A water supply network sound signal monitoring point layout method and system and a storage medium

Abstract

The present application relates to the field of water supply network leakage monitoring, and discloses a water supply network sound signal monitoring point layout method, system and storage medium, comprising: acquiring pipeline data of the water supply network, constructing a network topology graph containing a node set and a pipe section set; selecting a candidate monitoring point set from the node set of the network topology graph, embedding the pipe fittings in the water supply network as special nodes into the network topology graph, and assigning attenuation coefficients to the pipe sections and pipe fittings in the network topology graph; using a shortest path algorithm to calculate the minimum cumulative attenuation path between any potential leakage point and any candidate monitoring point; determining the coverable leakage point set of each candidate monitoring point according to the comparison result of the minimum cumulative attenuation path and the preset detection threshold; under the constraint of the preset sensor number, iteratively selecting monitoring points from the candidate monitoring point set, and outputting a monitoring point layout scheme. The present application can significantly improve the network monitoring coverage and key node guarantee level under the constraint of the same sensor number.

Description

Technical Field

[0001] This invention relates to the field of water supply network leakage monitoring technology, and in particular to a method, system and storage medium for deploying sound signal monitoring points in water supply networks based on the attenuation law of sound signals. Background Technology

[0002] Acoustic signal monitoring technology for water supply network leaks has received widespread attention in recent years. By deploying acoustic sensors at key locations in the network, continuous monitoring and early warning of leaks can be achieved. However, existing monitoring point deployment methods rely heavily on manual experience in practical engineering applications. They typically use evenly spaced placement or select easily accessible locations such as valve wells and fire hydrants based on the experience of engineers. This approach has the following problems: 1. Evenly spaced placement does not consider the differences in material, diameter, burial conditions, and fitting distribution among different pipe sections in the network. The attenuation of acoustic signals varies significantly across different pipe sections, leading to redundant sensor deployment in some areas and insufficient coverage in others. 2. Existing methods usually estimate coverage based on geometric distance, failing to fully consider the attenuation of acoustic signals along the network caused by pipe materials and fittings (valves, tees, etc.). This results in discrepancies between the estimated coverage and the actual detectable range, making it difficult to guarantee the engineering effectiveness of the deployment plan. 3. Existing methods lack differentiated protection mechanisms for key nodes in the pipeline network (such as nodes with a history of frequent leaks), and may overlook key monitoring of critical risk areas in pursuit of maximizing overall coverage.

[0003] Therefore, how to combine the actual topology of the pipeline network with the physical laws of acoustic signal attenuation to achieve scientifically optimized deployment of monitoring points has become an urgent technical problem to be solved. Summary of the Invention

[0004] To address the aforementioned problems, the purpose of this invention is to provide a method, system, and storage medium for deploying acoustic signal monitoring points in water supply networks, which can maximize the detectable coverage of network leaks and improve the monitoring and protection level of key nodes under a given number of sensor constraints.

[0005] To achieve the above objectives, in a first aspect, the technical solution adopted by the present invention is as follows: a method for deploying acoustic signal monitoring points in a water supply network, comprising: a step of constructing a network topology map: acquiring pipeline data of the water supply network and constructing a network topology map including a set of nodes and a set of pipe segments; the pipeline data includes node information and pipe segment information, the node information including a unique node identifier, spatial coordinates, and node type, the node type including pipe connection points, valve wells, fire hydrants, metering facilities, and zone boundary nodes; a step of constructing a candidate monitoring point set: selecting a candidate monitoring point set from the node set of the network topology map, embedding pipe fittings in the water supply network as special nodes into the network topology map, and assigning attenuation coefficients to the pipe segments and pipe fittings in the network topology map respectively; wherein, the candidate monitoring points include valve wells, fire hydrants, metering wells, and other pipeline reachable points; The steps for calculating the minimum cumulative attenuation path are as follows: Using the shortest path algorithm, calculate the minimum cumulative attenuation path between any potential leak point and any candidate monitoring point. The minimum cumulative attenuation path is the path with the smallest cumulative attenuation coefficient among all possible propagation paths from the potential leak point to the candidate monitoring point. The steps for determining the set of leak points are as follows: Based on the comparison between the minimum cumulative attenuation path and the preset detection threshold, determine the set of leak points that can be covered by each candidate monitoring point. The steps for selecting monitoring point locations are as follows: Under the preset sensor quantity constraint, use a greedy optimization algorithm to iteratively select monitoring points from the candidate monitoring point set. At each step, select the candidate monitoring point that maximizes the marginal gain of the currently covered leak point set until the number of selected monitoring points reaches the sensor quantity constraint or the pipeline coverage reaches the preset threshold, and output the monitoring point deployment plan.

[0006] Furthermore, attenuation coefficients are assigned to pipe segments and fittings in the pipeline network topology diagram, including: The attenuation coefficient of a pipe section is determined based on its pipe material type, pipe diameter, and burial conditions, and characterizes the attenuation of the sound signal along the pipe section during its propagation. The attenuation coefficient of a pipe fitting is determined based on the type, specifications, and connection method of the fitting, and characterizes the local attenuation caused by the sudden change in local acoustic impedance when the sound signal passes through the fitting. The attenuation coefficient is calculated using a frequency band averaging method based on the measured acoustic signal data of the outer wall of the pipeline network within a preset frequency band range.

