A method, device and medium for locating a leakage point of a water supply network

Abstract

The application discloses a kind of leakage point positioning method, equipment and medium of water supply network, belong to water supply network operation and leakage control technical field, for solving in existing leakage point positioning, it is easy to rely on single data, equipment and algorithm complex, and also lack high-precision space linkage and to data adaptability and insufficient refinement, it is difficult to realize the technical problems of accurate positioning of water leakage point of water supply network.Method includes: the operating state of water supply network is processed to multi-source data acquisition, obtains water supply network core data;The standardization processing of feature vector is carried out to the corrected water supply network core data after pre-processing, obtains effective water supply network data;Effective water supply network data is screened under the risk value of leakage point area about leakage point, obtains high suspected leakage point area based on water supply network section;Leakage point spatial positioning calculation is carried out to high suspected leakage point area under local topology, obtains the final leakage point area position in water supply network grid.

Description

Technical Field

[0001] This application relates to the field of water supply network operation and maintenance and leakage control technology, and in particular to a method, equipment and medium for locating leaks in water supply networks. Background Technology

[0002] Currently, urban water supply networks (covering tens of thousands to millions of square meters) commonly face leakage problems. Statistics show that the leakage rate in some cities exceeds 15%, causing not only serious waste of water resources but also increasing the operating costs of water supply companies and the difficulty of network maintenance. Existing leak location technologies mainly have the following shortcomings:

[0003] 1. Reliance on single data: Most technologies rely solely on pressure or flow rate data to identify leaks, which is susceptible to fluctuations in water usage and equipment errors, resulting in low location accuracy (usually above 200 meters) and difficulty in narrowing down the search area;

[0004] 2. Complex equipment and algorithms: Some technologies require the deployment of dense sensors or the use of complex algorithms such as LSTM, resulting in high equipment costs and difficult operation, making them unsuitable for small and medium-sized water supply enterprises or old pipe networks;

[0005] 3. Lack of high-precision spatial linkage: Without combining high-precision spatial information of the pipeline network (such as precise coordinates of the pipeline and three-dimensional position of the joint) with micro-topographic data, it is impossible to accurately locate the specific location of the leak. The positioning accuracy is mostly above 50 meters, and a lot of on-site investigation work is still required.

[0006] 4. Insufficient data adaptability and detail: In actual engineering, although the pipeline monitoring data includes pressure gauges and graded water meters, the equipment deployment density is low, the data sampling frequency is insufficient, and the local topology and pressure gradient of the pipeline network are not analyzed in detail, making it difficult to achieve positioning accuracy of 10 meters.

[0007] 5. Weak connection between on-site verification: The existing technical positioning results lack precise connection with on-site detection methods (such as acoustic detection and ground penetrating radar), which cannot directly guide the detection equipment to quickly focus on the core area of ​​the leak. Summary of the Invention

[0008] This application provides a method, device, and medium for locating leaks in a water supply network, which solves the following technical problems: In existing leak location methods, it is easy to rely on single data, the equipment and algorithms are complex, and there is a lack of high-precision spatial linkage and insufficient data adaptability and refinement, making it difficult to accurately locate leaks in the water supply network.

[0009] The embodiments of this application adopt the following technical solutions:

[0010] On one hand, this application provides a method for locating leaks in a water supply network, including: collecting and processing multi-source data on the operating status of the water supply network to obtain core data of the water supply network; preprocessing the core data of the water supply network and standardizing the feature vectors of the preprocessed core data of the water supply network to obtain effective water supply network data; performing preliminary screening of leak areas under relevant leak risk values ​​on the effective water supply network data to obtain high-suspected leak areas based on water supply network sections; constructing a GIS water supply network association model based on water supply network GIS data; and performing spatial location calculation of leaks in the high-suspected leak areas under local topology through the GIS water supply network association model to obtain the final location of the leak area in the water supply network grid.

[0011] This application's embodiment improves leak location accuracy from over 50 meters using traditional methods to within 10 meters through "encrypted data acquisition + high-precision spatial analysis using GIS." This directly guides on-site detection equipment to focus on the core area of ​​the leak, eliminating the need for extensive searching. Furthermore, by simply increasing the deployment of conventional pressure gauges (rather than specialized leak sensors) and enhancing the sampling frequency of smart water meters, the equipment cost is significantly reduced compared to dense sensor solutions, making it affordable for small and medium-sized water supply companies. It is also compatible with water supply networks of different materials and sizes. Through wavelet filtering and multi-dimensional correction, it reduces interference from water usage fluctuations and equipment errors, resulting in high leak identification accuracy.

