Intelligent water supply network leakage monitoring and positioning system and method thereof

Abstract

The application provides a smart water supply pipe network leakage monitoring and positioning system and method, relates to the technical field of monitoring and positioning, and is characterized in that information monitoring modules are arranged on the water supply pipe network, information of the water supply pipe network is monitored, water supply pipe network collection data is obtained, the water supply pipe network collection data is subjected to preliminary analysis and processing, and water supply preliminary processing data is obtained; water supply feature analysis and abnormality identification are performed according to the water supply preliminary processing data, water supply feature abnormality identification data is obtained, abnormality analysis and early warning are performed according to the water supply feature abnormality identification data, abnormality analysis and early warning data is obtained; water supply pipe abnormality positioning information is determined according to the abnormality analysis and early warning data, abnormality positioning and repair monitoring are performed according to the water supply pipe abnormality positioning information, positioning and repair monitoring data is obtained, the application can realize the intelligent monitoring and positioning technology of active monitoring, accurate identification, efficient positioning and closed-loop operation and maintenance, and improves the intelligent operation and maintenance level and operation reliability of the water supply pipe network.

Description

Technical Field

[0001] This invention proposes an intelligent water supply network leakage monitoring and location system and method, which relates to the field of monitoring and location technology, specifically to the field of intelligent water supply network leakage monitoring and location technology. Background Technology

[0002] Water supply networks are a crucial component of urban infrastructure, and their stable operation directly impacts residents' lives, industrial production, and the normal functioning of the city. Currently, traditional methods for monitoring leaks in water supply networks largely rely on manual inspections, resulting in passive detection, low efficiency, and high rates of missed and false alarms. Leaks are often only detected after significant damage has occurred, leading to substantial water waste and network damage. Existing monitoring technologies often rely on single parameters, identifying anomalies solely through sound or water pressure thresholds. This makes them susceptible to external interference, resulting in severe false alarms and missed alarms, and they cannot accurately correlate abnormal nodes or differentiate the severity of anomalies. Furthermore, traditional location methods are vague, relying heavily on experience, leading to indiscriminate excavation and repairs that waste human, material, and financial resources. The lack of continuous monitoring after repairs hinders closed-loop management, resulting in a high recurrence rate of leaks. Summary of the Invention

[0003] This invention provides an intelligent water supply network leakage monitoring and location system and method to solve the above-mentioned problems: This invention proposes an intelligent water supply network leakage monitoring and location system and method, the method comprising: S1. Set up an information monitoring module for the water supply network, monitor the water supply network, obtain the collected data of the water supply network, perform preliminary data analysis and processing on the collected data of the water supply network, and obtain preliminary water supply data. S2. Based on the preliminary water supply treatment data, perform water supply characteristic analysis and anomaly identification to obtain water supply characteristic anomaly identification data. Based on the water supply characteristic anomaly identification data, perform anomaly analysis and early warning to obtain anomaly analysis and early warning data. S3. Determine the abnormal location information of the water supply pipe based on the abnormal analysis and early warning data, and carry out abnormal location repair monitoring based on the abnormal location information of the water supply pipe to obtain location repair monitoring data.

[0004] Furthermore, the system includes: The preliminary data processing module is used to set up an information monitoring module for the water supply network, monitor the water supply network, obtain the collected data from the water supply network, perform preliminary data analysis and processing on the collected data from the water supply network, and obtain preliminary water supply data. The water supply anomaly analysis module is used to perform water supply characteristic analysis and anomaly identification based on the preliminary water supply treatment data, obtain water supply characteristic anomaly identification data, perform anomaly analysis and early warning based on the water supply characteristic anomaly identification data, and obtain anomaly analysis and early warning data. The water supply anomaly location module is used to determine the anomaly location information of the water supply pipe based on the anomaly analysis and early warning data, and to perform anomaly location repair monitoring based on the anomaly location information of the water supply pipe, thereby obtaining location repair monitoring data.

[0005] The beneficial effects of this invention are as follows: This method solves the core technical problems of passive detection, low efficiency, ambiguous location, and incomplete repair in traditional water supply network leakage monitoring, achieving proactive monitoring, accurate identification, and efficient repair of water supply network leaks. Through fully automated processing, the timeliness of leakage monitoring is significantly improved, avoiding the problems of missed or false detections caused by traditional manual inspections, and reducing water resource waste and network damage caused by untimely leakage detection. Systematic anomaly analysis and precise location reduce the difficulty and error of leakage location, improving location efficiency and accuracy, and avoiding the waste of manpower, material resources, and financial resources caused by blind excavation and repair. Continuous monitoring after repair ensures that the repair effect meets standards, reducing the probability of leakage recurrence, improving the stability and reliability of water supply network operation, and extending the service life of the network. At the same time, the entire method eliminates the need for complex manual operations, reducing manual maintenance costs and operational difficulty, and improving the intelligent level of water supply network operation and maintenance. Attached Figure Description

[0006] Figure 1 This is a schematic diagram of a smart water supply network leakage monitoring and location method. Detailed Implementation

[0007] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0008] In one embodiment of the present invention, an intelligent water supply network leakage monitoring and location system and method are proposed, the method comprising: S1. Set up an information monitoring module for the water supply network, monitor the water supply network, obtain the collected data of the water supply network, perform preliminary data analysis and processing on the collected data of the water supply network, and obtain preliminary water supply data. S2. Based on the preliminary water supply treatment data, perform water supply characteristic analysis and anomaly identification to obtain water supply characteristic anomaly identification data. Based on the water supply characteristic anomaly identification data, perform anomaly analysis and early warning to obtain anomaly analysis and early warning data. S3. Determine the location information of the water supply pipe anomaly based on the anomaly analysis and early warning data, and conduct anomaly location repair monitoring based on the anomaly location information to obtain location repair monitoring data, such as... Figure 1 As shown.

