Pipe network online leakage positioning method based on data fusion and intelligent optimization algorithm

Abstract

The invention provides a pipe network online leakage locating method based on data fusion and an intelligent optimization algorithm. Whether leakage occurs in a raw water pipe network or not is judged through water balance analysis; carrying out Kalman filtering processing on the collected flow data, and removing noise; constructing a raw water pipe network hydraulic model, and solving a leakage position by using an improved grey wolf optimization algorithm; and synchronously operating the two leakage positioning schemes, and judging the validity of positioning results through consistency comparison of the positioning results. According to the method, the accuracy and robustness of leakage positioning can be improved, and the leakage of the raw water pipe network can be rapidly and accurately detected.

Description

Technical Field

[0001] The present application belongs to the technical field of raw water pipe network leakage detection, and relates to an online pipe network leakage positioning method based on data fusion and intelligent optimization algorithm. Background Art

[0002] In urban water supply systems, raw water pipelines are a critical link connecting water sources with water plants or end users, fulfilling the crucial task of transporting raw water. However, leakage is a common problem in these networks over long-term operation. This not only wastes significant water resources but also poses a series of safety risks, such as ground subsidence and water pollution, posing a serious threat to urban infrastructure and the safety of residents' drinking water.

[0003] Traditional raw water pipeline leakage detection relies primarily on manual inspections and simple monitoring equipment. Manual inspections require significant manpower and time, and are limited by inspectors' experience and environmental factors. Leak detection often lags behind, making it difficult to detect hidden leaks in a timely manner. Furthermore, while simple monitoring equipment can assist with detection to a certain extent, it suffers from low accuracy, high false alarm rates, and inability to provide real-time monitoring of leaks. This makes it difficult to meet the efficiency and accuracy requirements of modern urban water supply systems.

[0004] With the development of science and technology, leak detection technologies based on sensor networks and data analysis have gradually emerged. These technologies deploy sensors in the pipeline network to collect real-time pipeline operation data and process the data using data analysis algorithms to achieve preliminary leakage detection. However, existing technologies still have many shortcomings when dealing with complex raw water environment pipeline networks:

[0005] (1) Positioning accuracy is not high:

[0006] Raw water pipeline networks are typically large in scale, with complex pipeline layouts and variable operating conditions. Furthermore, they contain a significant amount of data noise, such as pressure fluctuations and flow rate variations. These factors interfere with leak detection accuracy, making it difficult to pinpoint the exact location of leaks using existing technologies.

[0007] (2) Lack of robustness:

[0008] In complex pipe network environments, existing technologies are susceptible to data noise and fluctuating operating conditions, resulting in unstable detection results and the possibility of missed or false positives. This instability significantly reduces the reliability of leak detection, making it difficult to meet the high robustness requirements of urban water supply systems.

[0009] (3) Unable to monitor in real time:

[0010] While existing technologies can provide some leakage detection capabilities, they still lack real-time capabilities. Leakage conditions can change at any time, and existing technologies cannot provide real-time feedback on these dynamic changes. This results in leakage issues being delayed, increasing the risk of water waste and safety hazards.

[0011] Therefore, existing raw water pipeline leakage detection technologies, whether traditional manual inspections and simple monitoring equipment or advanced technologies based on sensor networks and data analysis, suffer from low efficiency, low positioning accuracy, insufficient robustness, and the inability to monitor in real time. These issues severely restrict the efficient operation of urban water supply systems and the rational use of water resources, while also failing to effectively ensure the safety and stability of water supply systems.

[0012] Therefore, developing an efficient, accurate and robust online leakage location method for raw water pipe networks has important practical significance and broad application prospects for solving the shortcomings of existing technologies, reducing leakage rates, ensuring the rational use of water resources and eliminating safety hazards. Summary of the Invention

[0013] The present application provides an online leakage location method for a pipeline network based on data fusion and intelligent optimization algorithm, which is used to solve the problems of low efficiency, low positioning accuracy, insufficient robustness and inability to monitor in real time in existing raw water pipeline leakage detection technologies, whether traditional manual inspections and simple monitoring equipment, or advanced technologies based on sensor networks and data analysis.