[0012] In one feasible implementation, multi-source data acquisition and processing are performed on the operating status of the water supply network to obtain core data of the water supply network. Specifically, this includes: collecting pressure data in the water supply network using large-diameter pressure gauges deployed at key nodes and branch sections of the water supply network; acquiring flow data by frequency-based acquisition of real-time flow difference values ​​of the water supply network using multi-level smart water meters deployed in the water supply network; obtaining basic attribute data by acquiring and determining the laying years, materials, pipe diameters, burial depths, joint types, and installation coordinates of the water supply network; collecting terrain information along the pipeline route of the water supply network to obtain micro-topography data; and combining the pressure data, flow data, basic attribute data, and micro-topography data to obtain the core data of the water supply network.

[0013] In one feasible implementation, the core data of the water supply network is preprocessed, specifically including: performing wavelet filtering on the pressure and flow data in the core data of the water supply network to remove error interference, resulting in corrected pressure and flow data; wherein the error interference includes equipment error and instantaneous water usage fluctuation interference; performing on-site correction processing on the basic attribute data of the core data of the water supply network to correct the pipeline coordinate data, resulting in corrected basic attribute data; wherein the on-site correction processing is on-site survey to correct pipeline position deviations in GIS; and combining the corrected pressure data, the corrected flow data, the corrected basic attribute data, and the micro-topography data to obtain the corrected core data of the water supply network.

[0014] In one feasible implementation, the preprocessed modified water supply network core data is subjected to feature vector standardization to obtain effective water supply network data. Specifically, this includes: extracting the daily pressure fluctuation amplitude features, nighttime pressure stability deviation rate features, and local pressure gradient features from the modified pressure data in the modified water supply network core data, and generating pressure features; extracting the nighttime minimum flow features, the proportion of flow difference at each level, and the frequency and duration of flow mutations from the modified flow data in the modified water supply network core data, and generating flow features; performing vector standardization on the pressure features and flow features to obtain pressure feature vectors and flow feature vectors under a unified dimension; and integrating the pressure feature vectors and flow feature vectors with the modified basic attribute data and micro-topographic data through standardized data integration to obtain the effective water supply network data.

[0015] In one feasible implementation, before performing preliminary screening of leak areas based on leak risk values ​​on the effective water supply network data to obtain high-suspected leak areas based on water supply network sections, the method further includes: assigning weights to the pressure feature vectors in the effective water supply network data based on local pressure gradients to obtain pressure feature weights; assigning weights to the flow feature vectors in the effective water supply network data based on the duration of abnormal flow to obtain flow feature weights; performing coefficient superposition processing on the corrected basic attribute data in the effective water supply network data based on various attribute types to obtain basic attribute correction coefficients; wherein, the various attribute types include at least: pipe material age, joint type, pipe material service life, flange joint, and socket; performing coefficient superposition processing on the micro-topography data in the effective water supply network data based on local settlement points and slope parameters to obtain micro-topography correction coefficients; and calculating the risk values ​​of the effective water supply network data under different network areas based on the pressure feature weights, the flow feature weights, the basic attribute correction coefficients, and the micro-topography correction coefficients to obtain the leak risk values.

[0016] In one feasible implementation, the effective water supply network data undergoes preliminary screening of leak areas based on leak risk values ​​to obtain high-suspected leak areas based on water supply network segments. Specifically, this includes: numerically screening the leak risk values ​​for different network areas according to a preset leak risk threshold, and identifying network areas exceeding the leak risk threshold as initial suspected leak areas; extracting local pressure gradient information related to pressure characteristics and nighttime flow information related to flow characteristics from the effective water supply network data; generating local pressure gradient thresholds based on the local pressure gradient information and nighttime flow thresholds based on the nighttime flow information; and performing secondary numerical screening on the initial suspected leak areas using the local pressure gradient thresholds and the nighttime flow thresholds to obtain the high-suspected leak areas based on water supply network segments.

[0017] In one feasible implementation, a GIS water supply network association model is constructed based on the GIS data of the water supply network. Specifically, this includes: importing high-precision spatial data of the network, coordinates of several pressure gauges and several water meters, and micro-topographic data into the ArcGIS Pro system; using the ArcGIS Pro system, dividing all the areas with high suspected leaks into regions under a fixed network grid, and performing data association processing on the pressure anomaly data and flow anomaly data in each grid to generate the GIS water supply network association model.