[0007] Furthermore, the shortest path algorithm is Dijkstra's algorithm; Calculate the minimum cumulative decay path between any potential leak point and any candidate monitoring point, including: ; in, denoted by , p represents the minimum cumulative attenuation path of the acoustic signal propagating from the potential leak point s along the network to the candidate monitoring point i; p represents a propagation path from the leak point s to the candidate monitoring point i; w(e) represents the attenuation coefficient of the pipe segment or fitting e in path p.

[0008] Furthermore, based on the comparison between the minimum cumulative attenuation path and the preset detection threshold, the set of coverable leakage points for each candidate monitoring point is determined, including: The detection threshold was set based on historical data statistics, on-site noise distribution, and permissible false alarm rate. ; For any candidate monitoring point i, the set of potential leak points that it can cover is determined according to the minimum cumulative attenuation path: ; in, A set of potential leakage points; Let i be the set of coverable leak points for candidate monitoring point i; This represents the minimum cumulative attenuation path of an acoustic signal propagating from a potential leak point s along the network to a candidate monitoring point i.

[0009] Furthermore, a greedy optimization algorithm is used to iteratively select monitoring points from the candidate monitoring point set, including: Each potential leak point in the set of potential leak points is assigned a weight, which is determined based on at least one of the following: historical pipe burst records of the corresponding pipe segment, pipe age, and pipe material vulnerability. The greedy optimization algorithm selects monitoring points with the goal of maximizing the weighted coverage rate.

[0010] Furthermore, the step of iteratively selecting monitoring points from the candidate monitoring point set using a greedy optimization algorithm also includes iteratively adjusting the monitoring points. The specific adjustment method is as follows: Nodes with a topological connectivity of no less than a preset threshold are selected from the pipeline topology diagram, and historical leakage nodes are determined based on historical operation and maintenance data to form an important monitoring node set; During the iterative process of the greedy optimization algorithm, the coverage of the important monitoring node set is set as a hard constraint: the selected monitoring points are required to cover the important monitoring node set to a preset ratio. Based on the hard constraints, the location of the monitoring points is iteratively adjusted with the goal of minimizing the topological distance from the important monitoring node to its nearest monitoring point.

[0011] Furthermore, after obtaining the monitoring point deployment plan, the process also includes an evaluation step for the monitoring point deployment plan: Construct a multi-scenario assessment set, which is the Cartesian product of four sets: sound source intensity level set, noise level set, pipe material scenario set, and attenuation coefficient fluctuation set. For each scenario combination in the multi-scenario assessment set, the steps of calculating the minimum cumulative attenuation path, determining the set of leakage points, and selecting the location of monitoring points are repeated to obtain the monitoring point deployment scheme and coverage corresponding to the scenario combination. Based on the coverage rate corresponding to each scenario combination, the coverage stability of the monitoring point deployment scheme under the condition of parameter uncertainty is evaluated; among which, the parameters include sound source intensity, noise level, pipe material type and attenuation coefficient.

[0012] Furthermore, based on the coverage rates corresponding to each scenario combination, the coverage stability of the monitoring point deployment scheme under conditions of parameter uncertainty is evaluated, including: For each uncertain parameter in a scenario, the minimum number of sensors required to reach the preset coverage threshold under multiple preset value scenarios is obtained, forming a set of quantities corresponding to the parameter. Calculate the difference between the maximum and minimum values ​​of the set of quantities; By comparing the differences between various parameters, if the difference of a certain type of parameter is greater than a preset sensitivity threshold, it is determined that the deployment scheme is sensitive to changes in that type of parameter and has low coverage stability; if the difference is less than or equal to the preset sensitivity threshold, it is determined that the deployment scheme is not sensitive to changes in that type of parameter and has high coverage stability.

[0013] Secondly, the technical solution adopted by the present invention is as follows: a system for deploying acoustic signal monitoring points in a water supply network, comprising: a network topology map construction module, which acquires pipeline data of the water supply network and constructs a network topology map including a set of nodes and a set of pipe segments; the pipeline data includes node information and pipe segment information, the node information including a unique node identifier, spatial coordinates, and node type, the node type including pipe connection points, valve wells, fire hydrants, metering facilities, and zone boundary nodes; a candidate monitoring point set construction module, which selects a set of candidate monitoring points from the set of nodes in the network topology map, embeds pipe fittings in the water supply network as special nodes into the network topology map, and assigns attenuation coefficients to the pipe segments and pipe fittings in the network topology map respectively; wherein, the candidate monitoring points include valve wells, fire hydrants, metering wells, and other reachable points of the pipelines; minimum cumulative The attenuation path calculation module uses the shortest path algorithm to calculate the minimum cumulative attenuation path between any potential leak point and any candidate monitoring point. The minimum cumulative attenuation path is the path with the smallest cumulative attenuation coefficient among all possible propagation paths between the potential leak point and the candidate monitoring point. The leak point set determination module determines the set of leak points that can be covered by each candidate monitoring point based on the comparison result between the minimum cumulative attenuation path and the preset detection threshold. The monitoring point deployment location selection module uses a greedy optimization algorithm to iteratively select monitoring points from the candidate monitoring point set under the preset sensor number constraint: at each step, it selects the candidate monitoring point that maximizes the marginal gain of the currently covered leak point set, until the number of selected monitoring points reaches the sensor number constraint or the pipeline coverage rate reaches the preset threshold, and outputs the monitoring point deployment plan.

[0014] Thirdly, the technical solution adopted by the present invention is: a computer-readable storage medium for storing one or more programs, characterized in that the one or more programs include instructions, which, when executed by a computing device, cause the computing device to perform any of the methods described above.

