtaining the deployed microwave resonator.

[0107] In an embodiment of the present invention, by analyzing the pipeline network topology and circulation data, nodes with strong flow volatility, sudden flow velocity changes, frequent pipe diameter changes, and a concentration of historical anomalies are extracted. A sliding window technique is used in combination with the coefficient of variation (CV) and volatility indicators to model the pressure and flow velocity change trends of each node, thereby identifying a set of key nodes. In addition, a graph neural network (GNN) can be introduced to enhance node importance assessment to take into account both structural topology and physical changes. For key nodes, upstream and downstream segments are divided along the pipeline path, and the entire trunk or branch pipe is divided into multiple segmented deployment units. Each unit consists of two key nodes or the path between a key node and the end node, and its pipe length, pipe diameter, material, direction, surrounding environment and other attributes are recorded. This process can be completed on a GIS platform through depth-first traversal combined with geographic buffer analysis. In each deployment unit, a simplified propagation model of the resonant cavity is established to calculate whether its waveguide boundary conditions meet the requirements of microwave resonance propagation. The waveguide adaptability indicators (such as Q value, coupling efficiency, and reflection loss) of each pipe wall segment are analyzed through numerical simulation (such as COMSOL or HFSS). Based on the waveguide adaptation results, the microwave frequency distribution is optimized to a non-uniformly spaced deployment structure. A multi-objective optimization method based on a genetic algorithm (GA) or particle swarm optimization (PSO) is used to achieve optimal matching of deployment frequency, spacing, and orientation. This generates resonator configuration data to avoid frequency overlap and harmonic interference. The ideal deployment points in the configuration are mapped to actual constructible locations. Using 3D laser scanning or BIM models, spatial modeling of the surrounding environment is performed, taking into account factors such as construction accessibility, terrain obstruction, water level fluctuations, and maintenance safety. Local adjustment algorithms (such as the ICP algorithm combined with spatial grid calibration) are used to achieve 3D spatial repositioning of the deployment points. Ultimately, deployment parameter data for each resonator is generated, including specific location coordinates (X, Y, Z), deployment orientation, mounting bracket specifications, and cable routing recommendations. These deployment parameters are input into a construction platform, and field layout is performed using a high-precision RTK or total station. Microwave resonator units are installed on-site using magnetic, snap-on, or bracket-mounted systems. Frequency response testing of each resonator is performed using a portable network analyzer to ensure that the resonant frequency is consistent with the simulated value. After installation, each resonator data node is connected to the data acquisition system via wireless or LoRa networking to form a deployed microwave resonator network that can be used for subsequent deformation detection.

[0108] Preferably, analyzing the longitudinal wave propagation delay of the pipe network flow data in step S2 includes:

[0109] Perform segmented flow velocity fitting on the pipe network flow data to generate segment flow velocity data;

[0110] Couple the sound velocity of the flow velocity data within the calculation section to obtain the medium sound velocity distribution data;

[0111] Perform topological path mapping on the medium sound velocity distribution data based on the pipe network circulation data to generate sound wave propagation path diagram data;

[0112] Calculate the propagation delay integral of the acoustic wave propagation path diagram data to generate initial longitudinal wave propagation delay data;

[0113] Detect the drift anomaly of the longitudinal wave propagation delay data, and thus obtain the longitudinal wave propagation delay of the pipeline network flow data.

[0114] In an embodiment of the present invention, the flow data (pressure, flow velocity, temperature) of the entire pipeline is divided according to the topological structure and nodes, and continuous flow segments are extracted to perform flow velocity modeling. A piecewise polynomial regression model (such as a third-order spline fitting or a piecewise Bessel function) is used to fit the flow velocity data of each segment to overcome the non-stationarity and local anomalies of the actual data. The intra-segment flow velocity function vi(t,x) under the time-space distribution of each segment is output to form an intra-segment flow velocity data set. Based on the flow velocity data of each segment and thermodynamic parameters such as temperature and pressure, combined with the sound velocity derivation model in the ideal gas state equation or the Navier-Stokes equation, the local medium sound velocity c is calculated. i The basic model is: Where γ is the specific heat ratio, P i is the pressure, ρ i is the density, which can be obtained by inverse calculation of flow velocity and temperature. For non-ideal working conditions, correction coefficients or numerical simulation can be used to solve the coupling model and output the medium sound velocity distribution data to reflect the wave propagation capacity of different pipe sections. Combined with the pipeline topology, according to the flow direction and node connection relationship, a directed weighted graph model G(V,E) is constructed, where each edge e ij The weight is the inverse of the medium sound velocity function on the corresponding pipe section 1 / c i (x) is used as the propagation delay factor. All paths from the starting node to the terminal node are mapped through topological traversal (such as the Dijkstra algorithm or dynamic path planning) to generate acoustic wave propagation path graph data, namely, the effective propagation path between each pair of nodes and its sound speed distribution sequence. The integral delay of each pipe segment on the path is estimated. The propagation delay can be defined as follows: Combined with the actual sound speed function interpolation, the numerical integration method (such as Simpson integral or Romberg integral) is used to solve the propagation time of each path in the propagation path diagram to generate the initial longitudinal wave propagation delay data matrix τ ij, representing the longitudinal wave propagation time from node i to j. A time series analysis is performed on the initial propagation delay data matrix, and a delay residual sequence is constructed for comparison with a reference standard model. Applications such as Z-score detection, CUSUM (cumulative sum control chart), or LSTM prediction residual models are used to identify drift anomalies in the delay data, with particular attention paid to sudden changes, trend drift, or non-periodic jumps. After the anomaly is detected, the drift is filtered and corrected (such as Kalman filtering or exponential smoothing), ultimately outputting well-structured, error-controlled longitudinal wave propagation delay data, which serves as the core input parameter for subsequent dynamic resonance modeling.