[0018] In one feasible implementation, the GIS water supply network association model is used to perform spatial location calculations for leaks in the high-suspected leak area under local topology to obtain the final leak area location within the water supply network grid. Specifically, this includes: using the topological relationships in the GIS water supply network association model to trace the location of the network branches containing abnormal data in the high-suspected leak area, and locking the socket joints and pipe positions of the corresponding network grid to obtain first leak location information; using the GIS water supply network association model to calculate the location of pressure gradient changes in adjacent pressure gauges in the high-suspected leak area, determining the abnormal leak grid location, and obtaining second leak location information; calculating the straight-line distance between each network grid in the high-suspected leak area and the nearest joint and / or valve, and based on the risk grid biased by the leak-prone characteristics, obtaining third leak location information; and using the first, second, and third leak location information, marking key detection locations within specific grids in the high-suspected leak area to obtain the final leak area location.

[0019] Secondly, embodiments of this application also provide a device for locating leaks in a water supply network. The device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to execute a method for locating leaks in a water supply network as described in any of the above embodiments.

[0020] Thirdly, embodiments of this application also provide a non-volatile computer storage medium, characterized in that the storage medium is a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium stores at least one program, each program includes instructions, and when the instructions are executed by a terminal, the terminal executes a method for locating leaks in a water supply network as described in any of the above embodiments.

[0021] This application provides a method, equipment, and medium for locating leaks in water supply networks. Compared with existing technologies, the embodiments of this application have the following beneficial technical effects:

[0022] 1. Significantly improved positioning accuracy: Through "encrypted data collection + GIS high-precision spatial refinement analysis", the positioning accuracy of leak points is improved from more than 50 meters in traditional methods to within 10 meters. It can directly guide on-site detection equipment to focus on the core area of ​​the leak point without the need for large-scale investigation.

[0023] 2. Controllable application costs: By simply deploying conventional pressure gauges (instead of professional leak sensors) and increasing the sampling frequency of smart water meters, the equipment cost is significantly reduced compared to dense sensor solutions, making it affordable for small and medium-sized water supply companies.

[0024] 3. Significantly improved efficiency: The accuracy of high-suspected leak areas is reduced to 30-50 meters, and finally located to a 10-meter grid, greatly shortening the on-site search time compared to traditional manual inspection.

[0025] 4. Wide applicability and strong anti-interference: It is compatible with water supply networks of different materials and sizes. Through wavelet filtering and multi-dimensional correction, it reduces water usage fluctuations and equipment error interference, and has a high accuracy rate in leak point identification.

[0026] 5. High applicability: The positioning results can be directly integrated with conventional on-site detection methods such as acoustic detection and ground penetrating radar, without the need for additional special equipment, and can be quickly promoted and applied in the existing pipeline network operation and maintenance system. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0028] Figure 1 A flowchart illustrating a method for locating leaks in a water supply network, as provided in this application embodiment;

[0029] Figure 2 This is a structural schematic diagram of a leak detection device for a water supply network, provided in an embodiment of this application. Detailed Implementation

[0030] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0031] This application provides a method for locating leaks in water supply networks, such as... Figure 1 As shown, the method for locating leaks in a water supply network specifically includes steps S101-S105:

[0032] S101. Perform multi-source data acquisition and processing on the operating status of the water supply network to obtain the core data of the water supply network.

[0033] Specifically, it is necessary to first collect pressure data in the water supply network by deploying large-diameter pressure gauges at key nodes and branch pipe sections.

[0034] Furthermore, by using multi-level smart water meters deployed in the water supply network, the real-time flow difference of the water supply network is collected and processed at frequency to obtain flow data.

[0035] Furthermore, it is necessary to obtain the laying years, materials, pipe diameters, pipe burial depths, joint types, and installation coordinates of the water supply network, and determine them as basic attribute data.

[0036] Furthermore, topographic information is collected along the water supply network to obtain micro-topographic data.

[0037] Furthermore, pressure data, flow data, basic attribute data, and micro-topography data are combined to obtain core data for the water supply network.

[0038] As a feasible implementation method, it is necessary to first collect core data of the water supply network, including: 1) Pressure data: Deploy large-diameter pressure gauges at key nodes and branch pipe sections of the network (density increased to 500 meters / gauge, covering main pipes and important branch pipes), increase the sampling frequency to once / minute, and record abnormal signals such as sudden pressure drops and minor fluctuations (above ±0.02MPa); 2) Flow data: Use first-level (main pipes), second-level (regional branch pipes), and third-level (user-end) smart water meters, increase the sampling frequency to once / 15 minutes, and accurately calculate the real-time flow difference between water meters at each level; 3) Basic attribute data: Obtain the laying years of the network, material (gray cast iron / PE pipe, etc.), pipe diameter, pipe burial depth, joint type (flange / socket, etc.), and accurate installation coordinates (error ≤2 meters); 4) Micro-topography data: Collect micro-topography information along the network (such as local slope, settlement points, and road load distribution).

