A dynamic positioning method for leakage position of water supply network

Abstract

The application relates to a dynamic positioning method for a leakage position of a water supply network, which comprises the following steps: reading leakage identification data and a pre-constructed water supply network hydraulic simulation model after a real leakage event occurs; estimating a leakage amount of the real leakage event, delimiting an initial candidate leakage area, and calculating a real leakage feature; grouping the candidate leakage area and selecting a feature center pipe section, simulating and calculating a simulated leakage feature at each feature center pipe section, reducing the candidate leakage area according to a similarity index of the simulated leakage feature, and stopping until a reduction ratio reaches a set reduction rate; simulating and calculating a simulated leakage feature of each pipe section in the reduced area, calculating a similarity index of each simulated leakage feature and sorting, and obtaining a pipe section position sorting result reflecting leakage possibility. Compared with the prior art, the result of the application has higher accuracy, can provide a range of the candidate leakage area, has a more comprehensive guiding effect on the investigation process, and has other advantages.

Description

Technical Field

[0001] This invention relates to the field of water supply network leakage management and control, and in particular to a method for dynamically locating leakage points in water supply networks. Background Technology

[0002] With urban development and expansion, the urban water supply pattern is changing rapidly, leading to higher demands on the water supply volume and quality of existing water supply networks. Currently, methods for locating leaks in water supply networks can be mainly divided into two categories: methods based on field equipment and methods based on remote sensors. Methods based on field equipment offer higher accuracy and are more suitable for pinpointing the exact leak point of a burst pipe within a relatively small area. Methods based on remote sensors, supported by advancements in communication technology and computer science, are suitable for preliminary analysis of potentially leaking areas.

[0003] However, methods based on field devices require specialized hardware and on-site operation, resulting in high costs. Leakage location methods based on remote sensors have been extensively studied both domestically and internationally, such as the literature "Robust Data-Driven Leak Localization in Water Distribution Networks Using Pressure Measurements and Topological Information" (Alves, D., Blesa, J., Duviella, E., Rajaoarisoa, L., 2021., Sensors, 21(22), Article 7551). However, most of these studies are based on highly simplified or small-scale benchmark pipe network models, or only use simulated observations to verify the methods. For leakage problems in water supply networks of medium-sized and larger cities (urban population greater than 500,000), there is a lack of case studies and successful applications. One key reason is that larger-scale models often require more time to complete hydraulic simulation and training, leading to more difficult convergence and more uncertainty.

[0004] Because large-scale water supply networks have a large water supply base, leakage problems can have unpredictable impacts on the stable operation of cities. Therefore, there is an urgent need to propose a method based on hydraulic models and monitoring data to quickly and dynamically locate leakage in large-scale water supply networks. This is of great significance for building a comprehensive and high-level urban leakage control system and promoting smart urban water supply management. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the existing technology and provide a method for rapid dynamic location of leakage in large water supply networks based on hydraulic models and monitoring data.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A method for dynamically locating leaks in a water supply network includes the following steps:

[0008] S1: Read leakage identification data of the water supply network and the pre-built hydraulic simulation model of the water supply network after a real leakage event occurs;

[0009] S2: Estimate the leakage amount of the actual leakage event, delineate the initial candidate leakage area in the hydraulic simulation model of the water supply network based on the leakage amount, and calculate the actual leakage characteristics of the actual leakage event;

[0010] S3: Group the candidate leakage areas, select a characteristic center pipe segment for each group, simulate leakage events at each characteristic center pipe segment and calculate the simulated leakage characteristics. Based on the similarity index between the simulated leakage characteristics and the real leakage characteristics, reduce the number of pipes included in the candidate leakage area until the ratio of the number of pipes in the candidate leakage area to the number of pipes in the initial candidate leakage area reaches the set reduction rate. At this time, the candidate leakage area is determined to be a high-risk leakage area.

[0011] S4: Simulate and calculate the simulated leakage characteristics of each pipe segment within the high-risk leakage area, calculate the similarity index between each simulated leakage characteristic and the actual leakage characteristics, and sort them to obtain the pipe segment location ranking result that reflects the possibility of leakage.

[0012] Furthermore, the leakage identification data in step S1 includes the identified leakage occurrence time, flow rate, pressure monitoring data and flow prediction data within the corresponding time interval, and the pre-constructed water supply network hydraulic simulation model is the online hydraulic model for the corresponding time.