[0015] The present invention has the following advantages due to the adoption of the above technical solutions: 1. This invention constructs a detectable coverage criterion based on the actual topology of the pipeline network and the physical laws of acoustic signal attenuation. Compared with coverage estimation methods based on geometric distance, it can more accurately reflect the detectable range of acoustic signals in the actual pipeline network and improve the engineering effectiveness of the deployment scheme.

[0016] 2. This invention employs a solution framework combining the shortest path algorithm and the greedy optimization algorithm, which can efficiently obtain a near-optimal deployment scheme under a given constraint on the number of sensors. Compared with manual deployment based on experience, it significantly improves the monitoring coverage rate with the same resource investment. According to actual test cases, deploying 18 sensors using the method of this invention can achieve a total pipeline network coverage rate of 95%, a critical node coverage rate of 100%, and an average monitoring distance of 29 meters for critical nodes. In contrast, using the equal-spacing deployment method with the same number of sensors, the total pipeline network coverage rate is only 49%, the critical node coverage rate is 60%, and the average monitoring distance for critical nodes is 105 meters.

[0017] 3. By introducing a hard constraint mechanism for the set of important monitoring nodes, this invention can ensure that key nodes in the pipeline network (such as nodes with a high history of leakage) receive priority and reliable monitoring protection while ensuring overall coverage.

[0018] 4. By constructing a multi-scenario evaluation set, this invention can evaluate the coverage stability of the monitoring point deployment scheme under uncertain conditions such as sound source intensity, noise level, pipe material differences and attenuation parameter fluctuations, thereby improving the applicability of the deployment scheme in complex real operating environments. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the method for deploying acoustic signal monitoring points in a water supply network according to an embodiment of the present invention. Figure 2 This is a water supply network topology diagram in an embodiment of the present invention; Figure 3 This is a schematic diagram of the layout optimization process under the constraints of important monitoring points in an embodiment of the present invention; Figure 4 This is a curve showing the change in monitoring coverage as the number of sensors increases in an embodiment of the present invention; Figure 5 This is a visualization of the sensor monitoring deployment in an embodiment of the present invention. Detailed Implementation

[0020] To address the technical problems of existing methods for deploying acoustic monitoring points in water supply networks, such as reliance on manual experience, insufficient consideration of acoustic signal attenuation laws, inaccurate coverage estimation, and lack of differentiated protection for key nodes, this invention provides a method, system, and storage medium for deploying acoustic signal monitoring points in water supply networks. The method includes: acquiring water supply network topology data and constructing a topology map; assigning attenuation coefficients representing friction-induced attenuation and local attenuation to pipe sections and fittings; calculating the minimum cumulative attenuation path between candidate monitoring points and potential leak points based on a shortest path algorithm; determining the coverage area of ​​each candidate point based on a detection threshold; and using a greedy algorithm to iteratively select monitoring point locations under sensor quantity constraints to maximize network coverage. Compared to existing methods using equal spacing or empirical deployment, this invention constructs a detectable coverage criterion based on the physical laws of acoustic signal attenuation, significantly improving network monitoring coverage and key node protection levels under the same sensor quantity constraints, demonstrating strong engineering practicality.

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0022] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0023] In one embodiment of the present invention, a method for deploying acoustic signal monitoring points in a water supply network is provided. In this embodiment, as shown... Figure 1 As shown, the method includes the following steps: 1) Steps for constructing a pipeline network topology map: Obtain pipeline data of the water supply network, and construct a pipeline network topology map G=(V,E) containing a set of nodes V and a set of pipe segments E; Pipeline data includes node information and pipe segment information. Node information includes unique node identifier, spatial coordinates and node type. Node types include pipe connection points, valve wells, fire hydrants, metering facilities and zone boundary nodes.

[0024] 2) Steps for constructing a candidate monitoring point set: Select a candidate monitoring point set from the node set V of the pipeline network topology diagram, embed the pipe fittings in the water supply network as special nodes into the pipeline network topology diagram, and assign attenuation coefficients to the pipe segments and pipe fittings in the pipeline network topology diagram respectively; among them, candidate monitoring points include valve wells, fire hydrants, metering wells and other pipeline reachable points.

[0025] 3) Steps for calculating the minimum cumulative attenuation path: Using the shortest path algorithm, calculate the minimum cumulative attenuation path between any potential leak point and any candidate monitoring point. The minimum cumulative attenuation path is the path with the smallest cumulative attenuation coefficient among all possible propagation paths between the potential leak point and the candidate monitoring point.

[0026] 4) Steps for determining the set of leak points: Based on the comparison results between the minimum cumulative attenuation path and the preset detection threshold, determine the set of leak points that can be covered by each candidate monitoring point.

[0027] 5) Steps for selecting monitoring point locations: Under the preset sensor quantity constraint, a greedy optimization algorithm is used to iteratively select monitoring points from the candidate monitoring point set: at each step, a candidate monitoring point is selected that maximizes the marginal gain of the currently covered leak point set, until the number of selected monitoring points reaches the sensor quantity constraint or the pipeline coverage rate reaches the preset threshold, and the monitoring point deployment plan is output.

[0028] In step 1) above, the pipe segment information includes the unique identifier of the pipe segment, the starting and ending nodes, the length, the pipe material type, and the pipe diameter. In the pipe network topology graph G=(V,E), the node set V corresponds to the connecting nodes and functional nodes in the pipe network, and the edge set E corresponds to each pipe segment.