[0039] In one embodiment, a 1.5 million square meter water supply network in a city is taken as the implementation object. The network includes gray cast iron pipes (laying life of 20-25 years, socket joints) and PE pipes (laying life of 5-10 years, heat fusion joints). 60 large-diameter pressure gauges are densely deployed (density 500 meters / gauge, covering the main pipe and important branch pipes, coordinate accuracy ≤2 meters) and 150 smart water meters (20 first-level water meters, 60 second-level water meters, and 70 third-level water meters, sampling frequency 1 time / 15 minutes). There are 5 local settlement points and 3 road sections with slopes of 15°-20° along the pipeline.

[0040] In one embodiment, 1) Pressure data is collected: Pressure values ​​are collected through 60 encrypted pressure gauges (once per minute), and wavelet filtering is used to remove 5 instantaneous fluctuation data (such as short-term pressure drops caused by fire truck water intake). Features are extracted: daily pressure fluctuation amplitude (mean 0.06 MPa), nighttime pressure stability deviation rate (mean 3%), and local pressure gradient (normal mean 0.0003 MPa / m, abnormal areas reach 0.0008 MPa / m).

[0041] 2) Collect flow data: Collect flow data from 150 smart water meters (once every 15 minutes), calculate the difference between level 1 and level 2 water meters (average 6%), and the difference between level 2 and level 3 water meters (average 9%), and extract features: minimum nighttime flow (average 18 m³ / h), percentage of flow difference (8 areas with a difference exceeding 15% and lasting ≥30 minutes), and frequency of flow change (an average of 1 change caused by a leak per day, lasting 1-2 hours).

[0042] 3) Collect basic attributes and micro-topographic data: Mark gray cast iron pipe sections (correction factor 0.3), socket joints (add 0.15), local settlement points (add 0.2), and sections with a slope of 15°-20° (add 0.1). Pipeline coordinates are corrected by on-site survey, with a deviation of ≤2 meters;

[0043] 4) Perform vector standardization: Convert the pressure and flow characteristics mentioned above into standardized vectors in the range of 0-1 (e.g., a local pressure gradient of 0.0008 MPa / m corresponds to a vector value of 0.9, and an abnormal flow rate lasting for 1 hour corresponds to a vector value of 0.85).

[0044] S102. Preprocess the core data of the water supply network, and then standardize the feature vectors of the preprocessed and corrected core data of the water supply network to obtain effective water supply network data.

[0045] Specifically, the pressure and flow data in the core data of the water supply network are first processed using a wavelet filtering algorithm to remove error interference, resulting in corrected pressure and flow data. The error interference includes equipment errors and fluctuations in instantaneous water usage.

[0046] Furthermore, the basic attribute data in the core data of the water supply network needs to undergo on-site correction of the pipeline coordinate data to obtain corrected basic attribute data. This on-site correction involves conducting field surveys to correct pipeline location deviations in the GIS.

[0047] Furthermore, the corrected pressure data, corrected flow data, corrected basic attribute data, and micro-topography data are combined to obtain the corrected core data of the water supply network.

[0048] As a feasible implementation method, it is also necessary to use wavelet filtering algorithm on pressure and flow data to eliminate interference from equipment errors (such as instrument drift) and instantaneous water usage fluctuations (such as short-term large water usage), while retaining continuous small abnormal signals caused by leaks; to correct pipeline coordinate data, and to correct pipeline position deviations in GIS in conjunction with on-site surveys, ensuring coordinate accuracy ≤2 meters; finally, the corrected core data of the water supply network is obtained.

[0049] Furthermore, it is necessary to extract the daily pressure fluctuation amplitude characteristics, nighttime pressure stability deviation rate characteristics, and local pressure gradient characteristics from the core data of the corrected water supply network, and generate pressure characteristics.

[0050] Furthermore, the minimum nighttime flow characteristics, the proportion of flow difference at each level, and the frequency and duration of flow mutations in the core data of the corrected water supply network are extracted and used to generate flow characteristics.

[0051] Furthermore, the pressure and flow characteristics are vectorized to obtain pressure and flow characteristic vectors under a unified dimension.

[0052] As a feasible implementation method, regarding pressure characteristics, it is necessary to first extract the daily pressure fluctuation range, the deviation rate of the nighttime (23:00-5:00) pressure stability value, and the local pressure gradient (pressure difference between adjacent pressure gauges / pipe length); regarding flow characteristics, it is necessary to extract the minimum nighttime flow rate, the proportion of flow difference at each level, the frequency and duration of flow mutations (flow anomalies caused by leaks usually last ≥30 minutes). Then, the extracted features are subjected to vector standardization to form a pressure feature vector and a flow feature vector with a unified dimension, in which the weight of local pressure gradient and the duration of flow anomalies is increased to 30%.