[0013] Further, step S2 includes the following steps:

[0014] S21: Estimate the actual leakage amount of the leakage event based on the leakage identification data;

[0015] S22: Based on the actual leakage amount of the leakage event, calculate the minimum pipe diameter required to produce that leakage amount. The expression for calculating the minimum pipe diameter is:

[0016]

[0017]

[0018] In the formula, D min For the minimum pipe diameter, Aout Q is the breach area calculated according to the orifice outflow formula. out To estimate leakage, α is the relaxation coefficient, g is the gravitational acceleration, H is the pressure at the orifice, and μ is the flow coefficient; in the hydraulic simulation model of the water supply network, all pipe sections with a diameter greater than or equal to the specified diameter are designated as the initial candidate leakage areas.

[0019] S23: Calculate the true leakage characteristics of a leakage event. The true leakage characteristics include the actual pressure value at the time of leakage, the predicted pressure value when there is no leakage event, and the actual pressure residual caused by the actual leakage event. The expression for calculating the actual pressure residual is as follows:

[0020] ΔP A =P AP -P AL

[0021] In the formula, ΔP A For the true pressure residual, P AP P is the predicted pressure value under conditions of no leakage events. AL This represents the actual pressure value after a real leakage event occurs.

[0022] Further, step S3 includes the following steps:

[0023] S31: Group the candidate leakage areas and select a characteristic center pipe segment for each group. The grouping method is to segment the network topology using the MLkP graph partitioning algorithm. The calculation expression for selecting the characteristic center pipe segment of each sub-region is as follows:

[0024]

[0025] In the formula, CP i Let N be the characteristic center pipe segment of the i-th sub-region, and N be the number of groups, (x j ,y j ) represents the coordinates of the midpoint of the j-th pipe, (μ) i,x ,μ i,y () represents the center coordinates of the i-th sub-region;

[0026] S32: Perform leakage event simulations on each characteristic center pipe segment and calculate the simulated leakage characteristics. The simulated leakage characteristics include the simulated pressure value before leakage at each characteristic center pipe segment, the simulated pressure value after leakage at each characteristic center pipe segment, and the simulated pressure residual caused by the simulated leakage event. The expression for calculating the simulated pressure residual is as follows:

[0027] ΔP i =P S,i -P Sl,i

[0028] In the formula, ΔP iTo simulate the pressure residual, P S,i For CP i Simulated pressure value before simulated leakage; P SL,i For CP i Simulated pressure value after simulated leakage;

[0029] S33: Calculate the similarity index between each simulated leakage feature and the actual leakage feature. The similarity index is the coupling similarity index obtained by weighting cosine similarity and Euclidean similarity using the entropy weight method. The expression for calculating the coupling similarity index is:

[0030]

[0031] SDI DIS,i =||P AL -P SL,i ||

[0032] SDI i =σSDI COs,i +(1-σ)SDI DIS,i

[0033] In the formula, SDI COS,i For CP i Cosine similarity between simulated leakage characteristics and real leakage characteristics, SDI DIS,i For CP i The Euclidean similarity between simulated leakage features and real leakage features, where σ is the weight calculated using the entropy weight method, and ΔP A For the true pressure residual, P AL This is the actual pressure value at the time of leakage;

[0034] S34: Set the sub-region retention rate, sort the feature center pipe segments according to the similarity index from high to low, and retain the feature center pipe segments with a proportion equal to the sub-region retention rate starting from the first item of the sequence, thereby reducing the number of pipe segments contained in the candidate missing region;

[0035] S35: Determine whether the number of pipe segments in the candidate leakage area has reached the set value. If yes, proceed to step S36; otherwise, return to step S31.

[0036] S36: The candidate leakage area at this time is determined to be a high-risk leakage area.

[0037] Furthermore, in step S34, the sub-region retention rate is 10% to 60%.

[0038] Furthermore, in step S35, the number of pipe segments is set to 1% to 10% of the number of pipe segments included in the initial candidate leakage area.

[0039] Further, step S4 includes the following steps:

[0040] S41: Simulate leakage at all pipe segments within the high-risk leakage area and calculate the simulated leakage characteristics;

[0041] S42: Calculate the similarity index between each simulated leakage feature and the actual leakage feature;

[0042] S43: Sort the pipe segments in the high-risk leakage area according to the similarity index to obtain the pipe segment location ranking result that reflects the possibility of leakage.

[0043] Furthermore, the types of leaks in water supply networks include gradual leaks and sudden leaks.

[0044] According to a second aspect of the present invention, an electronic device includes a memory, a processor, and a program stored in the memory, wherein the processor executes the program to implement any of the above-mentioned methods for dynamically locating leaking parts in a water supply network.