[0009] The working principle and technical effects of the above-mentioned technical solution are as follows: This method deploys an information monitoring module in the water supply network to achieve comprehensive collection of key information on network operation; the collected raw data undergoes preliminary processing to remove invalid interference, standardize data formats, and ensure data quality; based on the processed data, it focuses on analyzing two core characteristics: water supply sound and water pressure, identifying network operation anomalies, combining anomaly characteristics for analysis and issuing early warnings, and clarifying the suspected anomaly range; based on the early warning information, it conducts precise location, repairs and maintenance are carried out at the located anomaly location, and the repair effect is continuously monitored to ensure that the leakage problem is resolved in a timely and thorough manner. The entire process requires minimal manual intervention, achieving efficient operation of network leakage monitoring and location through automated data collection, intelligent analysis, and precise location.

[0010] This method solves the core technical problems of traditional water supply network leakage monitoring, such as passive detection, low efficiency, vague location, and incomplete repair. It achieves proactive monitoring, accurate identification, and efficient repair of water supply network leaks. Through fully automated processing, it significantly improves the timeliness of leakage monitoring, avoiding the problems of missed or false detections caused by traditional manual inspections, and reducing water resource waste and network damage caused by untimely leakage detection. Systematic anomaly analysis and precise location reduce the difficulty and error of leak location, improving efficiency and accuracy, and avoiding the waste of manpower, materials, and financial resources caused by blind excavation and repair. Continuous monitoring after repair ensures that the repair effect meets standards, reduces the probability of leakage recurrence, improves the stability and reliability of water supply network operation, and extends the service life of the network. At the same time, the entire method eliminates the need for complex manual operations, reducing manual maintenance costs and operational difficulty, and improving the level of intelligence in water supply network operation and maintenance.

[0011] In one embodiment of the present invention, S1 includes: Information monitoring modules are evenly installed in the water supply network. Information is collected from the water supply network through the information monitoring modules to obtain the collected data. Data node location information is obtained by locating data nodes based on data collected from the water supply network. Data node positioning is encoded based on data node positioning information to obtain data node positioning encoding information; Based on the data node location coding information, feature categories are divided to obtain data category feature location coding information; By integrating the data category characteristics, the coded information and its corresponding data, preliminary water treatment data are obtained.

[0012] The working principle and technical effects of the above technical solution are as follows: Information monitoring modules are evenly deployed along the water supply network at preset intervals. These modules integrate sound monitoring, water pressure monitoring, and data transmission functions, enabling real-time collection of key operational information such as water flow sound and pipeline water pressure within the network. Simultaneously, they record the module's own installation location information, summarizing the collected data to form water supply network data. Based on the module location information in the collected data, combined with the geographical distribution of the network, the network nodes corresponding to each monitoring module are spatially located, clarifying the specific location of each node, the corresponding network segment, and other information, thus obtaining data node location information. To achieve precise binding between data and nodes, facilitating rapid retrieval and... Analysis is conducted by assigning a unique code to each monitoring node based on the node location information using a unified coding rule, generating data node location coding information. Based on this coding information, the collected data is categorized according to feature type (e.g., sound data, water pressure data), and a corresponding location coding identifier is added to each category, forming data category feature location coding information, thus binding data, nodes, and feature categories. The categorized coding information and its corresponding data are then integrated, eliminating invalid interference data generated during the collection process, standardizing data formats and units of measurement, and forming standardized preliminary water supply treatment data to ensure data consistency and usability in subsequent analysis. This method solves the technical problems of traditional water supply network data collection, such as disorganization, ambiguous positioning, unclear classification, and poor data quality, achieving standardized and normalized data collection and preliminary processing. By evenly distributing monitoring modules, it ensures comprehensive network monitoring, avoids monitoring blind spots, and improves the coverage and representativeness of data collection. Through data node positioning and coding, it achieves precise identification of each monitoring node and its corresponding data, solving the problems of data and node disconnect and inaccurate traceability, facilitating rapid location of abnormal nodes. Through feature classification and data integration, it eliminates invalid and interfering data, standardizes data formats, improves data quality, and avoids subsequent analysis errors caused by disorganized data and inconsistent formats. Simultaneously, the standardized data processing method reduces the difficulty of data processing and improves the overall operational efficiency of the method.

[0013] In one embodiment of the present invention, S2 includes: Based on the preliminary water treatment data, the sound characteristics of the water supply are analyzed to obtain sound characteristic analysis data; Based on the preliminary water treatment data, water pressure characteristics analysis was performed to obtain water pressure characteristic analysis data. Based on the analysis of sound features and water pressure features, anomalies in the pipeline network are identified and determined to obtain anomaly identification information.

[0014] The working principle and technical effect of the above technical solution are as follows: Accurate identification of water supply network anomalies is achieved through multi-dimensional feature analysis of preliminary water treatment data. Encoded data corresponding to sound categories is extracted from the preliminary water treatment data. Using a professional feature extraction algorithm, core features such as frequency, amplitude, and waveform of the water flow sound are analyzed to determine if any anomalies exist, forming sound feature analysis data. Simultaneously, encoded data corresponding to water pressure categories is extracted from the preliminary water treatment data. Real-time changes, fluctuation amplitude, and abrupt changes in water pressure are analyzed to determine if any anomalies exist, forming water pressure feature analysis data. The sound feature analysis data and water pressure feature analysis data are then fused and analyzed. Combining the anomaly features of both, a collaborative judgment logic is constructed to comprehensively determine whether there is leakage anomaly in the water supply network, the location of the anomaly node, and the type of anomaly, forming anomaly identification judgment information. The entire process, through dual-feature collaborative analysis, avoids the limitations of single-feature analysis and improves the accuracy of anomaly identification.