[0029] In this embodiment, the acquired pipeline network data is processed by topological association, which associates the endpoints of each pipe segment with the node records, and cleans and corrects abnormal data such as isolated nodes, duplicate pipe segments, and coordinate offsets.

[0030] In step 2) above, attenuation coefficients are assigned to pipe segments and fittings in the pipeline network topology diagram, including the following steps: 2.1) The attenuation coefficient of the pipe section is determined according to its pipe material type, pipe diameter and burial conditions, and characterizes the attenuation of the sound signal along the pipe section during its propagation.

[0031] 2.2) The attenuation coefficient of pipe fittings is determined according to the type, specifications, and connection method of the fittings, and characterizes the local attenuation caused by sudden changes in local acoustic impedance when the sound signal passes through the fittings. Fittings include tees, socket joints, valves, flow meters, and flange connections.

[0032] The attenuation coefficient is calculated using a frequency band averaging method based on the measured acoustic signal data of the outer wall of the pipeline network within a preset frequency band.

[0033] In this embodiment, due to structural differences between various pipe fittings and straight pipes in terms of their cavity shape, flow distribution structure, diameter variation, and pipe stiffness, when these structural differences create localized abrupt changes in cross-sectional area, multi-branch acoustic loads, or closed rigid boundaries, discontinuous abrupt changes in acoustic impedance will occur at the pipe fitting interface. At this point, acoustic signals undergo reflection, transmission, and coherent interference, resulting in acoustic signal energy loss and amplitude attenuation.

[0034] In step 3) above, the shortest path algorithm is Dijkstra's algorithm.

[0035] In this embodiment, the pipeline topology is represented as a weighted graph G=(V,E). Each pipe segment in the graph is assigned a propagation cost, which is the attenuation contribution of the acoustic signal on that segment. The minimum cumulative attenuation path between any potential leak point and any candidate monitoring point is calculated, including: ; in, denoted by , p represents the minimum cumulative attenuation path of the acoustic signal propagating from the potential leak point s along the network to the candidate monitoring point i; p represents a propagation path from the leak point s to the candidate monitoring point i; w(e) represents the attenuation coefficient of the pipe segment or fitting e in path p.

[0036] In step 4) above, based on the comparison between the minimum cumulative attenuation path and the preset detection threshold, the set of coverable leakage points for each candidate monitoring point is determined, including the following steps: 4.1) Set the detection threshold based on historical data statistics, on-site noise distribution, and allowable false alarm rate. .

[0037] 4.2) For any candidate monitoring point i, the set of potential leakage points that it can cover is determined according to the minimum cumulative attenuation path: ; in, A set of potential leakage points; Let i be the set of coverable leak points for candidate monitoring point i; This represents the minimum cumulative attenuation path of an acoustic signal propagating from a potential leak point s along the network to a candidate monitoring point i.

[0038] In step 5) above, a greedy optimization algorithm is used to iteratively select monitoring points from the candidate monitoring point set. Specifically, each potential leak point in the potential leak point set is assigned a weight, which is determined based on at least one of the following: historical pipe burst records of the corresponding pipe section, pipe age, pipe material vulnerability, and sensitivity to important users. The greedy optimization algorithm selects monitoring points with the goal of maximizing the weighted coverage rate.

[0039] In the above embodiment, step 5) of iteratively selecting monitoring points from the candidate monitoring point set using a greedy optimization algorithm further includes iteratively adjusting the monitoring points. The specific adjustment method is as follows: 5.1) Select nodes with a topology connectivity of not less than a preset threshold from the pipeline topology diagram, and select historical leakage nodes determined based on historical operation and maintenance data to form an important monitoring node set.

[0040] 5.2) During the iteration of the greedy optimization algorithm, the coverage of the important monitoring node set is set as a hard constraint: the selected monitoring points are required to cover the important monitoring node set to a preset ratio.

[0041] In this embodiment, the preset ratio can be 95%.

[0042] 5.3) Based on satisfying the hard constraints, the location of the monitoring points is iteratively adjusted with the goal of minimizing the topological distance from the important monitoring node to its nearest monitoring point.

[0043] In the above embodiments, after obtaining the monitoring point deployment plan, a step 6) of evaluating the monitoring point deployment plan is further included, specifically including the following steps: 6.1) Construct a multi-scenario assessment set, which is the Cartesian product of the sound source intensity level set, the noise level set, the pipe material scenario set, and the attenuation coefficient fluctuation set; 6.2) For each scenario combination in the multi-scenario assessment set, repeat the steps of calculating the minimum cumulative attenuation path, determining the set of leakage points, and selecting the location of monitoring points to obtain the monitoring point deployment scheme and coverage corresponding to the scenario combination. 6.3) Based on the coverage rate corresponding to each scenario combination, evaluate the coverage stability of the monitoring point deployment scheme under conditions of parameter uncertainty. The parameters include sound source intensity, noise level, pipe type, and attenuation coefficient.

[0044] In this embodiment, the coverage stability of the monitoring point deployment scheme under conditions of parameter uncertainty is evaluated based on the coverage rate corresponding to each scenario combination, including the following steps: 6.3.1) For each scenario's uncertainty parameter, obtain the minimum number of sensors required to reach the preset coverage threshold under multiple preset value scenarios, forming the corresponding quantity set for that parameter; 6.3.2) Calculate the difference between the maximum and minimum values ​​of the set of quantities; 6.3.3) Compare the differences between various parameters. If the difference of a certain type of parameter is greater than the preset sensitivity threshold, it is determined that the deployment scheme is sensitive to the change of this type of parameter and has low coverage stability. If it is less than or equal to the preset sensitivity threshold, it is determined that the deployment scheme is not sensitive to the change of this type of parameter and has high coverage stability.