[0045] According to a third aspect of the present invention, a storage medium storing a program thereon, which, when executed, implements any of the above-mentioned methods for dynamically locating leaking parts in a water supply network.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1. This invention estimates the leakage amount and the location of candidate leakage areas by simulating leakage data collected in the model, constructs a dynamic search loop to update the similarity index, thereby narrowing down the range of possible leakage areas, locating pipeline areas with high leakage probability, and ranking the pipelines in the area by risk level. The ranking results are used to guide on-site inspection work. The location results of this invention have higher accuracy and can provide the range of candidate leakage areas, providing more comprehensive guidance for the investigation process.

[0048] 2. This invention uses a high-precision real-time hydraulic model to effectively simulate the normal operating conditions and leakage conditions when a new leakage occurs, which can more accurately describe the state and characteristics of the leakage, and help improve the accuracy of leakage location.

[0049] 3. The method provided by this invention can gradually and dynamically narrow down the possible leakage candidate area by constructing a loop body based solely on the leakage characteristics of the characteristic central pipe section. Therefore, compared with previous leakage location methods, it can significantly reduce the calculation time for simulating leakage at the candidate leakage location when performing leakage location analysis in large-scale complex pipe networks. In addition, the dynamic area narrowing rather than narrowing down to the candidate area at once can effectively improve the robustness of this method to monitoring noise.

[0050] 4. The method provided by this invention uses the entropy weight method to objectively evaluate the weights of cosine similarity and Euclidean similarity between simulated leakage features and real leakage features, which improves the positioning result deviation that may be caused by using a single similarity, and still has good practicality for large water supply networks with extremely low density of pressure monitoring points. Attached Figure Description

[0051] Figure 1 This is a flowchart of a method for dynamically locating leaking parts in a water supply network according to the present invention.

[0052] Figure 2 This is a schematic diagram of the water supply network topology and pressure monitoring point layout in the example area.

[0053] Figure 3 This is a process of narrowing down areas with high leakage risk.

[0054] Figure 4 This is a schematic diagram illustrating the leakage risk of pipe sections within a high leakage risk area. Detailed Implementation

[0055] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0056] Example

[0057] like Figure 1 As shown, this invention provides a method for dynamically locating leaking parts in a water supply network. The method includes the following steps:

[0058] S1: Read leakage identification data of the water supply network and the pre-built hydraulic simulation model of the water supply network after a real leakage event occurs;

[0059] S2: Estimate the leakage amount of the actual leakage event, delineate the initial candidate leakage area in the hydraulic simulation model of the water supply network based on the leakage amount, and calculate the actual leakage characteristics of the actual leakage event;

[0060] S3: Group the candidate leakage areas, select a characteristic center pipe segment for each group, simulate leakage events at each characteristic center pipe segment and calculate the simulated leakage characteristics. Based on the similarity index between the simulated leakage characteristics and the real leakage characteristics, reduce the number of pipes included in the candidate leakage area until the ratio of the number of pipes in the candidate leakage area to the number of pipes in the initial candidate leakage area reaches the set reduction rate. At this time, the candidate leakage area is determined to be a high-risk leakage area.

[0061] S4: Simulate and calculate the simulated leakage characteristics of each pipe segment within the high-risk leakage area, calculate the similarity index between each simulated leakage characteristic and the actual leakage characteristics, and sort them to obtain the pipe segment location ranking result that reflects the possibility of leakage.

[0062] Preferably, the leakage identification data in step S1 includes the identified leakage occurrence time, flow rate, pressure monitoring data and flow prediction data within the corresponding time interval, and the pre-constructed water pipe network hydraulic simulation model is the online hydraulic model for the corresponding time.

[0063] In this embodiment, step S1 identifies the occurrence time of the leakage event as 14:30 on April 30, 2021. The data read are the flow and pressure monitoring data and flow prediction data at that time. The model read is the online hydraulic model of the entire pipeline network at the corresponding time. There are 14 pressure monitoring points that can work stably in the area.

[0064] Step S2 includes the following steps:

[0065] S21: Estimate the actual leakage amount of the leakage event based on the leakage identification data;

[0066] S22: Based on the actual leakage amount of the leakage event, calculate the minimum pipe diameter required to produce that leakage amount. The expression for calculating the minimum pipe diameter is:

[0067]

[0068]

[0069] In the formula, D min For the minimum pipe diameter, A out Q is the breach area calculated according to the orifice outflow formula. out To estimate leakage, α is the relaxation coefficient, g is the gravitational acceleration, H is the pressure at the orifice, and μ is the flow coefficient; in the hydraulic simulation model of the water pipe network, all pipe sections with a diameter greater than or equal to the specified diameter are designated as the initial candidate leakage areas.