[0015] This method solves the technical problems of traditional water supply network anomaly identification, such as relying on single-parameter judgment, high false alarm rate, high false negative rate, and inability to accurately determine anomaly type, achieving accurate and efficient identification of network anomalies. By analyzing two core features—sound and water pressure—it fully utilizes the differences in water flow sound between normal and damaged pipes, and the sudden changes in water pressure during leaks, ensuring comprehensive anomaly feature capture. Through dual-feature fusion judgment, it overcomes the limitations of single-parameter recognition, avoiding false alarms and false negatives caused by relying solely on sound or water pressure, thus improving the accuracy and reliability of anomaly identification. It can accurately determine the location and type of anomalies, reducing invalid warnings and blind investigations, and improving the efficiency of network anomaly handling. Simultaneously, the standardized feature analysis process reduces the difficulty of anomaly identification and improves the level of automation.

[0016] In one embodiment of the present invention, the step of performing sound feature analysis on water supply based on preliminary water treatment data to obtain sound feature analysis data includes: Based on the preliminary water supply treatment data, obtain the corresponding data of the sound category feature localization code to obtain the localization sound information; Sound feature data is extracted from the location sound information to obtain sound feature extraction data; Obtain the preset normal pipe sound reference library and the preset abnormal pipe sound reference library; The similarity data between the location sound information and the preset normal pipe sound reference library and the preset abnormal pipe sound reference library are obtained respectively to obtain normal sound similarity data and abnormal sound similarity data. The normal sound similarity data is compared with the abnormal sound similarity data to obtain the sound similarity comparison result; Based on the sound similarity comparison results, the water supply sound feature status is determined by sound category feature localization encoding, and sound feature analysis data is obtained.

[0017] The working principle and technical effect of the above technical solution are as follows: From the preliminary water supply treatment data, based on the sound category feature localization code, all sound-related coded corresponding data are filtered out. These data are associated with specific monitoring nodes, thus obtaining location sound information with node location information, and clarifying the pipeline node corresponding to each sound data; a professional sound feature extraction algorithm (such as short-time Fourier transform) is used to process the location sound information, extracting core feature parameters such as sound frequency, amplitude, waveform, and spectral peak value to obtain sound feature extraction data. These feature parameters can accurately reflect the specific state of water flow sound; and a preset pipeline normal sound benchmark library and pipeline abnormal sound benchmark library are called (both benchmark libraries are based on a large amount of pipeline operation data). The system pre-trains and generates sound feature templates for both normal pipeline operation and leaking conditions. A similarity calculation algorithm is used to calculate the similarity between the location sound information and two benchmark databases, resulting in normal sound similarity data (the degree of matching between the location sound and the normal benchmark database) and abnormal sound similarity data (the degree of matching between the location sound and the abnormal benchmark database). The two similarity datasets are then compared to determine whether the location sound is closer to a normal or abnormal state, yielding a sound similarity comparison result. Based on the comparison result and the location code of the corresponding monitoring node, the water supply sound feature status (normal or abnormal) of that node is determined. The status determination result, similarity data, feature extraction data, and node code are then integrated to form sound feature analysis data.

[0018] This method addresses the technical problems of traditional sound monitoring, which relies solely on threshold judgment, suffers from low accuracy, cannot associate with specific nodes, and experiences severe false alarms and missed alarms. It achieves accurate identification and node association for abnormal water flow sounds in water supply networks. By acquiring location-based sound information, it achieves precise binding of sound data with monitoring nodes, solving the problem of not being able to locate specific nodes for sound anomalies. Through professional feature extraction, it accurately captures the core features of water flow sounds, avoiding the influence of external interference and improving the accuracy of sound feature recognition. By comparing with dual benchmark databases and similarity comparisons, it replaces the traditional single-threshold judgment method, enabling more accurate judgment of sound status and reducing the probability of false alarms and missed alarms caused by unreasonable single-threshold settings, thus improving the reliability of sound anomaly identification. Simultaneously, the entire process is standardized and automated, requiring no manual intervention, reducing the difficulty of manual operation, improving the efficiency of sound feature analysis, and further enhancing the accuracy of the entire anomaly identification system.

[0019] In one embodiment of the present invention, the step of performing water pressure characteristic analysis based on preliminary water treatment data to obtain water pressure characteristic analysis data includes: Based on the preliminary water supply treatment data, obtain the corresponding data of the water pressure category feature location code to obtain the location water pressure information; Water pressure feature data is extracted from the location water pressure information to obtain water pressure feature extraction data; Obtain the preset normal water pressure reference library and the preset abnormal water pressure reference library for pipelines; The similarity data between the location water pressure information and the preset pipeline normal water pressure reference library and the preset pipeline abnormal water pressure reference library are obtained respectively to obtain normal water pressure similarity data and abnormal water pressure similarity data; The normal water pressure similarity data is compared with the abnormal water pressure similarity data to obtain the water pressure similarity comparison result; Based on the water pressure similarity comparison results, the water pressure characteristic status of the water supply is determined by water pressure category feature localization coding, and water pressure characteristic analysis data is obtained.