[0053] Furthermore, the pressure feature vector and flow feature vector are then standardized and integrated with the corrected basic attribute data and micro-topographic data to obtain effective water supply network data.

[0054] S103. Perform preliminary screening of leak areas based on relevant leak risk values ​​on the effective water supply network data to obtain high-suspection leak areas based on water supply network sections.

[0055] Specifically, the pressure feature vector in the effective water supply network data needs to be weighted according to the local pressure gradient to obtain the pressure feature weight. Similarly, the flow feature vector in the effective water supply network data needs to be weighted according to the duration of flow anomalies to obtain the flow feature weight.

[0056] Furthermore, the corrected basic attribute data in the effective water supply network data must be processed by superimposing coefficients based on various attribute types to obtain the basic attribute correction coefficients. Among them, each attribute type includes at least: pipe material age, joint type, pipe material service life, flange joint, and socket plug.

[0057] Furthermore, the micro-topographic data in the effective water supply network data are further processed by superimposing coefficients under relevant local settlement points and slope parameters to obtain micro-topographic correction coefficients.

[0058] Furthermore, based on the pressure characteristic weight, flow characteristic weight, basic attribute correction coefficient, and micro-topography correction coefficient, the risk value of the effective water supply network data under different network areas is calculated to obtain the leakage risk value.

[0059] As a feasible implementation method, a weighted fusion calculation of the leak risk value is required first. That is, a weighted fusion algorithm is used to assign a weight of 0.5 to the standardized pressure feature vector (of which local pressure gradient accounts for 0.2) and a weight of 0.4 to the flow feature vector (of which the duration of abnormal flow accounts for 0.15). A basic attribute correction coefficient is introduced (set according to the pipe material age + joint type: 0.2 for pipes over 15 years old, 0.3 for pipes over 20 years old; 0.1 for flange joints, and 0.15 for socket joints). At the same time, a micro-topography correction coefficient is superimposed (0.2 for local settlement points, and 0.1 for road sections with a slope of more than 15°). The calculation formula is as follows: Leak risk value = pressure feature vector × 0.5 + flow feature vector × 0.4 + basic attribute correction coefficient + micro-topography correction coefficient.

[0060] In one embodiment, the risk value can be calculated using the formula "risk value = pressure vector × 0.5 + flow vector × 0.4 + basic attribute correction coefficient + micro-topography correction coefficient". For example, in a gray cast iron pipe settlement section: pressure vector 0.8 (including local pressure gradient 0.3), flow vector 0.75 (including flow anomaly duration 0.2), basic attribute correction coefficient 0.3 + 0.15 = 0.45, micro-topography correction coefficient 0.2, risk value = 0.8 × 0.5 + 0.75 × 0.4 + 0.45 + 0.2 = 0.4 + 0.3 + 0.45 + 0.2 = 1.35 (exceeding the threshold of 0.8, marked as the initial suspected leak area).

[0061] Furthermore, based on the preset leak risk threshold, the leak risk values ​​in different pipeline areas are numerically screened, and the pipeline areas that exceed the leak risk threshold are identified as the initial suspected leak areas.

[0062] Furthermore, local pressure gradient information related to pressure characteristics and nighttime flow information related to flow characteristics are extracted from the effective water supply network data. Local pressure gradient thresholds based on the local pressure gradient information and nighttime flow thresholds based on the nighttime flow information are then generated.

[0063] Furthermore, by using local pressure gradient thresholds and nighttime flow thresholds, a secondary numerical screening process is performed on the initial suspected leak areas to obtain high-suspected leak areas based on water supply network sections.

[0064] As a feasible implementation method, high-suspection leak areas are further screened out: first, a leak risk threshold (e.g., 0.8) is set, and areas with risk values ​​exceeding the threshold are marked as initial suspected areas; combined with abnormal nighttime flow (minimum nighttime flow exceeds the average of the same area by 1.2 times and lasts for ≥30 minutes) and abnormal local pressure gradient (pressure gradient between adjacent pressure gauges exceeds the normal average of 0.0005 MPa / m), the scope is further narrowed down, and the pipeline section where the leak is located is initially identified, which is to say, the high-suspection leak area based on the water supply pipeline section is initially obtained.

[0065] In one embodiment, by combining the nighttime flow rate (the minimum nighttime flow rate in this area is 22.5 m³ / h, exceeding the average of the same area by 1.2 times and lasting for 45 minutes) with the local pressure gradient (0.0008 MPa / m, exceeding the normal average by 1.67 times), the initial suspected leak area is marked as a high-suspected leak area; for example, a total of 6 high-suspected leak areas were finally selected, with a positioning accuracy of about 40 meters.

[0066] S104. Based on the GIS data of the water supply network, construct a GIS water supply network association model.