[0070] S23: Calculate the true leakage characteristics of a leakage event. The true leakage characteristics include the actual pressure value at the time of leakage, the predicted pressure value when there is no leakage event, and the actual pressure residual caused by the actual leakage event. The expression for calculating the actual pressure residual is as follows:

[0071] ΔP A =P AP -P AL

[0072] In the formula, ΔP A For the true pressure residual, P AP P is the predicted pressure value under conditions of no leakage events. ALThis represents the actual pressure value after a real leakage event occurs.

[0073] In this embodiment, the estimated leakage amount of the leakage event is approximately 2050m³. 3 / h; Delineate the initial candidate leakage region (I-CLA) based on the leakage rate; Calculate the minimum pipe diameter corresponding to the possible leakage event in this embodiment using the formula, which is 240mm, meaning that I-CLA includes all pipes with a diameter greater than this value within the entire region; Calculate the true leakage characteristic (ALF) of the leakage event; The true leakage characteristic mentioned in this step includes the pressure value P at the time of leakage. AL and the actual pressure residual ΔP A .

[0074] Step S3 includes the following steps:

[0075] Candidate leakage areas are grouped, and a characteristic center pipe segment is selected for each group. The grouping method is based on the pipe network topology using the MLkP (multilevel k-way partition) graph partitioning algorithm. The calculation expression for the characteristic center pipe segment of each sub-region is as follows:

[0076]

[0077] In the formula, CP i Let N be the characteristic center pipe segment of the i-th sub-region, and N be the number of groups, (x j ,y j ) represents the coordinates of the midpoint of the j-th pipe, (μ) i,x ,μ i,y () represents the center coordinates of the i-th sub-region;

[0078] S32: Perform leakage event simulations on each characteristic center pipe segment and calculate the simulated leakage characteristics. The simulated leakage characteristics include the simulated pressure value before leakage at each characteristic center pipe segment, the simulated pressure value after leakage at each characteristic center pipe segment, and the simulated pressure residual caused by the simulated leakage event. The expression for calculating the simulated pressure residual is as follows:

[0079] ΔP i =P S,i -P SL,i

[0080] In the formula, ΔP i To simulate the pressure residual, P S,i For CP i Simulated pressure value before simulated leakage; P SL,i For CP i Simulated pressure value after simulated leakage;

[0081] S33: Calculate the similarity index between each simulated leakage feature and the actual leakage feature. The similarity index is the coupling similarity index obtained by weighting cosine similarity and Euclidean similarity using the entropy weight method. The expression for calculating the coupling similarity index is:

[0082]

[0083] SDI DIS,i =||P AL -Q SL,i ||

[0084] SDI i =σSDI COS,i +(1-σ)SDI DIS,i

[0085] In the formula, SDI COS,i For CP i Cosine similarity between simulated leakage characteristics and real leakage characteristics, SDI DIS,i For CP i The Euclidean similarity between simulated leakage features and real leakage features, where σ is the weight calculated using the entropy weight method, and ΔP A For the true pressure residual, P AL This is the actual pressure value at the time of leakage;

[0086] S34: Set the sub-region retention rate, sort the feature center pipe segments according to the retention similarity index from high to low, and retain feature center pipe segments with a proportion equal to the sub-region retention rate starting from the first item of the sequence, thereby reducing the number of pipe segments included in the candidate missing region;

[0087] S35: Determine whether the number of pipe segments in the candidate leakage area has reached the set value. If yes, proceed to step S36; otherwise, return to step S31.

[0088] S36: The candidate leakage area at this time is determined to be a high-risk leakage area.

[0089] Preferably, the sub-region retention rate in step S34 is 10% to 60%.

[0090] Preferably, the number of pipe segments in step S35 is set to 1% to 10% of the number of pipe segments included in the initial candidate leakage area.

[0091] In this embodiment, the initial candidate leakage area in S31 is the initial input (I-CLA), and the subsequent leakage area (CLA) updated in S34 is the next step. The sub-region retention rate in step S34 is 40%. Since the reduction in the number of pipe segments within the candidate area is dynamic, the set value for the number of pipe segments is a range. In this embodiment, the set value for the number of pipe segments is 1% to 1.4%, i.e., 150 to 200 pipes. The high-risk leakage area (PLA) calculated in step S36 contains 183 high-risk pipes. The gradual reduction process of the possible leakage range in step S3 is as follows: Figure 3 As shown.