[0115] Preferably, in step S2, constructing a dynamic resonance spectrum of the pipe structure in combination with the harmonics of the circumferential deformation of the pipe includes:

[0116] Synchronously calibrate the longitudinal wave propagation delay data and the pipeline circumferential deformation harmonics to generate time-frequency joint benchmark data;

[0117] Extract the resonance response characteristics of the time-frequency joint benchmark data;

[0118] Map the pipeline structure through the resonance response characteristics to generate structural resonance distribution data;

[0119] Perform dynamic energy clustering analysis on the structural resonance distribution data to generate dynamic resonance clustering data;

[0120] The dynamic resonance spectrum of the pipe structure is constructed based on the structural resonance distribution data, dynamic resonance clustering data and resonance response characteristics.

[0121] In an embodiment of the present invention, the circumferential deformation harmonics of the pipeline are obtained from the raw data collected in real time by the microwave resonator, and the frequency changes thereof reflect the micro-deformation behavior of the pipe wall under fluid disturbance and internal pressure fluctuation. At the same time, the longitudinal wave propagation delay data is obtained by a high-precision sensor array arranged longitudinally to accurately characterize the spatiotemporal characteristics of the fluid disturbance propagating at different positions in the pipeline. A high-precision clock synchronization module (such as a PTP protocol device) is used to time-align the longitudinal wave propagation delay data with the deformation harmonic signal. In order to avoid errors introduced by time difference, a cross-correlation algorithm is used to calibrate the time feature points of the two signal sources (such as wave peaks and harmonic main frequency change points); in the frequency domain, a short-time Fourier transform (STFT) is used to convert the two signals into a unified time-frequency two-dimensional matrix, and interpolation processing is performed to form a time-frequency joint reference data with a unified sampling rate and resolution. The data generated in this step retains the time correlation and frequency response characteristics of the circumferential harmonics and longitudinal wave propagation, and is the core basic data for resonance analysis. Empirical mode decomposition (EMD) and Hilbert transform are performed on this combined data to extract intrinsic mode functions (IMFs) of various orders, identifying characteristic parameters such as natural resonant frequencies, excitation frequencies, decay rates, and quality factors (Q values). Dimensional noise reduction is performed using principal component analysis (PCA) or independent component analysis (ICA), preserving the key resonant frequency variations and energy distribution characteristics. A local maximum tracking algorithm is then used to extract frequency drift trajectories and obtain resonant response spectra, which serve as response indicators for subsequent structural mapping. Using the spatial geometric coordinates of the pipe network recorded in a GIS or BIM platform, each set of harmonic response characteristics is associated with its physical spatial location. Using a response-position mapping matrix, the resonant characteristics are projected onto the actual pipe sections, forming a spatialized structural resonance distribution map. Combining material properties (such as elastic modulus, wall thickness, and density) with historical operating data, finite element-assisted mapping is used to construct a structural resonance distribution dataset containing indicators such as resonant frequency, energy density, and wave propagation velocity. This data is organized as a spatial grid and can be viewed as a multi-layer data cube. The time series in the structural resonance distribution data is divided into sliding windows (e.g., 10-second sliding windows), and dynamic parameters such as local harmonic energy density, energy change rate, and frequency jitter amplitude are calculated in each window. These local structures are classified using time series clustering algorithms (e.g., K-shape, DTW-KMeans) or spectral clustering methods to identify location groups with frequent resonance or abnormal coupling in the pipe section. The clustering results are expressed in a heat map or flow map to form dynamic resonance clustering data, which clearly indicates which areas have dynamic coupling enhancement phenomena or long-term vibration trends. Combining the above three types of key data - (1) structural resonance distribution data, (2) dynamic resonance clustering data, and (3) resonance response characteristics - the dynamic structural response spectrum of the entire pipeline is modeled using a graph neural network (GNN) framework.Each pipe segment node is a point in the graph, and connecting pipe segments are edges. Node attributes include frequency, stress state, and energy concentration; edge attributes include time delay and resonance propagation path. Using graph generation algorithms (such as GCN or GraphSAGE), potential structural coupling hotspots and hidden fatigue segments are inferred, and the resonance state is dynamically updated.