[0014] In the first aspect, the present application provides an online leakage positioning method for a pipeline network based on data fusion and intelligent optimization algorithm, comprising the following steps: obtaining first basic data of the raw water pipeline network; the first basic data of the raw water pipeline network includes: inlet flow, outlet flow, and change in inlet and outlet water of the pipeline network; performing water balance analysis based on the first basic data of the raw water pipeline network, obtaining a first leakage amount in a certain independent metering area, and judging whether leakage occurs in the raw water pipeline network; filtering the leakage amount in the independent metering area to obtain a first leakage estimate value in the independent metering area; constructing a hydraulic model of the raw water pipeline network based on the first leakage estimate value, and adopting an improved gray wolf optimization algorithm to obtain a first leakage location; calculating a second leakage estimate value and a second leakage location based on the second basic data of the raw water pipeline network; comparing the first leakage estimate value and the first leakage location with the second leakage estimate value and the second leakage location to determine the final leakage location and leakage amount.

[0015] In this application, by combining two leakage location schemes and running them synchronously, and by comparing the consistency of the positioning results, the robustness of the algorithm is effectively enhanced, enabling it to operate stably in complex data environments.

[0016] In an implementation of the first aspect, a water balance analysis is performed based on the basic data of the raw water network, the leakage amount in a certain independent metering area is obtained, and it is determined whether the raw water network has leakage, including: determining whether the raw water network has leakage through water balance analysis; including: within a certain time period, when the water inlet flow of the raw water network is greater than or equal to the sum of the water outlet flow of the raw water network and the change in the water inlet and outflow of the network, determining that the raw water network may have leakage, and calculating the leakage amount in a certain independent metering area; when the water inlet flow of the raw water network is less than the sum of the water outlet flow of the raw water network and the change in the water inlet and outflow of the network, determining that the leakage of the raw water network is within a normal range.

[0017] In an implementation of the first aspect, filtering the leakage amount within the independent metering area to obtain a first leakage estimate value within the independent metering area includes: predicting the leakage amount within the independent metering area at a certain moment to obtain a leakage estimate value within the independent metering area at a next moment; obtaining a Kalman gain matrix based on the leakage estimate value within the independent metering area at the next moment; and updating the prediction based on the Kalman gain matrix to obtain a filtered first leakage estimate value at the next moment.

[0018] In this implementation, the data is denoised through water balance analysis and Kalman filtering algorithm, thereby improving the accuracy of leakage identification.

[0019] In an implementation of the first aspect, a hydraulic model of the raw water network is constructed based on the first leakage estimate value, and an improved grey wolf optimization algorithm is used to obtain the first leakage location, including: fitting based on the first leakage estimate value to construct a hydraulic model of the raw water network; using the improved grey wolf optimization algorithm to iteratively update the position of the first leakage estimate value to obtain an updated first leakage area; using a retrieval model to search and optimize the position of the first leakage area to obtain the first leakage location.

[0020] In this implementation, the improved Grey Wolf optimization algorithm is used to solve the leakage location, which further improves the accuracy of locating the leakage point in the pipeline network.

[0021] In an implementation of the first aspect, fitting is performed based on the first leakage estimation value to construct a hydraulic model of the raw water network, including: fitting with the goal of minimizing the mean square error between the monitoring value and the simulation value at the pressure measuring point when the leakage occurs, to construct a hydraulic model of the raw water network for online leakage positioning.

[0022] In an implementation of the first aspect, an improved gray wolf optimization algorithm is used to iteratively update the position of the first leakage estimate to obtain an updated first leakage area, including: using the improved gray wolf optimization algorithm to initialize the population and set population parameters; the population parameters include: population size, maximum number of iterations, and random vector parameters; based on the population parameters, the fitness of each gray wolf individual in the population is obtained; the position of the first leakage estimate is updated according to the maximum number of iterations and the fitness to obtain an updated first leakage area.