[0045] In this embodiment, the method of the present invention is verified using real water supply network data from a prefecture-level city in China. The network data is stored in GeoJSON format and contains a total of 1,750 pipelines, 1,750 nodes, and a total network length of 6.889 kilometers.

[0046] 1) Parse the GeoJSON data of the pipeline network and extract pipeline elements and node elements respectively; use coordinate matching and identifier comparison to associate each pipeline endpoint with the node record; clean and correct abnormal data such as topology broken links, pseudo-connectivity and coordinate offset, and construct the pipeline network topology map G=(V,E).

[0047] 2) Construct a set of candidate monitoring points in the pipeline network (valve wells, fire hydrants, metering wells, etc.); embed pipe fittings such as tees and valves in the pipeline network as special nodes into the topology map; calculate the friction loss coefficient of each pipe segment using a frequency band averaging method, based on the pipe material type, pipe diameter, and burial conditions, and combined with the measured external wall acoustic signal data in the 0-2000Hz frequency band. Obtain the local attenuation coefficient of each pipe fitting through a signal comparison experiment before and after the fitting, based on the fitting type and connection method. For example, in the pipeline network of this embodiment, the average friction loss coefficient in the steel pipe is measured to be 0.63 dB / m, and the average local attenuation coefficient at the valve is 2.44 dB.

[0048] 3) Calculate the minimum cumulative decay path between each candidate monitoring point and each potential leak point in the pipeline network using the Dijkstra algorithm.

[0049] 4) Set the detection threshold (signal-to-noise ratio -20dB) and determine the set of coverable leak points for each candidate monitoring point based on the calculation results in step 3).

[0050] 5) Under the constraint of the number of sensors, a greedy algorithm is used to iteratively select monitoring points. In this embodiment, 25 important monitoring nodes with high connectivity are selected from the pipeline topology attributes, and combined with 15 historical leakage nodes, a set of 40 important monitoring nodes is formed. The coverage hard constraint of this set is set to 100%, and the optimization objective is to minimize the topological distance from the important node to the nearest monitoring point.

[0051] Optimization results show that the final deployment scheme uses 18 sensors, achieving a total network coverage rate of over 95%, 100% coverage of 40 key monitoring nodes, and keeping the average monitoring distance for key nodes within 30 meters. In contrast, using an equidistant deployment method with the same number of sensors (18), the total network coverage rate is only 49%, the coverage rate for key nodes is 60%, and the average monitoring distance for key nodes is 105 meters. This demonstrates that the method of this invention has significant advantages in monitoring efficiency and critical node protection capabilities.

[0052] 6) Multi-scenario robustness assessment After completing the basic deployment scheme in step 5), a multi-scenario evaluation set Ω is further constructed to evaluate the coverage stability of the deployment scheme under parameter uncertainty conditions. The multi-scenario evaluation set Ω is the Cartesian product of the following four parameter sets:

[0053] Wherein, P is the set of sound source intensity levels, and in this embodiment, three representative levels are selected, corresponding to small leakage of 0.5 m³ / h, medium leakage of 2.0 m³ / h, and large leakage of 5.0 m³ / h, respectively; N is the set of noise levels, and in this embodiment, based on the actual measured environmental noise distribution, three levels are selected: low noise, normal noise, and high noise, with a noise difference of 10 dB between adjacent levels; M is the set of pipe material scenarios, and in this embodiment, based on the actual pipe material composition of the pipeline network, three typical pipe material configuration scenarios are selected: ductile iron pipe, cast iron pipe, and PE pipe; D is the set of attenuation coefficient fluctuations, and in this embodiment, based on the interquartile range of the measured attenuation parameter, three representative values ​​are selected: the upper limit, the average value, and the lower limit of the attenuation parameter.

[0054] For each scenario combination in Ω, repeat the calculation process from step 3) to step 5). That is, for the sound source intensity, noise level, pipe configuration and attenuation coefficient value under the scenario combination, recalculate the minimum cumulative attenuation path of the candidate monitoring point and the set of leak points that can be covered, and output the number of sensors, coverage rate, average pipeline length covered by the sensors and sensor density corresponding to the scenario combination.

[0055] This embodiment performs scenario calculations for single-factor changes (i.e., keeping the other three types of parameters constant and only changing one type of parameter), and the results are as follows: When the sound source intensity changes: 74 sensors are needed to achieve 95.03% coverage in a small leakage scenario, 35 sensors are needed to achieve 95.03% coverage in a medium leakage scenario, and 13 sensors are needed to achieve 95.37% coverage in a large leakage scenario.

[0056] When noise levels change: 32 sensors are needed to achieve 95.26% coverage in low noise scenarios, 35 sensors are needed to achieve 95.03% coverage in normal noise scenarios, and 46 sensors are needed to achieve 95.20% coverage in high noise scenarios.

[0057] When the pipe material conditions change: 35 sensors are needed to achieve 95.03% coverage for ductile iron pipes, 83 sensors are needed to achieve 95.09% coverage for cast iron pipes, and 202 sensors are needed to achieve 95.03% coverage for PE pipes.