[0122] Of particular importance, dynamic energy cluster analysis of structural resonance distribution data also includes:

[0123] Performing spectrum analysis on structural resonance distribution data to generate resonance spectrum data;

[0124] Calculate the energy density of resonance spectrum data;

[0125] Perform dynamic time clustering on the resonance spectrum data according to energy density to generate dynamic time-frequency clustering data;

[0126] Extract clustering features of dynamic time-frequency clustering data, where clustering features include peak frequency and amplitude;

[0127] The energy distribution of the structural resonance distribution data is extracted through clustering features to generate dynamic resonance clustering data.

[0128] In an embodiment of the present invention, structural resonance data is obtained, usually from sensor measurements, including structural response data in different time periods and different vibration modes. The resonance distribution data is denoised, filtered and standardized to eliminate external noise and environmental interference, ensuring the accuracy of the analysis results. Fast Fourier transform (FFT) or other spectrum analysis methods are applied to convert the time domain resonance distribution data into frequency domain data. FFT can convert the signal from the time domain to the frequency domain, revealing the various frequency components contained in the vibration signal. Through spectrum analysis, a spectrum containing frequency and amplitude is obtained. The spectrum reflects the resonant response of the structure at different frequencies. The power spectral density method is used to calculate the energy density corresponding to each frequency point. PSD reflects the energy distribution of different frequency components, which can help understand the vibration energy of the structure at different frequencies. Energy density formula: Where E(f) is the energy density at frequency f, X(f) is the Fourier transform amplitude at that frequency, and Δf is the frequency resolution. An energy density plot is generated based on the calculated energy density data. This plot shows the energy distribution of the structure across frequency bands, facilitating further analysis and clustering. The energy density data is temporally clustered using the Dynamic Time Warping (DTW) algorithm. DTW can align similar patterns in a time series and is particularly suitable for signals with temporal variations and phase differences. Dynamic temporal clustering is performed on the energy density-based spectral data using clustering algorithms (such as K-means, DBSCAN, and hierarchical clustering). By comparing the resonant responses across different time periods, similar spectra are clustered together to generate dynamic time-frequency cluster data. The clustering process classifies the structure's resonant spectrum data across different time periods into multiple clusters, each representing a resonant mode with similar dynamic characteristics. The output cluster data includes a cluster label and associated time-frequency features for each time period. For each cluster, the peak frequency is extracted from its spectrum. This peak frequency typically represents the primary resonant frequency of the structure within that cluster mode. The peak amplitude of each cluster is extracted to reflect the vibration intensity of the frequency. The larger the amplitude, the stronger the resonance response of the frequency band. A feature vector is generated for each cluster, which contains information such as peak frequency and amplitude. These features can be used for subsequent analysis or model training. Based on the extracted cluster features (such as peak frequency, amplitude, etc.), the energy distribution of each cluster is extracted. By calculating the energy density and frequency response of each cluster, the energy distribution of the structure in different modes can be obtained. The energy characteristics of each cluster are combined with the frequency response to generate a descriptive data containing the energy distribution of each resonance mode. The energy distribution is combined with the time-frequency characteristics to form complete dynamic resonance cluster data. These data will help analyze the resonance modes of the structure under different working conditions and the corresponding energy concentration areas.

[0129] As an example of the present invention, refer to Figure 2 As shown, in this example, step S3 includes:

[0130] Step S31: performing frequency inversion on the dynamic resonance spectrum of the pipe structure to generate resonance frequency-structure coupling data;

[0131] Step S32: Calculate the stress of the resonance frequency-structure coupling data to obtain the equivalent stress value of the pipe wall;

[0132] Step S33: performing stress distribution mapping on the pipeline topology network according to the equivalent stress value of the pipe wall to generate pipeline node stress diagram data;

[0133] Step S34: performing internal pressure inversion calculation on the pipeline node stress diagram data in combination with the pipeline network flow data to generate the pipeline internal pressure value;

[0134] Step S35: Perform time series comparison analysis on the internal pressure value data of the pipeline and the pipe network flow data to generate pressure time series deviation data; perform joint threshold discrimination processing on the pressure time series deviation data and the pipe wall equivalent stress value to generate pipe network abnormal pressure detection data.