[0023] In an implementation of the first aspect, a retrieval model is used to search and optimize the position of the first leakage area to obtain the first leakage position, including: using the L2 norm to calculate and obtain the distance between the current position of the gray wolf and the updated gray wolf position; constructing a neighboring gray wolf group based on the distance between the current position of the gray wolf and the updated gray wolf position; updating the position based on the neighboring gray wolf group to obtain an updated gray wolf position; comparing the updated gray wolf position and fitness value with the fitness of the position obtained through neighboring learning, updating the gray wolf position to the position with the best fitness, and using the position with the best fitness as the first leakage position.

[0024] In an implementation of the first aspect, the first leakage estimate value and the first leakage location are compared with the second leakage amount estimate value and the second leakage location to determine the final leakage location and leakage amount, including: presetting a leakage threshold; when the difference between the first leakage estimate value and the first leakage location and the second leakage amount estimate value and the second leakage location is less than or equal to the leakage threshold, the leakage estimate value and the leakage location are determined to be the final leakage positioning result; when the difference between the first leakage estimate value and the first leakage location and the second leakage amount estimate value and the second leakage location is greater than the leakage threshold, the leakage estimate value and the leakage location are determined to be the final leakage positioning result.

[0025] In this implementation, the operating status of the raw water network can be monitored in real time, leakage events can be quickly responded to, the leakage location can be located in time, time can be gained for leakage repair, and the waste of water resources and potential safety risks can be reduced.

[0026] In the second aspect, the present application provides an online leakage positioning system for a pipeline network based on data fusion and intelligent optimization algorithm, the system including: a data acquisition module for acquiring first basic data of the raw water pipeline network; the first basic data of the raw water pipeline network includes: inlet flow, outlet flow, and change in inlet and outlet water of the pipeline network; a leakage judgment module for performing water balance analysis based on the first basic data of the raw water pipeline network, obtaining a first leakage amount in a certain independent metering area, and judging whether a leakage occurs in the raw water pipeline network; a data filtering module for filtering the leakage amount in the independent metering area to obtain a first leakage estimate value in the independent metering area; a first leakage positioning module for constructing a hydraulic model of the raw water pipeline network based on the first leakage estimate value, and obtaining a first leakage location by adopting an improved grey wolf optimization algorithm; a second leakage positioning module for calculating a second leakage estimate value and a second leakage location based on the second basic data of the raw water pipeline network; a scheme comparison module for comparing the first leakage estimate value and the first leakage location with the second leakage estimate value and the second leakage location to determine the final leakage location and leakage amount.

[0027] In a third aspect, the present application provides an electronic device, a memory for storing a computer program;

[0028] A processor is used to execute the computer program stored in the memory so that the electronic device executes the pipeline online leakage positioning method based on data fusion and intelligent optimization algorithm.

[0029] As described above, the method for online pipe network leakage location based on data fusion and intelligent optimization algorithm described in this application has the following beneficial effects:

[0030] The online leakage location method for raw water pipe network based on Kalman filtering and improved gray wolf optimization algorithm provided by this application can reduce noise on data through water balance analysis and Kalman filtering algorithm, thereby improving the accuracy of leakage identification. At the same time, the improved gray wolf optimization algorithm is used to solve the leakage location, further improving the positioning accuracy; this application combines two leakage location schemes for synchronous operation, and through consistency comparison of positioning results, effectively enhances the robustness of the algorithm, enabling it to operate stably in complex data environments; at the same time, this application can monitor the operating status of the raw water pipe network in real time, quickly respond to leakage events, and locate the leakage location in time, buying time for leakage repair, reducing the waste of water resources and potential safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 Displayed is a scene diagram of the pipeline online leakage location method based on data fusion and intelligent optimization algorithm described in this application.

[0032] Figure 2Shown is a schematic diagram of the overall process of an embodiment of the method for online leakage location in a pipeline network based on data fusion and intelligent optimization algorithm described in this application.

[0033] Figure 3 Shown is a technical path diagram of a raw water pipe network online leakage location model based on Kalman filtering and improved Grey Wolf optimization algorithm in one embodiment of the pipe network online leakage location method based on data fusion and intelligent optimization algorithm described in this application.

[0034] Figure 4 Shown is a water balance analysis diagram of an embodiment of the online leakage location method for a pipe network based on data fusion and intelligent optimization algorithm described in this application.