[0020] The working principle and technical effect of the above technical solution are as follows: Through the process of positioning, extraction, comparison, and judgment, the abnormal state of water pressure in the water supply network is accurately identified, and the corresponding monitoring nodes are associated. From the preliminary water supply data, based on the water pressure category feature positioning code, all data corresponding to the codes related to water pressure are filtered out. These data are associated with specific monitoring nodes, thus obtaining the positioning water pressure information with node positioning information, and clarifying the network node corresponding to each water pressure data. Subsequently, a professional water pressure feature extraction algorithm is used to process the positioning water pressure information, extracting core feature parameters such as real-time water pressure values, fluctuation amplitude, rate of change, and sudden change values. The algorithm focuses on capturing the water pressure sudden change characteristics that occur a few seconds before a pipeline leak, obtaining water pressure feature extraction data. These feature parameters can accurately reflect the operating status of the pipeline water pressure. The algorithm calls the preset pipeline normal water pressure benchmark library and pipeline abnormal water pressure benchmark library (both benchmark libraries are pre-trained and generated based on a large amount of pipeline operation data, and are stored separately). The system generates water pressure characteristic templates for both normal operation and leakage of the storage pipeline, especially those showing a stable water pressure after a sudden change during leakage. A similarity calculation algorithm is used to calculate the similarity between the located water pressure information and two benchmark databases, yielding normal water pressure similarity data (the degree of matching between the located water pressure and the normal benchmark database) and abnormal water pressure similarity data (the degree of matching between the located water pressure and the abnormal benchmark database). The two similarity data are then compared to determine whether the located water pressure is closer to a normal or abnormal state, obtaining the water pressure similarity comparison result. Based on the comparison result and the location code of the corresponding monitoring node, the water pressure characteristic state (normal or abnormal) of that node is determined. The state determination result, similarity data, feature extraction data, and node code are integrated to form water pressure characteristic analysis data.

[0021] This method addresses the technical problems of traditional water pressure monitoring, which relies solely on fixed thresholds, fails to capture sudden water pressure changes, suffers from low accuracy, high false alarm and missed alarm rates, and cannot correlate with specific nodes. It achieves accurate identification and node correlation for water pressure anomalies in water supply networks. By acquiring location-based water pressure information, it achieves precise binding of water pressure data with monitoring nodes, solving the problem of not being able to pinpoint specific nodes for water pressure anomalies, and works synergistically with sound feature analysis. Through professional feature extraction, it accurately captures water pressure fluctuation and abrupt changes, especially the water pressure abrupt change signal during leakage, avoiding the impact of instantaneous errors and improving the accuracy of water pressure feature identification. By comparing two benchmark databases and similarity comparisons, it replaces the traditional single threshold judgment method, enabling more accurate judgment of water pressure status, reducing the probability of false alarms and missed alarms caused by normal water pressure fluctuations, and improving the reliability of water pressure anomaly identification. Simultaneously, the symmetrical process design with sound feature analysis improves the standardization and consistency of the entire feature analysis system, reduces the difficulty of system design and maintenance, provides high-quality water pressure feature data support for dual-feature fusion judgment, and further improves the accuracy of the entire anomaly identification system.

[0022] In one embodiment of the present invention, the step of identifying and determining pipeline anomalies based on sound feature analysis data combined with water pressure feature analysis data to obtain anomaly identification and determination information includes: Based on the sound feature analysis data and the water pressure feature analysis data, the abnormal sound node information and abnormal water pressure node information are determined. The abnormal sound node information is matched with the abnormal water pressure node information to obtain abnormal node matching information. Based on the node anomaly matching information, determine whether a node has no anomaly, a node has a single anomaly, or a node has two anomalies, and obtain node anomaly determination information. Based on the node anomaly determination information, obtain the abnormal sound intensity information and abnormal water pressure intensity information of the node dual anomaly determination; The abnormal sound intensity information and abnormal water pressure intensity information are normalized and weighted to obtain the abnormal intensity coefficient. The node anomaly determination information is combined with the anomaly intensity coefficient to obtain anomaly identification determination information.

[0023] The working principle and technical effect of the above technical solution are as follows: Accurate and comprehensive judgment of water supply network anomalies is achieved through the fusion matching, classification, and intensity quantification of sound and water pressure dual features. Node information judged as abnormal from sound feature analysis data is selected to form abnormal sound node information (including abnormal node code, abnormal sound features, etc.); simultaneously, node information judged as abnormal from water pressure feature analysis data is selected to form abnormal water pressure node information (including abnormal node code, abnormal water pressure features, etc.); subsequently, using the node code as the core, the abnormal sound node information and abnormal water pressure node information are matched to determine whether each abnormal node simultaneously exhibits sound and water pressure anomalies, forming node anomaly matching information (including successfully matched nodes, unmatched nodes, and matching type); based on the node anomaly matching information, each monitoring node is classified: nodes with neither sound nor water pressure anomalies are considered normal, while nodes with only sound or only water pressure anomalies are considered single anomalies. Nodes exhibiting both abnormal sound and abnormal water pressure are considered to have dual anomalies, and these are aggregated to form node anomaly determination information. For nodes determined to have dual anomalies, abnormal sound intensity information (reflecting the severity of the sound anomaly) is extracted from the sound feature analysis data, and abnormal water pressure intensity information (reflecting the severity of the water pressure anomaly) is extracted from the water pressure feature analysis data. Through normalization processing, the abnormal sound intensity and abnormal water pressure intensity are converted to the same order of magnitude. Then, based on the importance of both, reasonable weights are set, and a weighted sum is performed to obtain an anomaly intensity coefficient (the higher the coefficient, the higher the suspicion of node leakage and the more severe the anomaly). The node anomaly determination information (node ​​anomaly type, anomaly node code) is integrated with the anomaly intensity coefficient to form complete anomaly identification and determination information, clarifying the type and severity of each anomaly node.