[0135] In an embodiment of the present invention, dynamic response data of the pipe structure is collected at different locations on the pipeline using vibration sensors or accelerometers. Ensure that the sensor locations cover key points on the pipeline, particularly high-risk areas. Spectral analysis (e.g., Fourier transform) is performed on the collected dynamic response signals to generate a dynamic resonance spectrum of the pipe body. This step reveals the response characteristics of the pipeline at different frequencies. Using structural vibration theory and inverse problem solving methods, frequency inversion is performed on the resonance spectrum. Through inversion analysis, the resonant frequency of the pipeline structure and its coupling relationship with the structure are determined, generating "resonance frequency-structure coupling data." A dynamic structural coupling model of the pipeline is established based on the physical properties of the pipeline (e.g., material properties, geometry, wall thickness, etc.) and the frequency inversion results. Using the coupling relationship between the resonant frequency and the pipeline structure, the stress distribution of the pipeline at different frequencies is calculated using finite element analysis (FEA) or analytical mechanics methods. The maximum stress of the pipe wall is extracted from the stress distribution, and the pipe wall is weighted according to the stress generated at different frequencies to obtain the equivalent stress value of the pipe wall. This data reflects the stress response of the pipeline under dynamic load. A topological network model of the pipeline is constructed to identify key nodes and branches of the pipeline. The equivalent stress value of the pipe wall is mapped to each node in the pipeline topology network. Through mechanical analysis, the stress value at each node is compared with the stress transfer relationship of the surrounding pipes to obtain the stress distribution of the pipeline nodes. A visualization tool is used to generate pipeline node stress diagram data, clearly displaying the stress intensity at each node, providing a foundation for subsequent analysis. Data such as fluid flow rate, flow velocity, and temperature are collected from the pipeline network. This data helps infer the fluid state within the pipeline. An internal pressure inversion model is established, combining the pipeline node stress diagram data with the pipeline network flow data to calculate the internal pressure through inversion calculation. The actual pressure within the pipeline is estimated using the inversion method, taking into account fluid dynamics and the interaction between the fluid and the pipe wall, to obtain the internal pressure distribution data. A time series comparison of the internal pressure data with the pipeline network flow data is performed to analyze the pressure change trend and the difference in flow volume, generating pressure time series deviation data. This step reveals abnormal fluctuations in pipeline pressure over time. The pressure time series deviation data is combined with the equivalent stress value of the pipe wall for threshold discrimination. By setting a threshold, the relationship between pressure deviation and stress is determined, identifying potential pipeline anomalies. Based on the identification results, abnormal pressure detection data of the pipeline network is generated to identify pipeline areas with problems (such as local pressure anomalies, pipeline damage, etc.), providing a decision-making basis for further pipeline maintenance and monitoring.

[0136] Preferably, step S33 includes the following steps:

[0137] Step S331: reconstructing the mesh of the pipe wall equivalent stress data to generate meshed pipe wall stress data;

[0138] Step S332: performing spatial projection on the pipe wall gridded stress data to generate stress space mapping data;

[0139] Step S333: performing node fusion on the stress space mapping data and the pipeline topology network to generate initial node stress data; performing directional tensor decomposition on the initial node stress data to generate node principal stress vector data;

[0140] Step S334: Perform full-graph fusion and connectivity weighting on the node principal stress vector data to generate pipeline node stress graph data.

[0141] In an embodiment of the present invention, the pipe wall equivalent stress data is grid-reconstructed by selecting an appropriate gridding technology (for example, the finite element method, the triangulation method, or the hexahedral grid method). This step requires ensuring that the grid is sufficiently fine to ensure the accuracy of the stress data at each node. According to the geometric shape of the pipeline and the actual situation of the pipe wall, the equivalent stress data is divided into grid nodes using a gridding algorithm. A stress value is obtained at each grid node, which is obtained by interpolation and reconstruction from the original pipe wall equivalent stress data. The pipe wall gridded stress data is generated by the stress value of each grid node obtained after grid reconstruction, and data is prepared for subsequent spatial projection and node fusion. A spatial projection model of the pipeline is established. Considering the three-dimensional shape of the pipeline, it is necessary to select a suitable spatial mapping method to map the gridded stress data to the actual three-dimensional space of the pipeline. The gridded stress data is mapped to the three-dimensional space of the pipeline using a projection method (such as polynomial fitting, principal component analysis, etc.). In this process, it is necessary to maintain the spatial distribution characteristics of the stress data in the pipeline to reflect the real physical phenomenon. After spatial projection, the data represents the stress distribution at different spatial points within the pipeline, forming stress space mapping data, which provides the necessary input for subsequent node fusion. Based on the pipeline's topological structure, the stress space mapping data is fused with the pipeline's topological network. Using node correspondences, the spatial stress data is mapped to each node in the pipeline to generate initial node stress data. This step requires correctly associating stress data with nodes based on the pipeline's connectivity (such as pipeline branches and connection points). Directional tensor decomposition is performed on the initial node stress data. This can be achieved by extracting the direction and magnitude of the principal stresses at the node through eigenvalue decomposition of the stress tensor or principal stress calculation methods. The result of the tensor decomposition is node principal stress vector data, which reflects the magnitude and direction of stress at each pipeline node in different directions. Each node receives a principal stress vector, representing the node's stress response along different directions in space. This data provides a directional basis for further analysis of the stress state of the pipeline node. The principal stress vector data for all nodes are then fully fused. By merging all node data in the pipeline topology network, using global optimization methods (such as least squares method, weighted average method, etc.), and combining the stress data of each node, a global node stress distribution model is obtained. During the graph fusion process, the connectivity of the pipeline network is taken into account. For interconnected nodes, the strength of the connection should be weighted to reflect the degree of stress transfer between nodes. This can be achieved through the weighted edge algorithm in graph theory, which assigns different weights to the connections based on the relative position and stress transfer relationship between the nodes. Through full graph fusion and connectivity weighting, the node stress graph data of the pipeline is finally generated. This graph data can intuitively display the stress status of each node in the pipeline network, helping to identify high-stress sections in the pipeline and their damage risks.