[0035] Figure 5 Shown is a flow chart of S3 in the pipeline online leakage location method based on data fusion and intelligent optimization algorithm described in this application.

[0036] Figure 6 Shown is a schematic diagram of the Kalman filtering process of the leakage amount in one embodiment of the online leakage location method for a pipeline network based on data fusion and intelligent optimization algorithm described in this application.

[0037] Figure 7 Shown is a flow chart of S4 in the pipeline online leakage location method based on data fusion and intelligent optimization algorithm described in this application.

[0038] Figure 8 Shown is a flow chart of an improved Grey Wolf optimization algorithm in one embodiment of the method for online leakage location in a pipe network based on data fusion and intelligent optimization algorithm described in this application.

[0039] Figure 9 Shown is a flow chart of S42 in the pipeline online leakage location method based on data fusion and intelligent optimization algorithm described in this application.

[0040] Figure 10 Shown is a flow chart of S43 in the pipeline online leakage location method based on data fusion and intelligent optimization algorithm described in this application.

[0041] Figure 11 Shown is a schematic diagram of the principle structure of an online pipeline leakage location system based on data fusion and intelligent optimization algorithm described in this application in one embodiment.

[0042] Figure 12 Shown is a structural schematic diagram of an electronic device described in an embodiment of the present application.

[0043] Component number description

[0044] 1 Pipeline network online leakage location device based on data fusion and intelligent optimization algorithm

[0045] 100 sensor devices

[0046] 200 Communication transmission module

[0047] 300 cloud servers

[0048] 400 Control Terminal

[0049] 111 Data Acquisition Module

[0050] 112 Leakage Judgment Module

[0051] 113 Data Filtering Module

[0052] 114 First leakage location module

[0053] 115 Second leakage location module

[0054] 116 Solution Comparison Module

[0055] 120 Electronic Equipment

[0056] 121 Memory

[0057] 122 processors

[0058] 123 Display

[0059] Steps S1 to S6 DETAILED DESCRIPTION

[0060] The following describes the embodiments of the present application through specific examples. Those skilled in the art can easily understand the other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0061] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0062] See also Figure 1, showing a scenario diagram of the method for online pipe network leakage location based on data fusion and intelligent optimization algorithm described in this application. The following embodiments of this application provide an online pipe network leakage location device based on data fusion and intelligent optimization algorithm, including: a sensor device 100, a communication transmission module 200, a cloud server 300, and a control terminal 400.

[0063] In one embodiment, the sensing equipment is installed at key nodes of the raw water pipeline to monitor the flow rate, pressure, vibration, and other data of the raw water pipeline in real time. The sensing equipment may include pressure sensors, flow sensors, acoustic / vibration sensors, water quality sensors, and other devices. The pressure sensors are installed at key nodes in the pipeline to monitor changes in water pressure in real time, providing basic data for leak detection. The flow sensors are deployed at the pipeline inlet / outlet to monitor changes in water flow and assist in determining leak conditions. The acoustic / vibration sensors are distributed along the pipeline to capture acoustic or vibration signals generated by leaks, improving the accuracy of leak location. The water quality sensors monitor changes in water quality, indirectly reflecting the pipeline status and providing a reference for leak warning.

[0064] The communication transmission module configures wireless network parameters according to the on-site environment to ensure stable and efficient data transmission.

[0065] The cloud server is used for real-time state estimation, dynamic optimization of leakage location search space, and visualization of three-dimensional pipe network leakage probability maps.

[0066] The control terminal 400 is used for functional testing, performance testing and field verification to ensure that the system meets the design requirements; and to establish a regular inspection, troubleshooting and upgrade maintenance mechanism to ensure the long-term stable operation of the system.

[0067] This application proposes an online water network leakage location device based on data fusion and intelligent optimization algorithms. By integrating sensing, edge computing, and cloud computing, this device enables real-time monitoring and efficient management of raw water networks. This device not only improves the accuracy and efficiency of leak detection but also provides strong support for the intelligent operation and maintenance of water networks.

[0068] The technical solutions in the embodiments of the present application will be described in detail below with reference to the accompanying drawings in the embodiments of the present application.