[0092] Step S4 includes the following steps:

[0093] S41: Simulate leakage at all pipe segments within the high-risk leakage area and calculate the simulated leakage characteristics. The simulated leakage characteristics include the simulated pressure value before the simulated leakage at each pipe segment, the simulated pressure value before the simulated leakage at each pipe segment, and the simulated pressure residual caused by the simulated leakage event. The expression for calculating the simulated pressure residual is as follows:

[0094] ΔP m =P m -P ml

[0095] In the formula, ΔP m To simulate the pressure residual, P m To simulate the pressure value before leakage at pipe segment m; P ml The simulated pressure value after leakage at pipe segment m;

[0096] S42: Calculate the similarity index between each simulated leakage feature and the actual leakage feature. The similarity index is the coupling similarity index obtained by weighting cosine similarity and Euclidean similarity using the entropy weight method. The expression for calculating the coupling similarity index is:

[0097]

[0098] SDI DIS,m =||P AL -P ml ||

[0099] SDI i =σSDI COS,m +(1-σ)SDI DIS,m

[0100] In the formula, SDI COS,m SDI is the cosine similarity between the simulated leakage characteristics and the actual leakage characteristics of pipe segment m. DIS,m Let σ be the Euclidean similarity between the simulated leakage characteristics and the actual leakage characteristics of pipe segment m, and let ΔP be the weight calculated using the entropy weight method.A For the true pressure residual, P LL This is the actual pressure value at the time of leakage;

[0101] S43: Sort the pipe segments in the high-risk leakage area according to the similarity index to obtain the pipe segment location ranking result that reflects the possibility of leakage.

[0102] In this embodiment, the leakage risk ranking of each candidate leakage pipe within the PLA is calculated as follows: Figure 4 The method identifies and marks the top-1 pipe segment with the highest probability of leakage. Taking the leakage event in the embodiment as an example, the calculation and analysis time used by this invention is 23.5 minutes. The topological distance between the actual maintenance records of the water company and the pipe segment with the highest probability located by this invention is 169.7 meters, and the spatial distance is also 169.7 meters. For the embodiment's pipeline network with a total pipeline length of over 980 km, this location result has high accuracy and reliability. In addition, the number of pipes in the embodiment's pipeline network that may have this leakage exceeds 14,000. Using the method of this invention, the leakage location can be roughly determined in just 23.5 minutes, demonstrating the high efficiency of this invention. It can guide the on-site leak detection as quickly as possible while greatly reducing the waste of water resources.

[0103] Furthermore, the types of leaks in water supply networks include gradual leaks and sudden leaks.

[0104] The electronic device of this invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) or loaded from storage units into random access memory (RAM). The RAM can also store various programs and data required for device operation. The CPU, ROM, and RAM are interconnected via a bus, and input / output (I / O) interfaces are also connected to the bus.

[0105] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0106] The machine-readable medium of the present invention may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof.