[0058] When the attenuation coefficient fluctuates: under the upper limit scenario of the attenuation parameter, 39 sensors are needed to achieve a coverage rate of 95.54%; under the average scenario, 35 sensors are needed to achieve a coverage rate of 95.03%; and under the lower limit scenario, 32 sensors are needed to achieve a coverage rate of 95.20%.

[0059] Based on the multi-scenario calculation results above, it can be seen that the sound source intensity and pipe material type have a significant impact on the sensor deployment density, with the difference in pipe material leading to the widest range of sensor number variations (35 to 202). In contrast, fluctuations in noise level and attenuation coefficient have a relatively smaller impact on the deployment scheme. Therefore, it can be concluded that the deployment scheme obtained in this embodiment is quite sensitive to changes in pipe material composition, but exhibits good coverage stability within the range of noise and attenuation parameter fluctuations. In practical engineering applications, the deployment scheme should be carefully checked and adjusted based on the actual pipe material distribution in the pipeline network.

[0060] In one embodiment of the present invention, a system for deploying acoustic signal monitoring points in a water supply network is provided, comprising: The pipeline topology construction module acquires pipeline data of the water supply network and constructs a pipeline topology map containing node sets and pipe segment sets. The pipeline data includes node information and pipe segment information. The node information includes the node's unique identifier, spatial coordinates, and node type. The node types include pipe connection points, valve wells, fire hydrants, metering facilities, and zone boundary nodes. The candidate monitoring point set construction module selects a set of candidate monitoring points from the node set of the pipeline network topology map, embeds pipe fittings in the water supply network as special nodes into the pipeline network topology map, and assigns attenuation coefficients to pipe segments and pipe fittings in the pipeline network topology map respectively; among them, candidate monitoring points include valve wells, fire hydrants, metering wells and other pipeline reachable points; The minimum cumulative attenuation path calculation module uses the shortest path algorithm to calculate the minimum cumulative attenuation path between any potential leak point and any candidate monitoring point. The minimum cumulative attenuation path is the path with the smallest cumulative attenuation coefficient among all possible propagation paths between the potential leak point and the candidate monitoring point. The leak point set determination module determines the set of leak points that can be covered by each candidate monitoring point based on the comparison results between the minimum cumulative attenuation path and the preset detection threshold. The monitoring point deployment location selection module, under the preset sensor number constraint, uses a greedy optimization algorithm to iteratively select monitoring points from the candidate monitoring point set: at each step, it selects the candidate monitoring point that maximizes the marginal gain of the currently covered leak point set, until the number of selected monitoring points reaches the sensor number constraint or the pipeline coverage rate reaches the preset threshold, and outputs the monitoring point deployment scheme.

[0061] In the above embodiments, attenuation coefficients are assigned to pipe segments and fittings in the pipeline network topology diagram, including: The attenuation coefficient of a pipe section is determined based on its pipe material type, pipe diameter, and burial conditions, and characterizes the attenuation of the sound signal along the pipe section during its propagation. The attenuation coefficient of a pipe fitting is determined based on the type, specifications, and connection method of the fitting, and characterizes the local attenuation caused by the sudden change in local acoustic impedance when the sound signal passes through the fitting. The attenuation coefficient is calculated using a frequency band averaging method based on the measured acoustic signal data of the outer wall of the pipeline network within a preset frequency band range.

[0062] In the above embodiments, the shortest path algorithm is Dijkstra's algorithm; Calculate the minimum cumulative decay path between any potential leak point and any candidate monitoring point, including: ; in, denoted by , p represents the minimum cumulative attenuation path of the acoustic signal propagating from the potential leak point s along the network to the candidate monitoring point i; p represents a propagation path from the leak point s to the candidate monitoring point i; w(e) represents the attenuation coefficient of the pipe segment or fitting e in path p.

[0063] In the above embodiments, based on the comparison result between the minimum cumulative attenuation path and the preset detection threshold, the set of coverable leakage points for each candidate monitoring point is determined, including: The detection threshold was set based on historical data statistics, on-site noise distribution, and permissible false alarm rate. ; For any candidate monitoring point i, the set of potential leak points that it can cover is determined according to the minimum cumulative attenuation path: ; in, A set of potential leakage points; Let i be the set of coverable leak points for candidate monitoring point i; This represents the minimum cumulative attenuation path of an acoustic signal propagating from a potential leak point s along the network to a candidate monitoring point i.

[0064] In the above embodiments, a greedy optimization algorithm is used to iteratively select monitoring points from the candidate monitoring point set, including: Each potential leak point in the set of potential leak points is assigned a weight, which is determined based on at least one of the following: historical pipe burst records of the corresponding pipe segment, pipe age, and pipe material vulnerability. The greedy optimization algorithm selects monitoring points with the goal of maximizing the weighted coverage rate.

[0065] In the above embodiments, the step of iteratively selecting monitoring points from the candidate monitoring point set using a greedy optimization algorithm further includes iteratively adjusting the monitoring points. The specific adjustment method is as follows: Nodes with a topological connectivity of no less than a preset threshold are selected from the pipeline topology diagram, and historical leakage nodes are determined based on historical operation and maintenance data to form an important monitoring node set; During the iterative process of the greedy optimization algorithm, the coverage of the important monitoring node set is set as a hard constraint: the selected monitoring points are required to cover the important monitoring node set to a preset ratio. Based on the hard constraints, the location of the monitoring points is iteratively adjusted with the goal of minimizing the topological distance from the important monitoring node to its nearest monitoring point.