[0142] Preferably, the combined threshold discrimination processing of the pressure time series deviation data and the pipe wall equivalent stress value in step S35 includes:

[0143] When any of the following conditions occurs, it is determined to be a sudden pressure fluctuation abnormality and the sudden pressure fluctuation abnormality data will be obtained: the pressure change rate exceeds 0.5MPa / min within any 5 minutes; the single point pressure value increases or decreases by more than 1.2MPa within 10 minutes; the pressure fluctuation frequency is greater than 0.8Hz and lasts for more than 15 minutes;

[0144] When the following conditions occur simultaneously, it is determined to be a periodic abnormal pressure fluctuation and the periodic pressure fluctuation abnormal data is obtained: the pressure peak deviation within adjacent monitoring cycles exceeds ±20%; the peak / trough time interval change rate within three consecutive cycles exceeds ±25%; after comparison with the historical baseline waveform, the dynamic time regularization deviation exceeds 10%;

[0145] When the following conditions are met at the same time, it is determined that the pipe wall equivalent stress exceeds the limit abnormality and the equivalent stress exceedance abnormality data is obtained: the pipe wall equivalent stress value exceeds 80% of the design material yield strength, that is, exceeds 160MPa, where the design material yield strength limit is 200MPa; the stress concentration factor is higher than 2.5; the equivalent stress sudden increase rate exceeds 15MPa / 10min within any 30-minute window, and the abnormal section length exceeds 20 meters;

[0146] Integrate the abnormal data of sudden pressure fluctuation, abnormal data of periodic pressure fluctuation and abnormal data of equivalent stress exceeding the limit, align the spatial position and time stamp, and generate abnormal pressure detection data of the pipeline network.

[0147] As an example of the present invention, refer to Figure 3 As shown, in this example, step S4 includes:

[0148] Step S41: Analyze the spatial coupling of abnormal pressure detection data of the pipe network to generate abnormal node screening data; extract topological paths from the abnormal node screening data;

[0149] Step S42: identifying components of the pipeline topology network according to the extracted topological path to generate pipeline network fitting data; performing bidirectional fluid-structure coupling modeling on the pipeline network fitting data to generate water hammer effect structural response data;

[0150] Step S43: extracting the time domain characteristics of the water hammer effect structural response data to obtain the water hammer coupled pulse pressure peak; performing joint positioning processing on the water hammer coupled pulse pressure peak and the abnormal node screening data to generate abnormal pressure area data of the pipeline network;

[0151] Step S44: Adaptive monitoring deployment processing is performed based on the abnormal pressure area data of the pipeline network to realize automatic monitoring of the pipeline network pressure.

[0152] In an embodiment of the present invention, a spatial coupling model for abnormal pressure data in a pipeline network is established based on the pipeline network's topological structure and the spatial distribution of pressure data. This model considers the mutual influence of each node and connected pipe in the pipeline network and analyzes the propagation characteristics of abnormal pressure data within the network. By analyzing the relationship between abnormal pressure and adjacent nodes, the coupling coefficient between each node is calculated, reflecting the transmission intensity and spread range of the abnormal pressure. Common methods include correlation analysis and covariance matrix calculation. Based on the results of the spatial coupling analysis, nodes with large abnormal pressure fluctuations in the coupling relationship are screened to generate abnormal node screening data. These nodes are typically the areas with the most significant pressure anomalies in the pipeline network. Within the pipeline topological network, paths from one abnormal node to other nodes are defined, with a focus on the connectivity paths between abnormal nodes. A shortest path algorithm from graph theory (such as the Dijkstra algorithm) is used to extract topological paths, ensuring that the extracted paths reflect the propagation trend of the abnormal pressure. Path extraction requires consideration of pipeline connectivity and inter-node distances. The extracted topological paths are analyzed to assess the propagation path and impact range of the abnormal pressure, providing data support for subsequent component identification and water hammer effect modeling. Based on the topological path, key components in the pipeline system are identified, including pipe segments, valves, joints, and brackets. These components are essential to the pipeline system and directly affect water flow and pressure fluctuations. Each component in the pipeline network is classified, and pipeline fitting data is generated. This data, including component geometry, material properties, and connection relationships, facilitates subsequent fluid-structure interaction analysis and water hammer modeling. A bidirectional fluid-structure coupling model is established based on the pipeline network fitting data. This model considers the interaction between fluid pressure fluctuations and the pipeline structure, particularly the impact of rapid fluid changes on the pipeline structure during water hammer. Sudden changes in water flow (such as water hammer caused by valve closure or pump station startup) are simulated in the model to calculate the impact of water hammer on the pipeline structure. During the fluid-structure interaction modeling process, CFD (computational fluid dynamics) and FEA (finite element analysis) are co-simulated. Based on the simulation results of the bidirectional fluid-structure interaction model, response data of the pipeline structure under water hammer is obtained, including deformation, vibration, and stress changes. This data provides detailed structural response information for subsequent water hammer analysis. Time-domain features are extracted from the structural response data of the water hammer effect, focusing on the fluctuations of signals such as pressure, displacement, and acceleration. Common methods include short-time Fourier transform (STFT) and wavelet transform. Based on the time-domain features, the pulse pressure peak in the water hammer effect is identified. This pressure peak usually occurs at the moment of sudden flow rate change or sudden stop of the pipeline and is the main impact of the water hammer effect on the pipeline structure. Through time-domain analysis, the peak value of the water hammer coupled pulse pressure is calculated and used as an important indicator for water hammer effect analysis, further used to locate abnormal pressure areas in the pipeline network.Water hammer-coupled pulse pressure peaks are combined with data from abnormal node screening to identify the spatial relationship between the pipeline network areas where the pulse pressure peaks occur and the abnormal nodes. This combined analysis locates areas within the pipeline network affected by water hammer and experiencing abnormal pressure. These areas are potential fault points due to factors such as weak structures and improper connections. Based on the combined location results, abnormal pressure area data for the pipeline network is generated. This data includes the coordinates of the abnormal pressure area, the impact range, and the degree of pressure fluctuation, providing a foundation for subsequent monitoring and maintenance. Based on the abnormal pressure area data, an adaptive monitoring point deployment plan is designed. Monitoring points should cover the abnormal pressure area and be able to collect real-time data such as pressure, flow, and temperature. A dynamic monitoring point adjustment mechanism is established to automatically adjust the location and frequency of monitoring points based on real-time monitoring data to maximize monitoring effectiveness in critical areas and potential risk points. Installed sensors collect real-time pressure data from the pipeline network and analyze it in real time using a data processing and analysis system to identify abnormal pressure fluctuations. When the system detects abnormal pressure values ​​or water hammer, it automatically triggers warning and response mechanisms, including notifying pipeline maintenance personnel and initiating emergency response procedures. In the event of an anomaly, the system automatically adjusts the pressure and flow of the pipe network according to pre-set rules to reduce the impact of water hammer on the pipeline. Through the adaptive monitoring system, the pressure control strategy of the pipe network is continuously optimized to avoid excessive pressure on the pipe structure and unnecessary water hammer effects.