[0024] This method addresses the technical challenges of traditional pipeline anomaly identification, such as relying on single-feature judgment, high false alarm and false negative rates, inability to differentiate anomaly severity, and inability to accurately pinpoint leaking nodes. It achieves precise classification, node identification, and intensity quantification of pipeline anomalies. By using dual-feature node matching and classification, it effectively distinguishes between single and dual anomalies, avoiding false alarms caused by single-feature anomalies (e.g., sound anomalies may be due to external interference, and water pressure anomalies may be normal fluctuations), improving the accuracy of anomaly judgment, and ensuring that only nodes with dual anomalies are considered key suspected leak nodes, reducing invalid warnings. Quantifying the anomaly intensity coefficient enables precise assessment of anomaly severity, quickly identifying the node with the highest suspected leak, providing priority guidance for subsequent location, and improving location efficiency. Combining node anomaly type with anomaly intensity forms complete anomaly identification and judgment information, solving the problem that traditional anomaly identification can only determine whether an anomaly exists, but cannot provide information on the location and severity of the anomaly. Furthermore, by using a normalized weighted summation method, the weights of sound and water pressure anomalies are balanced, ensuring the rationality of anomaly intensity assessment and further improving the scientific rigor and reliability of anomaly judgment.

[0025] In one embodiment of the present invention, S3 includes: The sound propagation speed information of each information monitoring module is obtained based on the anomaly identification and judgment information; Propagation time difference analysis is performed based on sound propagation speed information to obtain propagation analysis data; Based on the propagation analysis data and anomaly identification judgment information, a deep analysis of monitoring and positioning is performed to obtain the anomaly positioning information of the water supply pipe. Based on the abnormal location information of the water supply pipe, the abnormal location is marked to obtain the abnormal location marking information; Based on the abnormal location marking information, perform abnormal location repair and maintenance to obtain repair and maintenance information; Monitor the repair and maintenance information to obtain location repair monitoring data.

[0026] The working principle and technical effect of the above technical solution are as follows: Relevant data from each monitoring node is extracted from the anomaly identification and judgment information. Combined with parameters such as pipe material and diameter, the sound propagation speed information within the pipe corresponding to each information monitoring module is determined (sound propagation speed is affected by pipe material and diameter, requiring specific determination). Based on the sound propagation speed information, the propagation time difference of the leaking sound between different monitoring nodes is analyzed. Combined with the node spacing, the preliminary distance from the leak point to each monitoring node is calculated, and integrated to form propagation analysis data. The propagation analysis data is fused with the anomaly identification and judgment information (especially the anomaly intensity coefficient and information on dual anomaly nodes) to conduct deep positioning analysis, correct positioning errors, determine the specific location of the leak point, the pipe burial depth, and the extent of damage, and obtain... Water supply pipe anomaly location information; based on the anomaly location information, the anomaly location is accurately marked on the pipeline network geographical distribution map, clarifying the specific coordinates of the leak point, the distribution of surrounding pipelines, and other information, forming anomaly location marking information to provide intuitive guidance for repair and maintenance; staff go to the site to carry out leak repair and pipeline maintenance work according to the anomaly location marking information, recording information such as repair plan, repair process, and maintenance measures, forming repair and maintenance information; after the repair is completed, the pipeline network operation status (sound, water pressure) in the repair area is continuously monitored through the information monitoring module, collecting post-repair operation data to form location repair monitoring data, judging whether the repair effect meets the standards, if not, the repair work is restarted to ensure that the leak problem is completely resolved, forming a complete closed-loop management.

[0027] This method solves the technical problems of traditional water supply network leak location, blind repair, inability to verify repair effects, and lack of closed-loop management, achieving precise leak location, efficient repair, and long-term operation and maintenance. By using sound propagation time difference analysis and depth positioning, it overcomes the inaccuracy of single-parameter positioning, improving the accuracy and efficiency of leak location, avoiding resource waste caused by blind excavation and repair, and reducing repair costs. Anomaly location marking provides intuitive and accurate guidance for repair and maintenance, improving the efficiency and standardization of repair work. Through repair, maintenance, and continuous monitoring, a closed-loop management system is formed, ensuring that leak problems are completely resolved, reducing the probability of leak recurrence, and improving the stability of the water supply network. Simultaneously, by collecting repair and maintenance information and location and repair monitoring data, the intelligence level and reliability of the entire monitoring and positioning system are further improved, extending the service life of the water supply network and reducing water resource waste and losses caused by network damage.

[0028] In one embodiment of the present invention, the step of performing propagation time difference analysis based on sound propagation speed information to obtain propagation analysis data includes: Based on the anomaly identification information, identify the abnormal leakage nodes, obtain the difference in anomaly intensity coefficient between adjacent abnormal leakage nodes, and obtain the adjacent anomaly difference coefficient. Acquire sound feature analysis data for each abnormal flow node to determine sound propagation speed information; Calculate the difference in sound propagation speed between adjacent abnormal leakage nodes, and then calculate the preliminary distance from the leakage point to each abnormal water flow node. By integrating information on the speed of sound propagation and the initial distance, propagation analysis data is obtained.