[0069] See also Figure 2 、 Figure 3 , which respectively show the overall process diagram of the online leakage positioning method for a pipe network based on data fusion and intelligent optimization algorithm in one embodiment described in the present application, and the technical path diagram of the online leakage positioning model for a raw water pipe network based on Kalman filtering and improved grey wolf optimization algorithm in one embodiment of the online leakage positioning method for a pipe network based on data fusion and intelligent optimization algorithm described in the present application.

[0070] like Figure 2 and Figure 3 As shown, this embodiment provides a method for online leakage location in a pipe network based on data fusion and intelligent optimization algorithm.

[0071] The method for online pipe network leakage location based on data fusion and intelligent optimization algorithm specifically includes the following steps:

[0072] S1, obtaining first basic data of the raw water pipe network, wherein the first basic data of the raw water pipe network includes but is not limited to: inlet flow, outlet flow, change in inlet and outlet water of the pipe network, etc.

[0073] In this embodiment, several monitoring devices (e.g., flow sensors, pressure sensors, water quality sensors, etc.) are installed within the target area's pipeline network to monitor various parameters of the raw water pipeline equipment within the target area. Alternatively, raw water pipeline-related data can be extracted from control systems or databases associated with each device.

[0074] Specifically, during the online leak location process in the raw water pipeline network, real-time data collection is required. This means installing a sensor group on the raw water pipeline to collect and initially process the sensor data before transmitting it to a cloud platform or control system for further processing.

[0075] For example, pressure sensors can be used and installed at key nodes of the pipeline to monitor changes in water pressure in the pipe in real time, providing basic data for leakage detection; flow sensors can be used and deployed at the inlet / outlet of the pipeline to monitor changes in water flow and assist in judging leakage conditions; sound wave / vibration sensors distributed along the pipeline can be used to capture sound waves or vibration signals generated by leakage to improve the accuracy of leakage locating; and water quality sensors can be used to monitor changes in water quality, indirectly reflect the pipeline status, and provide a reference for leakage warning, etc.

[0076] To summarize, it's crucial to select the appropriate field detection equipment and acquire data through the appropriate device or system. Next, choose the appropriate access method based on the type and format of the data source. For example, sensor data may require real-time collection through an API or device communication protocol (such as Modbus or OPC UA).

[0077] S2: Performing a water balance analysis based on the first basic data of the raw water network, obtaining a first leakage amount in a certain independent metering area, and determining whether leakage occurs in the raw water network.

[0078] See also Figure 4 , showing a water balance analysis diagram of an embodiment of the online leakage location method for a pipe network based on data fusion and intelligent optimization algorithm described in this application.

[0079] Water balance analysis is a core method in water management. It refers to the process of quantifying the changes in water input, output and storage of a system (such as a pipeline network, region, water plant, etc.) over a certain period of time, establishing a "water conservation" relationship model, and thus evaluating the system's operating status and identifying anomalies or losses.

[0080] In this embodiment, water balance analysis is used to determine whether leakage has occurred in the raw water network. Specifically, within a certain time period, if the inflow rate of the raw water network is greater than or equal to the sum of the outflow rate of the raw water network and the change in the network's inflow and outflow, the network is considered to have potential leakage, and the leakage amount within a certain independent metering area is calculated. If the inflow rate of the raw water network is less than the sum of the outflow rate of the raw water network and the change in the network's inflow and outflow, the network's leakage is considered to be within a normal range.

[0081] Specifically, water balance analysis is used to determine whether leakage has occurred in the raw water network. Leakage is determined to have occurred when the inflow rate of the raw water network is greater than or equal to the sum of the outflow rate of the raw water network and the change in the inflow and outflow of the network within a given time period.

[0082] The calculation formula for leakage in an independent metering area of ​​the pipeline network is:

[0083]

[0084] Where Qlesk,i represents the leakage in the i-th independent metering area; represents the nth water inflow of area i; represents the mth water inflow of area i; Represents the water inflow and outflow of the sth pool in area i, and the water inflow is a positive number.