[0153] It is particularly important that the combined positioning processing of the water hammer coupled pulse pressure peak and the abnormal node screening data in step S43 further includes:

[0154] Reconstruct the spatiotemporal distribution of the water hammer coupled pulse pressure peak data to generate the pressure peak spatiotemporal map data;

[0155] Perform topological neighborhood expansion on abnormal node screening data to generate abnormal node expansion area data;

[0156] Overlay analysis of pressure peak spatiotemporal graph data and abnormal node expansion area data to generate pressure fluctuation area data;

[0157] The intersection analysis of the pressure fluctuation area data and the pipeline topology network is performed to generate the abnormal pressure area data of the pipeline network.

[0158] In this embodiment of the present invention, data on water hammer coupled pulse pressure peaks is collected, including timestamps, peak pressures, and node locations. Using spatiotemporal interpolation techniques, such as bilinear interpolation and kriging interpolation, the peak pressure data is reconstructed to generate a spatiotemporal graph encompassing both temporal and spatial dimensions. Spatial interpolation fills in areas where sensor data is missing, while temporal interpolation accurately reconstructs the distribution of peak pressures at different time points. The reconstructed data forms a spatiotemporal graph, where the abscissa represents time, the ordinate represents spatial location (node ​​or pipeline segment), and the data points represent the intensity of the peak pressures. This spatiotemporal graph visually demonstrates the temporal evolution and spatial expansion of peak pressures. Based on the pipeline topology, a neighborhood range is defined for each node. This neighborhood range can be defined based on distance, connectivity, or flow path. By setting an extension range, the impact of an abnormal node on its neighboring nodes is determined. The impact range can be a fixed distance (e.g., the length of a pipeline segment) or dynamically adjusted based on the intensity of the pressure fluctuations and the coupling relationship. A neighborhood extension rule is applied to the abnormal node screening data, and the expanded area represents the area affected by the abnormal pressure. These areas include the abnormal node and the affected areas around it. Based on topological neighborhood expansion analysis, abnormal node expansion area data is generated. This data includes the neighborhood range of each abnormal node, the boundaries of the expansion area, and all affected nodes or pipeline sections within the area. The generated abnormal node expansion area data is stored in a database, and the dynamic changes of each expansion area are recorded in conjunction with time information for subsequent analysis. Spatiotemporal overlay rules are defined, primarily combining the pressure peak spatiotemporal graph data with the abnormal node expansion area data based on temporal and spatial location. The goal of the overlay analysis is to identify areas with both pressure fluctuations and abnormal node expansion. By calculating the spatiotemporal overlap between the pressure peak spatiotemporal graph and the abnormal node expansion area, areas experiencing significant pressure fluctuations and impacting the topological neighborhood are identified. These areas are considered pressure fluctuation areas in the pipeline network. After the overlay analysis is completed, pressure fluctuation area data is identified. These areas are typically where significant pressure fluctuations occur in the pipeline network due to water hammer or other factors. The identified pressure fluctuation area data is stored, including the spatial location, impact range, and pressure fluctuation intensity. By performing an intersection analysis between the pressure fluctuation area data and the pipeline topology, we identify which pipeline segments, nodes, or areas are located within both the pressure fluctuation area and the pipeline topology. This intersection analysis ensures that only areas affected by water hammer are considered. Using geometric calculations or graph theory-based intersection algorithms, we determine the intersection of the pressure fluctuation area and the pipeline topology. These intersections represent potential fault areas in the pipeline network affected by water hammer. Based on the results of the intersection analysis, we identify and mark areas in the pipeline network affected by abnormal pressure. These areas are typically pipeline segments or nodes where water hammer causes significant pressure fluctuations.The generated abnormal pressure area data of the pipe network is stored as data for visualization or analysis, including information such as the pipe segment number, node number, and pressure fluctuation degree.