[0067] Specifically, high-precision spatial data of the pipeline network, coordinates of several pressure gauges and water meters, and micro-topographic data are imported into the ArcGIS Pro system.

[0068] Furthermore, using the ArcGIS Pro system, all areas with high suspected leaks were divided into regions under a fixed pipe network grid, and the pressure anomaly data and flow anomaly data in each grid were correlated to generate a GIS water supply pipe network correlation model.

[0069] As a feasible implementation method, high-precision spatial data of water supply networks (precise coordinates of pipes, three-dimensional positions of joints / valves, pipe diameter change points, accuracy ≤ 2 meters), installation coordinates of encrypted pressure gauges / smart water meters, and micro-topography data can be imported into a GIS system to construct a "monitoring data - high-precision spatial information - micro-topography" association model (GIS water supply network association model). In the GIS water supply network association model, high-suspection leak areas are divided into 10-meter grids, and each grid is marked with the corresponding pressure and flow anomaly data, thereby completing the overall construction of the above-mentioned GIS water supply network association model.

[0070] In one embodiment, high-precision spatial data of the pipeline network (precise coordinates of the pipeline, three-dimensional positions of 80 joints), coordinates of 60 pressure gauges / 150 water meters, and micro-topographic data can be imported into the ArcGIS Pro system. The system can then divide the network into six high-suspection leak areas using a 10-meter grid, and associate each grid with abnormal pressure and flow data.

[0071] S105. Using the GIS water supply network association model, perform spatial location calculations for leaks in areas with high suspected leaks under local topology to obtain the final location of the leak area in the water supply network grid.

[0072] Specifically, the topological relationships in the GIS water supply network association model are first used to trace the location of the abnormal data in the network branches in the high-suspected leak area, and the socket joints and pipe locations of the corresponding network grid are locked to obtain the first leak location information.

[0073] Furthermore, by using the GIS water supply network association model, the location of pressure gradient changes in adjacent pressure gauges in areas with high suspected leaks is calculated to determine the location of the abnormal grid of the leak and obtain the second leak location information.

[0074] Furthermore, for each pipe network grid in the high-suspected leak area, the straight-line distance to the nearest joint and / or valve is calculated, and the risk grid is biased based on the leak-prone characteristics, to obtain the third leak location information.

[0075] As a feasible implementation method, in the local topology analysis of high-suspected leak areas, the specific pipe segments of the network branches where abnormal pressure / flow occurs can be traced based on the topological relationships of the GIS water supply network association model. This identifies 3-5 upstream and downstream joints / valves that the leak may affect, excluding non-associated grids. Then, the pressure gradient back-calculation method is used, which calculates the approximate location of the leak based on the pressure gradient changes between adjacent pressure gauges (the pressure gradient at the leak point will show abrupt changes; the grid where the leak is located can be inferred from the gradient abrupt change point). Next, distance-weighted analysis is performed, which involves calculating the straight-line distance between each 10-meter grid in the high-suspected leak area and the nearest joint / valve. Considering the characteristic that leaks tend to occur near joints (accounting for over 70%), grids within 10 meters of joints are assigned higher weights. In other words, leak location information needs to be comprehensively calculated from three aspects to obtain leak location information under each consideration.

[0076] In one embodiment, during local topology analysis, the branch of the pipeline network where the abnormal data in a high-suspection area is located can be traced first. This identifies three socket joints (J12, J13, J14) and their corresponding two pipe sections (P180, P181) on that branch, excluding other unrelated branch grids. Then, pressure gradient back-calculation can be performed: the pressure gradient between adjacent pressure gauges (Y25, Y26) in this area abruptly changes from 0.0003 MPa / m to 0.0008 MPa / m. The abrupt change point is located 10 meters from Y26 in the grid (G18-2). Finally, distance-weighted analysis is performed: grid G18-2 is only 5 meters from joint J13, so it is assigned the highest weight and identified as the core location grid, i.e., the grid with a high suspicion of a leak area.

[0077] Furthermore, based on the location information of the first, second, and third leak points, the high-suspection leak point areas are marked with key detection locations within specific grids to obtain the final leak point location.

[0078] As a feasible implementation method, a GIS visualization interface can be used to combine the above analysis results, that is, to integrate the leak location information under each consideration, thereby outputting the 10-meter grid range where the leak is located, and marking the pipe number, joint type and precise coordinates (error ≤ 5 meters) within the grid; generating a field detection guidance map, clarifying the detection focus within the 10-meter grid (such as joint location, pipe burial depth change), providing accurate positioning guidance for field detection equipment such as acoustic detection and ground penetrating radar, and finally achieving the location of the leak within 10 meters, determining the final leak area location with high precision.