[0029] The working principle and technical effect of the above technical solution are as follows: Nodes identified as abnormal (i.e., abnormal leaking nodes) are selected from the anomaly identification and judgment information, with a focus on dual-abnormal nodes. Anomaly intensity coefficients between adjacent abnormal leaking nodes are extracted, and the difference between the two is calculated to obtain the adjacent anomaly difference coefficient (the larger the difference, the greater the difference in the suspicion of leakage between adjacent nodes, which can be used as a reference for location correction). From the sound feature analysis data of each abnormal leaking node, sound propagation-related feature parameters are extracted. Combined with parameters such as the pipe material and diameter corresponding to the node, the sound propagation speed information within the pipe at each abnormal leaking node is determined. (Pipe parameters may differ at different nodes, so the sound propagation speed needs to be determined separately); Calculate the difference in sound propagation speed between adjacent abnormal leak nodes, correct the calculation error of sound propagation time, and then, based on the sound propagation speed in the pipe, the propagation time difference between adjacent nodes, and the node spacing, calculate the preliminary distance from the leak point to each abnormal leak node using a geometric algorithm (the preliminary distance provides a basic range for location and needs further correction later); Integrate the sound propagation speed information of each abnormal leak node, the preliminary distance from the leak point to that node, and the adjacent abnormality difference coefficient to form propagation analysis data.

[0030] This method addresses the technical problems of traditional propagation time difference analysis (PTD) that fail to consider differences in node anomaly intensity, use uniformly set sound propagation speeds, and suffer from large errors in preliminary distance calculations, thus improving the accuracy of TPD analysis. By determining the difference coefficient between adjacent anomalies, the method incorporates anomaly intensity differences into TPD analysis, helping to narrow the positioning range and reduce positioning errors. By determining the sound propagation speed for each anomaly node separately, it avoids errors caused by uniformly setting propagation speeds, improving the accuracy of propagation time and preliminary distance calculations. By calculating the difference in propagation speeds between adjacent nodes and correcting the preliminary distance, the method further reduces calculation errors and ensures the reliability of the preliminary distance data. Integrating sound propagation speed, preliminary distance, and the difference coefficient between adjacent anomalies into propagation analysis data effectively improves the accuracy of subsequent positioning and overcomes the problem of inaccurate positioning with a single parameter.

[0031] In one embodiment of the present invention, the step of performing monitoring and positioning depth analysis based on propagation analysis data and anomaly identification judgment information to obtain abnormal positioning information of the water supply pipe includes: Extract the corresponding node location coding information from the propagation analysis data and anomaly identification and judgment information; Based on the node coding information and associated data node location information, the spatial location information of each abnormal leakage node is determined. Combined with the sound propagation speed information, the initial distance from the leakage point to each node is corrected to obtain the corrected distance data. Based on the spatial coordinates of each abnormal leakage node, and combined with the corrected distance data, a three-dimensional spatial positioning model is constructed. Based on the anomaly intensity coefficient, the three-dimensional spatial positioning model is weighted and optimized to determine the weighted optimization information; Based on the results of the double anomaly detection of nodes, the corrected distance data corresponding to the double anomaly nodes are selected; The weighted optimization information and the corrected distance data are used to generate abnormal location information for the water supply pipe.

[0032] The working principle and technical effects of the above technical solution are as follows: Node positioning codes corresponding to data such as sound propagation speed and preliminary distance are extracted from propagation analysis data; abnormal node codes, abnormal intensity coefficients, and node dual-abnormality judgment results are extracted from anomaly identification and judgment information to ensure accurate correlation between the two types of data through node coding; based on the node coding information, the node positioning information of the associated data is determined, clarifying the specific spatial coordinates, corresponding pipe material, diameter, and other parameters of each abnormal leak node; combined with the sound propagation speed information in the propagation analysis data, the preliminary distance from the leak point to each node is corrected, eliminating the influence of pipe material, diameter, and spatial location on the sound propagation speed and distance calculation, obtaining corrected distance data (the corrected distance data is more accurate than the preliminary distance, providing core data for positioning); using the spatial coordinates of each abnormal leak node as a benchmark, the corrected distance data is integrated into three-dimensional spatial modeling technology to construct a three-dimensional spatial positioning model, initially delineating the leak... The spatial range of the water point visually presents the spatial relationship between the leak point and each monitoring node. Based on the anomaly intensity coefficient in the anomaly identification and judgment information, the three-dimensional spatial positioning model is weighted and optimized. The higher the anomaly intensity coefficient of the node (the higher the suspicion of leakage), the greater the weight of its corresponding corrected distance data, highlighting the role of core positioning data and determining the weighted optimization information (the role of the weighted optimization information is to narrow the positioning range of the leak point and reduce positioning deviation). Based on the results of the dual anomaly judgment of the nodes, the corrected distance data corresponding to the dual anomaly nodes are selected as the core positioning basis, and the corrected distance data of single anomaly nodes are removed (single anomaly nodes may have interference, and removing them can further improve positioning accuracy). The weighted optimization information is fused with the selected corrected distance data, combined with the three-dimensional spatial positioning model, to determine the specific spatial coordinates of the leak point, the pipe burial depth, and the estimated range of the damaged area. This information is then integrated to generate complete water supply pipe anomaly positioning information.