[0159] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0160] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present 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 present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for automatically monitoring data processing of pipe network pressure, characterized in that: The following steps are involved: Step S1: Obtaining pipe network structure data; constructing a pipe topology network based on the pipe network structure data to generate a pipe topology network; screening the main pipes and branches in the pipe topology network to obtain pipe network flow data; Step S2: Based on the pipeline network flow data, microwave resonators are deployed on the pipe walls of the main pipeline and branch pipes, and the deployed microwave resonators are used to capture the pipeline circumferential deformation harmonics in real time; the longitudinal wave propagation delay of the pipeline network flow data is analyzed, and the dynamic resonance spectrum of the pipe body structure is constructed in combination with the pipeline circumferential deformation harmonics; Step S3: Calculating the internal pressure and the equivalent stress of the pipe wall of the pipe topology network using the dynamic resonance spectrum of the pipe structure to obtain the internal pressure value and the equivalent stress value of the pipe wall; and performing abnormal pressure determination on the pipe network flow data based on the internal pressure value and the equivalent stress value of the pipe wall to obtain abnormal pressure detection data of the pipe network; Step S4: Screen the pipe fittings of the pipeline topology network based on the abnormal pressure detection data of the pipeline network to obtain the pipeline network pipe fitting data; analyze the bidirectional fluid-solid coupling of the pipeline network pipe fitting data to obtain the water hammer coupling pulse pressure peak; accurately locate the abnormal pipeline network pressure area in the pipeline topology network through the abnormal pressure detection data of the pipeline network and the water hammer coupling pulse pressure peak, so as to realize the automatic monitoring operation of the pipeline network pressure.

2. The method for automatically monitoring data processing of pipe network pressure according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: obtaining an original engineering drawing of the pipe network and extracting pipe network structure information in the original engineering drawing of the pipe network to obtain pipe network structure data; Step S12: performing node connectivity analysis on the pipe network structure data to generate pipe topology network data; Step S13: clustering the flow paths of the pipeline topology network data to generate candidate trunk path data; Step S14: performing path weight determination on the candidate trunk path data, and dividing the candidate trunk path data into trunk pipelines and branches according to the determination result, to obtain trunk and branch division data; Step S15: extracting the circulation logic of the trunk and branch pipe division data, thereby generating pipe network circulation data.

3. The method for automatically monitoring data processing of pipe network pressure according to claim 2, characterized in that: Step S14 includes the following steps: Step S141: performing a path weight determination on the candidate trunk path data to obtain a determination result, wherein the path weight includes the geometric length of the path, the flow demand on the path, and the pressure demand on the path; Step S142: When the following conditions are simultaneously present, the candidate trunk path data is determined as trunk pipeline partition data: the geometric length of the path is between 500 meters and 5000 meters, the flow demand on the path is between 50 cubic meters / hour and 1000 cubic meters / hour, and the pressure demand on the path is between 0.5 MPa and 5 MPa; Step S143: When any of the following conditions occurs, the candidate trunk path data is determined to be branch partitioning data: the geometric length of the path is less than 500 meters, the flow demand on the path is less than 50 cubic meters / hour, and the pressure demand on the path is less than 0.5 MPa or greater than 5 MPa; Step S144: Integrate the trunk pipeline division data and the branch pipeline division data into trunk and branch pipeline division data.

4. The method for automatically monitoring data processing of pipe network pressure according to claim 1, characterized in that: In step S2, deploying microwave resonators on the main pipeline and branch pipes based on the pipe network flow data includes: Screen key nodes of pipeline network circulation data; Map key nodes into trunk and branch segments to generate segmented deployment unit data; Analyze the waveguide adaptability of the segmented deployment unit data, and optimize the multi-point frequency distribution of the segmented deployment unit data based on the waveguide adaptability to generate resonator configuration solution data; Performing position calibration on the resonator configuration scheme data to generate microwave resonator deployment parameter data; The microwave resonator is deployed on the pipe wall according to the microwave resonator deployment parameter data, thereby obtaining the deployed microwave resonator.

5. The method for automatically monitoring data processing of pipe network pressure according to claim 1, characterized in that: The analysis of the longitudinal wave propagation delay of the pipe network flow data in step S2 includes: Perform segmented flow velocity fitting on the pipe network flow data to generate segment flow velocity data; Couple the sound velocity of the flow velocity data within the calculation section to obtain the medium sound velocity distribution data; Perform topological path mapping on the medium sound velocity distribution data based on the pipe network circulation data to generate sound wave propagation path diagram data; Calculate the propagation delay integral of the acoustic wave propagation path diagram data to generate initial longitudinal wave propagation delay data; Detect the drift anomaly of the longitudinal wave propagation delay data, and thus obtain the longitudinal wave propagation delay of the pipeline network flow data.