[0107] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A method for dynamically locating leaking parts in a water supply network, characterized in that, Includes the following steps: S1: Read leakage identification data of the water supply network and the pre-built hydraulic simulation model of the water supply network after a real leakage event occurs; S2: Estimate the leakage amount of the actual leakage event, delineate the initial candidate leakage area in the hydraulic simulation model of the water supply network based on the leakage amount, and calculate the actual leakage characteristics of the actual leakage event; S3: Group the candidate leakage areas, select a characteristic center pipe segment for each group, simulate leakage events at each characteristic center pipe segment and calculate the simulated leakage characteristics. Based on the similarity index between the simulated leakage characteristics and the real leakage characteristics, reduce the number of pipes included in the candidate leakage area until the ratio of the number of pipes in the candidate leakage area to the number of pipes in the initial candidate leakage area reaches the set reduction rate. At this time, the candidate leakage area is determined to be a high-risk leakage area. S4: Simulate and calculate the simulated leakage characteristics of each pipe segment in the high-risk leakage area, calculate the similarity index between each simulated leakage characteristic and the real leakage characteristics and sort them to obtain the pipe segment location ranking result that reflects the possibility of leakage. Step S3 includes the following steps: S31: Group the candidate leakage areas and select a characteristic center pipe segment for each group. The grouping method is to segment the network topology using the MLkP graph partitioning algorithm. The calculation expression for selecting the characteristic center pipe segment of each sub-region is as follows: In the formula, For the characteristic center pipe segment of the i-th sub-region, Number of groups Let J be the coordinates of the midpoint of the j-th pipe. Let the coordinates be the center coordinates of the i-th sub-region; S32: Perform leakage event simulation on each characteristic central pipe segment and calculate the simulated leakage characteristics. The simulated leakage characteristics include the simulated pressure value before the simulated leakage at each characteristic central pipe segment, the simulated pressure value after the simulated leakage at each characteristic central pipe segment, and the simulated pressure residual caused by the simulated leakage event. The calculation expression for the simulated pressure residual is as follows: In the formula, To simulate pressure residual, In order to be in Simulated pressure value before simulated leakage; In order to be in Simulated pressure value after simulated leakage; S33: Calculate the similarity index between each simulated leakage feature and the actual leakage feature. The similarity index is a coupling similarity index obtained by weighting cosine similarity and Euclidean similarity using the entropy weight method. The expression for calculating the coupling similarity index is as follows: In the formula, for The cosine similarity between simulated leakage characteristics and real leakage characteristics. for The Euclidean similarity between simulated leakage characteristics and real leakage characteristics. The weights are calculated using the entropy weight method. For the true pressure residual, This is the actual pressure value at the time of leakage; S34: Set the sub-region retention rate, sort the feature center pipe segments according to the similarity index from high to low, and retain the feature center pipe segments with a proportion equal to the sub-region retention rate starting from the first item of the sequence, thereby reducing the number of pipe segments contained in the candidate missing region; S35: Determine whether the number of pipe segments in the candidate leakage area has reached the set value. If yes, proceed to step S36; otherwise, return to step S31. S36: The candidate leakage area at this time is identified as a high-risk leakage area.

2. The method for dynamically locating leaking parts in a water supply network according to claim 1, characterized in that, The leakage identification data in step S1 includes the identified leakage occurrence time, flow rate, pressure monitoring data and flow prediction data within the corresponding time interval, and the pre-constructed water supply network hydraulic simulation model is an online hydraulic model for the corresponding time.

3. The method for dynamically locating leaking parts in a water supply network according to claim 1, characterized in that, Step S2 includes the following steps: S21: Estimate the actual leakage amount of the leakage event based on the leakage identification data; S22: Based on the actual leakage amount of the leakage event, calculate the minimum pipe diameter required to produce that leakage amount. The expression for calculating the minimum pipe diameter is: In the formula, For minimum pipe diameter, The break area is calculated according to the orifice outflow formula. To estimate the leakage, The relaxation coefficient is... It is the acceleration due to gravity. The pressure at the orifice, The flow coefficient is defined as the initial candidate leakage region in the hydraulic simulation model of the water supply network, where all pipe sections with a diameter greater than or equal to this diameter are designated as such. S23: Calculate the true leakage characteristics of the leakage event, wherein the true leakage characteristics include the actual pressure value at the time of leakage, the predicted pressure value when there is no leakage event, and the actual pressure residual caused by the actual leakage event. The expression for calculating the actual pressure residual is as follows: In the formula, For the true pressure residual, This is the predicted pressure value under conditions of no leakage events. This represents the actual pressure value after a real leakage event occurs.

4. The method for dynamically locating leaking parts in a water supply network according to claim 1, characterized in that, In step S34, the sub-region retention rate is 10%~60%.

5. The method for dynamically locating leaking parts in a water supply network according to claim 1, characterized in that, In step S35, the number of pipe segments is set to 1% to 10% of the number of pipe segments included in the initial candidate leakage area.

6. The method for dynamically locating leaking parts in a water supply network according to claim 1, characterized in that, Step S4 includes the following steps: S41: Simulate leakage at all pipe segments within the high-risk leakage area and calculate the simulated leakage characteristics; S42: Calculate the similarity index between each simulated leakage feature and the actual leakage feature; S43: Sort the pipe segments in the high-risk leakage area according to the similarity index to obtain the pipe segment location ranking result that reflects the possibility of leakage.

7. The method for dynamically locating leaking parts in a water supply network according to claim 1, characterized in that, The types of leaks in the water supply network include gradual leaks and sudden leaks.

8. An electronic device comprising a memory, a processor, and a program stored in the memory, characterized in that, When the processor executes the program, it implements a dynamic location method for leaking parts of a water supply network as described in any one of claims 1-7.

9. A storage medium having a program stored thereon, characterized in that, When the program is executed, it implements a dynamic location method for leaking parts of a water supply network as described in any one of claims 1-7.

Images