[0079] In one embodiment, the precise coordinates (X: 123456.78, Y: 98765.43, error ≤ 5 meters) of the core grid G18-2 are finally output by GIS, and the pipe P181 (gray cast iron pipe, socket joint J13) within the grid is marked. A field inspection guidance map is generated, which clarifies that the focus of the detection is the J13 joint and the surrounding 10-meter range, thus achieving the determination of the final leak location area with high precision.

[0080] In one embodiment, an acoustic detector (accuracy ±3 meters) can be used to detect the eight core grids of six high-suspection areas at specific leak locations. All eight locations accurately identified leak points, with six of them located at the joints (consistent with the weight analysis), achieving an accuracy of 100%. Furthermore, the actual location of the detected leak points deviated from the center of the GIS positioning grid by a maximum of 8 meters, a minimum of 3 meters, and an average of 5 meters, fully meeting the accuracy requirement of less than 10 meters mentioned in this application.

[0081] In addition, this application embodiment also provides a device for locating leaks in water supply networks, such as... Figure 2 As shown, the water supply network leak location device 200 specifically includes:

[0082] At least one processor 201; and a memory 202 communicatively connected to the at least one processor 201; wherein the memory 202 stores instructions executable by the at least one processor 201 to enable the at least one processor 201 to execute:

[0083] Multi-source data acquisition and processing are performed on the operating status of the water supply network to obtain core data of the water supply network;

[0084] The core data of the water supply network is preprocessed, and the preprocessed and corrected core data of the water supply network is then standardized by feature vector processing to obtain effective water supply network data.

[0085] Preliminary screening of leak areas based on relevant leak risk values ​​is performed on effective water supply network data to obtain high-suspection leak areas based on water supply network sections.

[0086] Based on the GIS data of the water supply network, a GIS water supply network association model was constructed.

[0087] By using the GIS water supply network association model, the spatial location calculation of leaks in areas with high suspected leaks is performed under local topology to obtain the final location of the leak area in the water supply network grid.

[0088] This application's embodiment improves leak location accuracy from over 50 meters using traditional methods to within 10 meters through "encrypted data acquisition + high-precision spatial analysis using GIS." This directly guides on-site detection equipment to focus on the core area of ​​the leak, eliminating the need for extensive searching. Furthermore, by simply increasing the deployment of conventional pressure gauges (rather than specialized leak sensors) and enhancing the sampling frequency of smart water meters, the equipment cost is significantly reduced compared to dense sensor solutions, making it affordable for small and medium-sized water supply companies. It is also compatible with water supply networks of different materials and sizes. Through wavelet filtering and multi-dimensional correction, it reduces interference from water usage fluctuations and equipment errors, resulting in high leak identification accuracy.

[0089] This application provides a distributed deployment-based memory caching method, device, and medium. By providing a unified cache access interface, business code only needs to interact with the cache interface to read and write cached data, without needing to concern itself with the internal logic of the cache interface, greatly simplifying the calling method. At the same time, by utilizing the access interface of the cache component area and Redis's own publish-subscribe mechanism, the update of memory cached data in the software application server is realized, and the accuracy and full utilization of memory cached data in the software application are also guaranteed, improving the access capability and response speed of the software application, and enhancing the user experience.