6. The method for automatically monitoring data processing of pipe network pressure according to claim 1, characterized in that: In step S2, the dynamic resonance spectrum of the pipe structure is constructed by combining the harmonics of the circumferential deformation of the pipe, including: Synchronously calibrate the longitudinal wave propagation delay data and the pipeline circumferential deformation harmonics to generate time-frequency joint benchmark data; Extract the resonance response characteristics of the time-frequency joint benchmark data; Map the pipeline structure through the resonance response characteristics to generate structural resonance distribution data; Perform dynamic energy clustering analysis on the structural resonance distribution data to generate dynamic resonance clustering data; The dynamic resonance spectrum of the pipe structure is constructed based on the structural resonance distribution data, dynamic resonance clustering data and resonance response characteristics.

7. The method for automatically monitoring data processing of pipe network pressure according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing frequency inversion on the dynamic resonance spectrum of the pipe structure to generate resonance frequency-structure coupling data; Step S32: Calculate the stress of the resonance frequency-structure coupling data to obtain the equivalent stress value of the pipe wall; Step S33: performing stress distribution mapping on the pipeline topology network according to the equivalent stress value of the pipe wall to generate pipeline node stress diagram data; Step S34: performing internal pressure inversion calculation on the pipeline node stress diagram data in combination with the pipeline network flow data to generate the pipeline internal pressure value; Step S35: Perform time series comparison analysis on the internal pressure value data of the pipeline and the pipe network flow data to generate pressure time series deviation data; perform joint threshold discrimination processing on the pressure time series deviation data and the pipe wall equivalent stress value to generate pipe network abnormal pressure detection data.

8. The method for automatically monitoring data processing of pipe network pressure according to claim 7, characterized in that: Step S33 includes the following steps: Step S331: reconstructing the mesh of the pipe wall equivalent stress data to generate meshed pipe wall stress data; Step S332: performing spatial projection on the pipe wall gridded stress data to generate stress space mapping data; Step S333: performing node fusion on the stress space mapping data and the pipeline topology network to generate initial node stress data; performing directional tensor decomposition on the initial node stress data to generate node principal stress vector data; Step S334: Perform full-graph fusion and connectivity weighting on the node principal stress vector data to generate pipeline node stress graph data.

9. The method for automatically monitoring data processing of pipe network pressure according to claim 7, characterized in that: In step S35, the combined threshold discrimination processing of the pressure time series deviation data and the pipe wall equivalent stress value includes: When any of the following conditions occurs, it is determined to be a sudden pressure fluctuation abnormality and the sudden pressure fluctuation abnormality data will be obtained: the pressure change rate exceeds 0.5MPa / min within any 5 minutes; the single point pressure value increases or decreases by more than 1.2MPa within 10 minutes; the pressure fluctuation frequency is greater than 0.8Hz and lasts for more than 15 minutes; When the following conditions occur simultaneously, it is determined to be a periodic abnormal pressure fluctuation and the periodic pressure fluctuation abnormal data is obtained: the pressure peak deviation within adjacent monitoring cycles exceeds ±20%; the peak / trough time interval change rate within three consecutive cycles exceeds ±25%; after comparison with the historical baseline waveform, the dynamic time regularization deviation exceeds 10%; When the following conditions are met at the same time, it is determined that the pipe wall equivalent stress exceeds the limit abnormality and the equivalent stress exceedance abnormality data is obtained: the pipe wall equivalent stress value exceeds 80% of the design material yield strength, that is, exceeds 160MPa, where the design material yield strength limit is 200MPa; the stress concentration factor is higher than 2.5; the equivalent stress sudden increase rate exceeds 15MPa / 10min within any 30-minute window, and the abnormal section length exceeds 20 meters; Integrate the abnormal data of sudden pressure fluctuation, abnormal data of periodic pressure fluctuation and abnormal data of equivalent stress exceeding the limit, align the spatial position and time stamp, and generate abnormal pressure detection data of the pipeline network.

10. The method for automatically monitoring data processing of pipe network pressure according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Analyze the spatial coupling of abnormal pressure detection data of the pipe network to generate abnormal node screening data; extract topological paths from the abnormal node screening data; Step S42: identifying components of the pipeline topology network according to the extracted topological path to generate pipeline network fitting data; performing bidirectional fluid-structure coupling modeling on the pipeline network fitting data to generate water hammer effect structural response data; Step S43: extracting the time domain characteristics of the water hammer effect structural response data, thereby obtaining the water hammer coupled pulse pressure peak; Combined positioning processing is performed on the water hammer coupled pulse pressure peak and abnormal node screening data to generate abnormal pressure area data of the pipeline network; Step S44: Adaptive monitoring deployment processing is performed based on the abnormal pressure area data of the pipeline network to realize automatic monitoring of the pipeline network pressure.

Images