[0033] This method solves the technical problems of traditional leak location methods, such as large positioning errors, weak anti-interference capabilities, inability to accurately pinpoint the specific location of leaks, and incomplete positioning results. It achieves accurate and comprehensive positioning of leaks in water supply networks. By using node coding association and distance correction, the influence of pipeline parameters and spatial location on positioning is eliminated, improving the accuracy of distance data. By constructing a three-dimensional spatial positioning model, abstract distance data is transformed into an intuitive spatial range, making it easier for staff to quickly understand the approximate location of the leak and improving the intuitiveness of positioning. Through anomaly intensity coefficient weighted optimization, the role of nodes with high suspicion of leaks is highlighted, solving the positioning deviation problem caused by multi-node data conflicts, narrowing the positioning range, and improving positioning accuracy. By filtering the core data corresponding to dual-abnormal nodes, the interference of single-abnormal nodes is eliminated, further improving the anti-interference capability and accuracy of positioning and avoiding positioning deviations caused by interference data. The final generated water supply pipe anomaly positioning information includes complete information such as the specific coordinates of the leak point, pipeline burial depth, and damage range, solving the problem that traditional positioning can only provide an approximate range and cannot meet the needs of precise repair, reducing the difficulty and cost of repair and improving repair efficiency.

[0034] According to one embodiment of the present invention, the system includes: The preliminary data processing module is used to set up an information monitoring module for the water supply network, monitor the water supply network, obtain the collected data from the water supply network, perform preliminary data analysis and processing on the collected data from the water supply network, and obtain preliminary water supply data. The water supply anomaly analysis module is used to perform water supply characteristic analysis and anomaly identification based on the preliminary water supply treatment data, obtain water supply characteristic anomaly identification data, perform anomaly analysis and early warning based on the water supply characteristic anomaly identification data, and obtain anomaly analysis and early warning data. The water supply anomaly location module is used to determine the anomaly location information of the water supply pipe based on the anomaly analysis and early warning data, and to perform anomaly location repair monitoring based on the anomaly location information of the water supply pipe, thereby obtaining location repair monitoring data.

[0035] The working principle and technical effects of the above-mentioned technical solution are as follows: This method deploys an information monitoring module in the water supply network to achieve comprehensive collection of key information on network operation; the collected raw data undergoes preliminary processing to remove invalid interference, standardize data formats, and ensure data quality; based on the processed data, it focuses on analyzing two core characteristics: water supply sound and water pressure, identifying network operation anomalies, combining anomaly characteristics for analysis and issuing early warnings, and clarifying the suspected anomaly range; based on the early warning information, it conducts precise location, repairs and maintenance are carried out at the located anomaly location, and the repair effect is continuously monitored to ensure that the leakage problem is resolved in a timely and thorough manner. The entire process requires minimal manual intervention, achieving efficient operation of network leakage monitoring and location through automated data collection, intelligent analysis, and precise location.

[0036] This method solves the core technical problems of traditional water supply network leakage monitoring, such as passive detection, low efficiency, vague location, and incomplete repair. It achieves proactive monitoring, accurate identification, and efficient repair of water supply network leaks. Through fully automated processing, it significantly improves the timeliness of leakage monitoring, avoiding the problems of missed or false detections caused by traditional manual inspections, and reducing water resource waste and network damage caused by untimely leakage detection. Systematic anomaly analysis and precise location reduce the difficulty and error of leak location, improving efficiency and accuracy, and avoiding the waste of manpower, materials, and financial resources caused by blind excavation and repair. Continuous monitoring after repair ensures that the repair effect meets standards, reduces the probability of leakage recurrence, improves the stability and reliability of water supply network operation, and extends the service life of the network. At the same time, the entire method eliminates the need for complex manual operations, reducing manual maintenance costs and operational difficulty, and improving the level of intelligence in water supply network operation and maintenance.

[0037] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for detecting and locating leaks in an intelligent water supply network, characterized in that, The method includes: S1. Set up an information monitoring module for the water supply network, monitor the water supply network, obtain the collected data of the water supply network, perform preliminary data analysis and processing on the collected data of the water supply network, and obtain preliminary water supply data. S2. Based on the preliminary water supply treatment data, perform water supply characteristic analysis and anomaly identification to obtain water supply characteristic anomaly identification data. Based on the water supply characteristic anomaly identification data, perform anomaly analysis and early warning to obtain anomaly analysis and early warning data. S3. Determine the abnormal location information of the water supply pipe based on the abnormal analysis and early warning data, and carry out abnormal location repair monitoring based on the abnormal location information of the water supply pipe to obtain location repair monitoring data.

2. The intelligent water supply network leakage monitoring and location method according to claim 1, characterized in that, S1 includes: Information monitoring modules are evenly installed in the water supply network. Information is collected from the water supply network through the information monitoring modules to obtain the collected data. Data node location is determined by collecting data from the water supply network to obtain data node location information. Data node positioning is encoded based on data node positioning information to obtain data node positioning encoding information; Based on the data node location coding information, feature categories are divided to obtain data category feature location coding information; By integrating the data category characteristics, the coded information and its corresponding data, preliminary water treatment data are obtained.

3. The intelligent water supply network leakage monitoring and location method according to claim 1, characterized in that, S2 includes: Based on the preliminary water treatment data, the sound characteristics of the water supply are analyzed to obtain sound characteristic analysis data; Based on the preliminary water treatment data, water pressure characteristics analysis was performed to obtain water pressure characteristic analysis data. Based on the analysis of sound features and water pressure features, anomalies in the pipeline network are identified and determined to obtain anomaly identification information.

4. The intelligent water supply network leakage monitoring and location method according to claim 3, characterized in that, The step of performing sound characteristic analysis on the water supply based on the preliminary water treatment data to obtain sound characteristic analysis data includes: Based on the preliminary water supply treatment data, obtain the corresponding data of the sound category feature localization code to obtain the localization sound information; Sound feature data is extracted from the location sound information to obtain sound feature extraction data; Obtain the preset normal pipe sound reference library and the preset abnormal pipe sound reference library; The similarity data between the location sound information and the preset normal pipe sound reference library and the preset abnormal pipe sound reference library are obtained respectively to obtain normal sound similarity data and abnormal sound similarity data. The normal sound similarity data is compared with the abnormal sound similarity data to obtain the sound similarity comparison result; Based on the sound similarity comparison results, the water supply sound feature status is determined by sound category feature localization encoding, and sound feature analysis data is obtained.