[0085] S3, filtering the leakage amount in the independent metering area to obtain a first leakage estimation value in the independent metering area. Figure 5 、 Figure 6 , respectively showing a flow chart of S3 in the method for online leakage location of a pipe network based on data fusion and intelligent optimization algorithm described in this application, and a schematic diagram of the Kalman filtering process of the leakage amount in one embodiment of the method for online leakage location of a pipe network based on data fusion and intelligent optimization algorithm described in this application. Figure 5 and Figure 6 As shown, S3 includes the following steps:

[0086] S31, predicting the leakage amount in the independent metering area at a certain moment, and obtaining an estimated value of the leakage amount in the independent metering area at a next moment;

[0087] S32, obtaining a Kalman gain matrix based on the estimated value of leakage in the independent metering area at the next moment;

[0088] S33: performing an update prediction based on the Kalman gain matrix to obtain a first leakage estimation value after filtering at the next moment.

[0089] In this embodiment, a state prediction is first performed based on the leakage within the independent metering area at a certain moment, obtaining an estimated leakage within the independent metering area at the next moment. Specifically, the state value at the current moment is predicted based on the state estimate (filtered leakage) at the previous moment. The variance of the predicted value at the current moment is then calculated based on the variance of the predicted value at the previous moment and the state process noise (i.e., random fluctuations in the monitoring data). A Kalman gain matrix is ​​then calculated based on the predicted value variance and the measured value covariance. This Kalman gain matrix is ​​used to subsequently correct the predicted value to bring it closer to the actual measured value. The current predicted value (i.e., filtered leakage) is then corrected using a weighted average method based on the current measured value and the Kalman gain matrix. The measured value covariance is then updated based on the corrected state estimate and the measured value. The corrected state estimate and the updated measured value covariance are then iteratively optimized. Finally, the potential leakage within the raw water network is calculated based on the state estimate (i.e., filtered leakage) optimized by the Kalman filter algorithm and the actual flow rate monitoring value.

[0090] Specifically, the leakage amount in the independent metering area can be determined through water balance technology. The fluctuation of its value is affected by the noise of the monitoring data. When the raw water network operates stably, the difference between the inlet flow and the outlet flow tends to be stable, so formula (3) can be obtained.

[0091] The specific formula is as follows:

[0092] X(k)=X(k-1)+Q (3)

[0093] Z(k)=X(k)+R (4)

[0094] Among them, X(k) represents the state estimate at time k; X(k-1) represents the state estimate at time k-1; Q represents the state process noise, that is, the random fluctuation of the monitoring data; Z(k) represents the measurement value at time k; R represents the measurement error value.

[0095] The result of the Kalman filter optimization at the kth moment can be expressed as X(k / k), and the state estimate at the kth moment calculated according to formula (3) is expressed as X(k / k-1). X(k / k) is calculated using the standard Kalman filter algorithm. The specific steps are as follows:

[0096] Step 1: Predict the current state value based on the previous state value;

[0097] X(k|k-1)=X(k-1|k-1) (5)

[0098] Where X(k|k-1) represents the predicted value of the state at time k given the state at time k-1. It is assumed here that the state transition model is an identity transformation, that is, the current predicted value is equal to the estimated value at the previous time.

[0099] Step 2: Calculate the variance of the predicted value;

[0100] p(k|k-1)=p(k-1|k-1)+q(k) (6)

[0101] Where p(k|k-1) represents the covariance of the state estimate at time k given the information at time k-1; q(k) represents the process noise covariance, which reflects the uncertainty of the state transition model;

[0102] Step 3: Calculate the Kalman gain matrix;

[0103] g(k)=p(k|k-1) / [p(k|k-1)+r(k)] (7)

[0104] Where g(k) represents the Kalman gain, which is used to weigh the credibility of the predicted value and the actual measurement value; r(k) represents the measurement noise covariance;

[0105] Step 4: Based on the measured value at time k, the current predicted value is corrected using the weighted average method;

[0106] X(k|k)=X(k|k-1)+g(k)[Z(k)-X(k|k-1)] (8)

[0107] Where X(k|k) represents the estimated value of the state at time k given the information at time k; Z(k) represents the actual measured value at time k (i.e., the leakage in the independent metering area);

[0108] Step 5: Update the measurement covariance;

[0109] p(k|k)=[1-g(k)]p(k|k-1) (9)

[0110] Where p(k|k) represents the updated covariance given the information at time k;

[0111] Step 6: Substitute the results calculated by formulas (8) and (9) into step 1 to estimate the state at the next moment.