[0066] In the above embodiments, after obtaining the monitoring point deployment plan, the method further includes an evaluation step of the monitoring point deployment plan: Construct a multi-scenario assessment set, which is the Cartesian product of four sets: sound source intensity level set, noise level set, pipe material scenario set, and attenuation coefficient fluctuation set. For each scenario combination in the multi-scenario assessment set, the steps of calculating the minimum cumulative attenuation path, determining the set of leakage points, and selecting the location of monitoring points are repeated to obtain the monitoring point deployment scheme and coverage corresponding to the scenario combination. Based on the coverage rate corresponding to each scenario combination, the coverage stability of the monitoring point deployment scheme under the condition of parameter uncertainty is evaluated.

[0067] In the above embodiments, the coverage stability of the monitoring point deployment scheme under conditions of parameter uncertainty is evaluated based on the coverage rate corresponding to each scenario combination, including: For each uncertain parameter in a scenario, the minimum number of sensors required to reach the preset coverage threshold under multiple preset value scenarios is obtained, forming a set of quantities corresponding to the parameter. Calculate the difference between the maximum and minimum values ​​of the set of quantities; By comparing the differences between various parameters, if the difference of a certain type of parameter is greater than a preset sensitivity threshold, it is determined that the deployment scheme is sensitive to changes in that type of parameter and has low coverage stability; if the difference is less than or equal to the preset sensitivity threshold, it is determined that the deployment scheme is not sensitive to changes in that type of parameter and has high coverage stability.

[0068] The system provided in this embodiment is used to execute the above-described method embodiments. For specific processes and details, please refer to the above embodiments, which will not be repeated here.

[0069] In one embodiment of the present invention, a computing device is provided, which may be a terminal and may include: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, and the one or more programs include instructions for performing any of the methods in the above embodiments.

[0070] Furthermore, when the aforementioned instructions can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0071] In one embodiment of the present invention, a computer program product is provided, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, and when the program instructions are executed by a computer, the computer is able to perform the methods provided in the above-described method embodiments.

[0072] In one embodiment of the present invention, a non-transitory computer-readable storage medium is provided, which stores server instructions that cause a computer to perform the methods provided in the above embodiments.

[0073] The computer-readable storage medium provided in the above embodiments has a similar implementation principle and technical effect to the above method embodiments, and will not be described again here.

[0074] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0075] 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.

[0076] 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.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for deploying acoustic signal monitoring points in a water supply network, characterized in that, include: The steps to construct a pipeline network topology map are as follows: Obtain pipeline data of the water supply network and construct a pipeline network topology map that includes node sets and pipe segment sets; pipeline data includes node information and pipe segment information. Node information includes unique node identifier, spatial coordinates and node type. Node types include pipe connection points, valve wells, fire hydrants, metering facilities and zone boundary nodes. The steps for constructing a candidate monitoring point set are as follows: Select a candidate monitoring point set from the node set of the pipeline network topology diagram; embed pipe fittings in the water supply network as special nodes into the pipeline network topology diagram; and assign attenuation coefficients to pipe segments and pipe fittings in the pipeline network topology diagram respectively; among them, candidate monitoring points include valve wells, fire hydrants, metering wells, and other pipeline reachable points; The steps for calculating the minimum cumulative attenuation path are as follows: Using the shortest path algorithm, calculate the minimum cumulative attenuation path between any potential leak point and any candidate monitoring point. The minimum cumulative attenuation path is the path with the smallest cumulative attenuation coefficient among all possible propagation paths between the potential leak point and the candidate monitoring point. The steps for determining the set of leak points are as follows: Based on the comparison between the minimum cumulative attenuation path and the preset detection threshold, determine the set of leak points that can be covered by each candidate monitoring point; The steps for selecting monitoring point locations are as follows: Under the preset sensor quantity constraint, a greedy optimization algorithm is used to iteratively select monitoring points from the candidate monitoring point set: at each step, a candidate monitoring point is selected that maximizes the marginal gain of the currently covered leak point set, until the number of selected monitoring points reaches the sensor quantity constraint or the pipeline coverage rate reaches the preset threshold, and the monitoring point deployment plan is output.

2. The method for deploying acoustic signal monitoring points in a water supply network as described in claim 1, characterized in that, Assign attenuation coefficients to pipe segments and fittings in the pipeline network topology diagram, including: The attenuation coefficient of a pipe section is determined based on its pipe material type, pipe diameter, and burial conditions, and characterizes the attenuation of the sound signal along the pipe section during its propagation. The attenuation coefficient of a pipe fitting is determined based on the type, specifications, and connection method of the fitting, and characterizes the local attenuation caused by the sudden change in local acoustic impedance when the sound signal passes through the fitting. The attenuation coefficient is calculated using a frequency band averaging method based on the measured acoustic signal data of the outer wall of the pipeline network within a preset frequency band range.

3. The method for deploying acoustic signal monitoring points in a water supply network as described in claim 1, characterized in that, The shortest path algorithm is Dijkstra's algorithm; Calculate the minimum cumulative decay path between any potential leak point and any candidate monitoring point, including: ； in, denoted by , p represents the minimum cumulative attenuation path of the acoustic signal propagating from the potential leak point s along the network to the candidate monitoring point i; p represents a propagation path from the leak point s to the candidate monitoring point i; w(e) represents the attenuation coefficient of the pipe segment or fitting e in path p.