[0090] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0091] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0092] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0094] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0095] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0096] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0097] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0098] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0099] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0100] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for locating leaks in a water supply network, characterized in that, The method includes: Multi-source data acquisition and processing are performed on the operational status of the water supply network to obtain core data of the water supply network, specifically including: Pressure data in the water supply network is collected by large-diameter pressure gauges deployed at key nodes and branch pipe sections of the water supply network. By deploying multi-level smart water meters in the water supply network, the real-time flow difference of the water supply network is collected and processed at frequency to obtain flow data; Obtain the laying years, material, pipe diameter, pipe burial depth, joint type and installation coordinates of the water supply network, and determine them as basic attribute data; Topographic information is collected along the water supply network to obtain micro-topographic data; The pressure data, flow data, basic attribute data, and micro-topography data are combined to obtain the core data of the water supply network. The core data of the water supply network is preprocessed, and the preprocessed and corrected core data of the water supply network is standardized by feature vector processing to obtain effective water supply network data. The pressure feature vector in the effective water supply network data is weighted according to the relevant local pressure gradient to obtain the pressure feature weights. The flow feature vector in the effective water supply network data is weighted according to the duration of flow anomalies to obtain the flow feature weights. The corrected basic attribute data in the effective water supply network data are processed by superimposing coefficients based on various attribute types to obtain the basic attribute correction coefficients; wherein, the various attribute types include at least: pipe material age, joint type, pipe material service life, flange joint, and socket plug. The micro-topography data in the effective water supply network data is processed by superimposing coefficients under relevant local settlement points and slope parameters to obtain micro-topography correction coefficients. Based on the pressure characteristic weight, the flow characteristic weight, the basic attribute correction coefficient, and the micro-topography correction coefficient, the risk value of the effective water supply network data under different network areas is calculated to obtain the leakage risk value. The valid water supply network data is subjected to preliminary screening of leak areas based on relevant leak risk values ​​to obtain high-probability leak areas based on water supply network sections, specifically including: Based on the preset leak risk threshold, the leak risk values ​​in different pipeline areas are numerically filtered, and the pipeline areas that exceed the leak risk threshold are identified as initial suspected leak areas. Extract local pressure gradient information of pressure characteristics and nighttime flow information of flow characteristics from the effective water supply network data; and generate local pressure gradient thresholds based on the local pressure gradient information and nighttime flow thresholds based on the nighttime flow information. The initial suspected leak area is subjected to secondary numerical screening using the local pressure gradient threshold and the nighttime flow threshold to obtain the high suspected leak area based on the water supply network section. Based on GIS data of the water supply network, a GIS-based water supply network association model is constructed, which includes: Import high-precision spatial data of the pipeline network, coordinates of several pressure gauges and water meters, and micro-topography data into the ArcGIS Pro system; Using the ArcGIS Pro system, all areas with high suspected leaks are divided into regions under a fixed pipe network grid, and the pressure anomaly data and flow anomaly data in each grid are correlated to generate the GIS water supply network correlation model. Using the GIS water supply network association model, the spatial location calculation of the leak point under the local topology is performed on the high-suspected leak point area to obtain the final location of the leak point area in the water supply network grid.

2. The method for locating leaks in a water supply network according to claim 1, characterized in that, The core data of the water supply network is preprocessed, specifically including: The pressure and flow data in the core data of the water supply network are processed by wavelet filtering algorithm to remove error interference, resulting in corrected pressure and flow data; wherein, the error interference includes: equipment error and instantaneous water consumption fluctuation interference; The basic attribute data in the core data of the water supply network is subjected to on-site correction of the relevant pipeline coordinate data to obtain corrected basic attribute data; wherein, the on-site correction process is to correct the pipeline position deviation in the GIS through on-site survey. The corrected pressure data, the corrected flow rate data, the corrected basic attribute data, and the micro-topography data are combined to obtain the corrected core data of the water supply network.

3. The method for locating leaks in a water supply network according to claim 1, characterized in that, The preprocessed core data of the corrected water supply network is then standardized using feature vectors to obtain effective water supply network data, specifically including: Extract the daily pressure fluctuation amplitude characteristics, nighttime pressure stability deviation rate characteristics, and local pressure gradient characteristics from the core data of the corrected water supply network, and generate pressure characteristics. Extract the nighttime minimum flow characteristics, the proportion of flow difference at each level, and the frequency and duration of flow mutations from the core data of the corrected water supply network, and generate flow characteristics. The pressure features and flow features are vectorized to obtain pressure feature vectors and flow feature vectors under a unified dimension. The pressure feature vector and the flow feature vector are integrated with the corrected basic attribute data and micro-topography data to obtain the effective water supply network data.

4. The method for locating leaks in a water supply network according to claim 1, characterized in that, Using the GIS water supply network association model, spatial location calculations for leaks in the high-suspected leak areas are performed under local topology to obtain the final location of the leak area within the water supply network grid, specifically including: By using the topological relationships in the GIS water supply network association model, the location of the abnormal data in the network branch in the high-suspected leak area is traced, and the location of the socket joint and pipe in the corresponding network grid is locked to obtain the first leak location information. Using the GIS water supply network association model, the location of pressure gradient changes in adjacent pressure gauges in the high-suspected leak area is calculated to determine the abnormal grid location of the leak and obtain the second leak location information. For each pipe network grid in the high-suspected leak area, the straight-line distance to the nearest joint and / or valve is used, and the risk grid biased based on the leak-prone characteristics is used to obtain the third leak location information; Based on the first leak location information, the second leak location information, and the third leak location information, the high-suspected leak area is marked with key detection locations within a specific grid to obtain the final leak area location.

5. A device for locating leaks and drips in a water supply network, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, enabling the at least one processor to perform a method for locating leaks in a water supply network according to any one of claims 1-4.

6. A non-volatile computer storage medium, characterized in that, The storage medium is a non-volatile computer-readable storage medium, which stores at least one program. Each program includes instructions, which, when executed by a terminal, cause the terminal to perform a method for locating leaks in a water supply network according to any one of claims 1-4.

Images