[0112] Then, based on the Kalman filter algorithm optimization value X(k / k) and the actual flow monitoring value, the possible leakage in the raw water network is calculated using formula (10). The specific formula is as follows:

[0113] R(k)=Z(k)-X(k / k) (10)

[0114] It should be noted that since water balance analysis relies on multi-source flow data, noise is inevitably present; therefore, in this application, the Kalman filter algorithm is chosen to perform noise reduction on the data to improve the accuracy of leakage identification.

[0115] S4: Based on the first leakage loss estimate, a hydraulic model of the raw water network is constructed, and the first leakage location is obtained using an improved grey wolf optimization algorithm. Figure 7 、 Figure 8 , which respectively show the flow chart of S4 in the method for online leakage location of a pipe network based on data fusion and intelligent optimization algorithm described in this application, and the flow chart of the improved grey wolf optimization algorithm in one embodiment of the method for online leakage location of a pipe network based on data fusion and intelligent optimization algorithm described in this application. Figure 7 and Figure 8 As shown, the S4 comprises the following steps:

[0116] S41: Perform fitting based on the first leakage loss estimation value to construct a hydraulic model of the raw water network.

[0117] In this embodiment, a fitting is performed with the goal of minimizing the mean square error between the monitored value and the simulated value at the pressure measuring point when leakage occurs, and a hydraulic model of the raw water pipe network for online leakage location is constructed.

[0118] Specifically, first, a hydraulic model of the raw water network is constructed. The overall accuracy of the model is high, which facilitates the implementation of online leakage location.

[0119] The objective function of the online leakage location model is established with the goal of minimizing the mean square error between the monitored value and the simulated value at the pressure measuring point when leakage occurs.

[0120] The objective function is:

[0121]

[0122] Wherein, Ns represents the total number of pressure measuring points in the raw water network; Pn represents the real-time simulation value and real-time monitoring value of each pressure measuring point respectively.

[0123] S42: Using an improved grey wolf optimization algorithm, perform iterative position update on the first leakage estimation value to obtain an updated first leakage area.

[0124] See also Figure 9 , which is a flow chart of S42 in the method for online pipe network leakage location based on data fusion and intelligent optimization algorithm described in this application. The S42 includes the following steps:

[0125] S421, using the improved gray wolf optimization algorithm to initialize the population and set population parameters; the population parameters include: population size, maximum number of iterations, and random vector parameters;

[0126] S422, obtaining the fitness of each individual gray wolf in the population based on the population parameters;

[0127] S423: Update the position of the first leakage estimation value according to the maximum number of iterations and the fitness to obtain an updated first leakage area.

[0128] In this embodiment, IGWO (Improved Grey Wolf Optimizer) is preferably used for processing.

[0129] That is, chaotic mapping (such as Logistic mapping) or Latin hypercube sampling is used to generate an initial gray wolf population to cover areas where the pipeline network may leak.

[0130] First, in IGWO, the population is initialized and the population parameters are set (such as population size N, maximum number of iterations T_max, the decreasing rule of the improved nonlinear convergence factor a (and its parameters), spatial dimension, hybridization probability Pc, mutation probability Pm and other parameters. Chaotic mapping, reverse learning and other methods are used to initialize the position of the gray wolf population in the search space; and the fitness value of each gray wolf individual (i.e., the objective function value) is calculated; then the initial α, β, and δ wolves are determined according to the fitness value sorting. Among them, α wolf: the leader of the wolf pack (optimal solution); β wolf: assists α wolf in making decisions (suboptimal solution); δ wolf: executes orders, scouting, and alerting (third optimal solution); ω wolf: obeys the instructions of wolves of other levels (other candidate solutions).