4. The method for deploying acoustic signal monitoring points in a water supply network as described in claim 1, characterized in that, Based on the comparison between the minimum cumulative attenuation path and the preset detection threshold, the set of coverable leakage points for each candidate monitoring point is determined, including: The detection threshold was set based on historical data statistics, on-site noise distribution, and permissible false alarm rate. ; For any candidate monitoring point i, the set of potential leak points that it can cover is determined according to the minimum cumulative attenuation path: ； in, A set of potential leakage points; Let i be the set of coverable leak points for candidate monitoring point i; This represents the minimum cumulative attenuation path of an acoustic signal propagating from a potential leak point s along the network to a candidate monitoring point i.

5. The method for deploying acoustic signal monitoring points in a water supply network as described in claim 1, characterized in that, A greedy optimization algorithm is used to iteratively select monitoring points from the candidate monitoring point set, including: Each potential leak point in the set of potential leak points is assigned a weight, which is determined based on at least one of the following: historical pipe burst records of the corresponding pipe segment, pipe age, and pipe material vulnerability. The greedy optimization algorithm selects monitoring points with the goal of maximizing the weighted coverage rate.

6. The method for deploying acoustic signal monitoring points in a water supply network as described in claim 1, characterized in that, The step of iteratively selecting monitoring points from the candidate monitoring point set using a greedy optimization algorithm also includes iteratively adjusting the monitoring points. The specific adjustment method is as follows: Nodes with a topological connectivity of no less than a preset threshold are selected from the pipeline topology diagram, and historical leakage nodes are determined based on historical operation and maintenance data to form an important monitoring node set; During the iterative process of the greedy optimization algorithm, the coverage of the important monitoring node set is set as a hard constraint: the selected monitoring points are required to cover the important monitoring node set to a preset ratio. Based on the hard constraints, the location of the monitoring points is iteratively adjusted with the goal of minimizing the topological distance from the important monitoring node to its nearest monitoring point.

7. The method for deploying acoustic signal monitoring points in a water supply network as described in claim 1, characterized in that, After obtaining the monitoring point deployment plan, the process also includes an evaluation step of the monitoring point deployment plan: Construct a multi-scenario assessment set, which is the Cartesian product of four sets: sound source intensity level set, noise level set, pipe material scenario set, and attenuation coefficient fluctuation set. For each scenario combination in the multi-scenario assessment set, the steps of calculating the minimum cumulative attenuation path, determining the set of leakage points, and selecting the location of monitoring points are repeated to obtain the monitoring point deployment scheme and coverage corresponding to the scenario combination. Based on the coverage rate corresponding to each scenario combination, the coverage stability of the monitoring point deployment scheme under the condition of parameter uncertainty is evaluated; among which, the parameters include sound source intensity, noise level, pipe material type and attenuation coefficient.

8. The method for deploying acoustic signal monitoring points in a water supply network as described in claim 7, characterized in that, Based on the coverage rates corresponding to each scenario combination, evaluate the coverage stability of the monitoring point deployment scheme under conditions of parameter uncertainty, including: For each uncertain parameter in a scenario, the minimum number of sensors required to reach the preset coverage threshold under multiple preset value scenarios is obtained, forming a set of quantities corresponding to the parameter. Calculate the difference between the maximum and minimum values ​​of the set of quantities; By comparing the differences between various parameters, if the difference of a certain type of parameter is greater than a preset sensitivity threshold, it is determined that the deployment scheme is sensitive to changes in that type of parameter and has low coverage stability; if the difference is less than or equal to the preset sensitivity threshold, it is determined that the deployment scheme is not sensitive to changes in that type of parameter and has high coverage stability.

9. A system for deploying acoustic signal monitoring points in a water supply network, characterized in that, include: The pipeline topology construction module acquires pipeline data of the water supply network and constructs a pipeline topology map containing node sets and pipe segment sets. The pipeline data includes node information and pipe segment information. The node information includes the node's unique identifier, spatial coordinates, and node type. The node types include pipe connection points, valve wells, fire hydrants, metering facilities, and zone boundary nodes. The candidate monitoring point set construction module selects a set of candidate monitoring points from the node set of the pipeline network topology map, embeds pipe fittings in the water supply network as special nodes into the pipeline network topology map, and assigns attenuation coefficients to pipe segments and pipe fittings in the pipeline network topology map respectively; among them, candidate monitoring points include valve wells, fire hydrants, metering wells and other pipeline reachable points; The minimum cumulative attenuation path calculation module uses the shortest path algorithm to calculate the minimum cumulative attenuation path between any potential leak point and any candidate monitoring point. The minimum cumulative attenuation path is the path with the smallest cumulative attenuation coefficient among all possible propagation paths between the potential leak point and the candidate monitoring point. The leak point set determination module determines the set of leak points that can be covered by each candidate monitoring point based on the comparison results between the minimum cumulative attenuation path and the preset detection threshold. The monitoring point deployment location selection module, under the preset sensor number constraint, uses a greedy optimization algorithm to iteratively select monitoring points from the candidate monitoring point set: at each step, it selects the candidate monitoring point that maximizes the marginal gain of the currently covered leak point set, until the number of selected monitoring points reaches the sensor number constraint or the pipeline coverage rate reaches the preset threshold, and outputs the monitoring point deployment scheme.

10. A computer-readable storage medium for storing one or more programs, characterized in that, The one or more programs include instructions that, when executed by a computing device, cause the computing device to perform any of the methods described in claims 1 to 8.

Images