5. The intelligent water supply network leakage monitoring and location method according to claim 3, characterized in that, The step of performing water pressure characteristic analysis based on preliminary water treatment data to obtain water pressure characteristic analysis data includes: Based on the preliminary water supply treatment data, obtain the corresponding data of the water pressure category feature location code to obtain the location water pressure information; Water pressure feature data is extracted from the location water pressure information to obtain water pressure feature extraction data; Obtain the preset normal water pressure reference library and the preset abnormal water pressure reference library for pipelines; The similarity data between the location water pressure information and the preset pipeline normal water pressure reference library and the preset pipeline abnormal water pressure reference library are obtained respectively to obtain normal water pressure similarity data and abnormal water pressure similarity data; The normal water pressure similarity data is compared with the abnormal water pressure similarity data to obtain the water pressure similarity comparison result; Based on the water pressure similarity comparison results, the water pressure characteristic status of the water supply is determined by water pressure category feature localization coding, and water pressure characteristic analysis data is obtained.

6. The intelligent water supply network leakage monitoring and location method according to claim 3, characterized in that, The step of identifying and determining pipeline anomalies based on sound feature analysis data combined with water pressure feature analysis data, and obtaining anomaly identification and determination information, includes: Based on the sound feature analysis data and the water pressure feature analysis data, the abnormal sound node information and abnormal water pressure node information are determined. The abnormal sound node information is matched with the abnormal water pressure node information to obtain abnormal node matching information. Based on the node anomaly matching information, determine whether a node has no anomaly, a node has a single anomaly, or a node has two anomalies, and obtain node anomaly determination information. Based on the node anomaly determination information, obtain the abnormal sound intensity information and abnormal water pressure intensity information of the node dual anomaly determination; The abnormal sound intensity information and abnormal water pressure intensity information are normalized and weighted to obtain the abnormal intensity coefficient. The node anomaly determination information is combined with the anomaly intensity coefficient to obtain anomaly identification determination information.

7. The intelligent water supply network leakage monitoring and location method according to claim 1, characterized in that, S3 includes: The sound propagation speed information of each information monitoring module is obtained based on the anomaly identification and judgment information; Propagation time difference analysis is performed based on sound propagation speed information to obtain propagation analysis data; Based on the propagation analysis data and anomaly identification judgment information, a deep analysis of monitoring and positioning is performed to obtain the anomaly positioning information of the water supply pipe. Based on the abnormal location information of the water supply pipe, the abnormal location is marked to obtain the abnormal location marking information; Based on the abnormal location marking information, perform abnormal location repair and maintenance to obtain repair and maintenance information; Monitor the repair and maintenance information to obtain location repair monitoring data.

8. The intelligent water supply network leakage monitoring and location method according to claim 7, characterized in that, The step of performing propagation time difference analysis based on sound propagation speed information to obtain propagation analysis data includes: Based on the anomaly identification information, identify the abnormal leakage nodes, obtain the difference in anomaly intensity coefficient between adjacent abnormal leakage nodes, and obtain the adjacent anomaly difference coefficient. Acquire sound feature analysis data for each abnormal flow node to determine sound propagation speed information; Calculate the difference in sound propagation speed between adjacent abnormal leakage nodes, and then calculate the preliminary distance from the leakage point to each abnormal water flow node. By integrating information on the speed of sound propagation and the initial distance, propagation analysis data is obtained.

9. The intelligent water supply network leakage monitoring and location method according to claim 7, characterized in that, The step of performing depth analysis of monitoring and positioning based on propagation analysis data and anomaly identification judgment information to obtain anomaly positioning information of the water supply pipe includes: Extract the corresponding node location coding information from the propagation analysis data and anomaly identification and judgment information; Based on the node coding information and associated data node location information, the spatial location information of each abnormal leakage node is determined. Combined with the sound propagation speed information, the initial distance from the leakage point to each node is corrected to obtain the corrected distance data. Based on the spatial coordinates of each abnormal leakage node, and combined with the corrected distance data, a three-dimensional spatial positioning model is constructed. Based on the anomaly intensity coefficient, the three-dimensional spatial positioning model is weighted and optimized to determine the weighted optimization information; Based on the results of the node dual anomaly determination, the corrected distance data corresponding to the dual anomaly nodes are selected; The weighted optimization information and the corrected distance data are used to generate abnormal location information for the water supply pipe.

10. A smart water supply network leakage monitoring and location system, characterized in that, The system includes: The preliminary data processing module is used to set up an information monitoring module for the water supply network, monitor the water supply network, obtain the collected data from the water supply network, perform preliminary data analysis and processing on the collected data from the water supply network, and obtain preliminary water supply data. The water supply anomaly analysis module is used to perform water supply characteristic analysis and anomaly identification based on the preliminary water supply treatment data, obtain water supply characteristic anomaly identification data, perform anomaly analysis and early warning based on the water supply characteristic anomaly identification data, and obtain anomaly analysis and early warning data. The water supply anomaly location module is used to determine the anomaly location information of the water supply pipe based on the anomaly analysis and early warning data, and to perform anomaly location repair monitoring based on the anomaly location information of the water supply pipe, thereby obtaining location repair monitoring data.

Images