[0131] Then, the convergence factor a is updated according to the preset nonlinear strategy; each individual ω wolf in the population is traversed again, and the distance between the current ω wolf and the α wolf, β wolf, and δ wolf is calculated to update the position; through iteration, the position update is gradually improved; the fitness value of the individual in the new position is calculated; then, among all the current individuals (including possible hybrid offspring and mutant individuals), they are re-sorted according to the fitness value to select new α wolf, β wolf, and δ wolf.

[0132] Finally, when the maximum number of iterations is reached or other stopping conditions are met (such as: the fitness value improvement is less than the threshold, the optimal solution is not updated after multiple consecutive iterations, etc.), the loop is terminated. The position of the best gray wolf is output as the optimal solution found.

[0133] Specifically, in the IGWO algorithm, the first three solutions with the best fitness values ​​are regarded as α wolf, β wolf, and δ wolf, respectively, and the remaining solutions are ω wolf. The maximum size of the wolf pack is N, and each gray wolf is located in D-dimensional space. The candidate solution vector is represented by the position Xi,j = (X i,1 ,X i,2 ,X i,3 ,…,X i,D The mathematical model of the hunting process is shown in formulas (11) to (14). and It is a random vector, which allows the gray wolf to reach any position around the prey after updating its position, thereby simulating the process of tracking the prey.

[0134] At the same time, since the wolf pack cannot know the true location of the prey during the search process, it is assumed that α wolf, β wolf and δ wolf know more information about the location of the prey, and use α wolf, β wolf and δ wolf as guidance to update the positions of the other gray wolves. The mathematical model is shown in formula (15) to formula (16).

[0135] The specific formula is as follows:

[0136]

[0137] in, and Both represent coefficient vectors; Indicates the distance between the gray wolf and its prey; represents the position of the i-th gray wolf in the t-th iteration; Indicates the location of prey; Represents a parameter that decreases linearly from 2 to 0 with the number of iterations; and represent random vectors of [0,1] respectively; and Represent the positions of α wolf, β wolf, and δ wolf respectively; Indicates the updated gray wolf position of GWO.

[0138] In summary, the process of simulating wolves attacking prey is achieved by controlling The size of When , the wolves will move away from the prey to find more suitable prey and achieve the goal of global search. When , the wolves will attack the prey, achieving the purpose of local search. As the number of iterations decreases linearly from 2 to 0, the previous iteration Perform global search and subsequent iteration Perform local search, thus balancing the algorithm's global search capabilities and local search capabilities.

[0139] S43: Use a retrieval model to search and optimize the position of the first leakage area, thereby obtaining a first leakage position.

[0140] See also Figure 10 , which shows a flow chart of S43 in the method for online pipe network leakage location based on data fusion and intelligent optimization algorithm described in this application. The S43 includes the following steps:

[0141] S431, using the L2 norm to calculate and obtain the distance between the current position of the gray wolf and the updated position of the gray wolf;

[0142] S432, constructing a neighboring gray wolf pack based on the distance between the current position of the gray wolf and the updated position of the gray wolf;

[0143] S433, updating the position of the neighboring gray wolf pack to obtain an updated position of the gray wolf;

[0144] S434, comparing the updated gray wolf position and fitness value with the fitness of the position obtained through proximity learning, updating the gray wolf position to the position with the best fitness, and using the position with the best fitness as the first leakage position.

[0145] In this embodiment, in the DLH search phase, the gray wolf position is calculated by the L2 norm With the updated The distance R i (t)(Formula (17)); then construct the gray wolf X according to the distance i Neighboring gray wolf pack N i (t) (Formula (18)), by learning from neighboring gray wolf packs to update the gray wolf position (Formula (19)); Finally, by comparing and The fitness value of the gray wolf is updated to the position with the best fitness (Formula (20)).

[0146]

[0147] Among them, R i (t) represents the distance between the gray wolf's previous and next positions after the update; N i (t) indicates a neighboring gray wolf pack; Indicates the updated position of the gray wolf obtained through neighbor learning; Indicates the updated position fitness and selects the updated gray wolf position; represents the position of the i-th gray wolf in the t-th iteration; Represents the updated position of the gray wolf at time t+1.

[0148] S5: Calculate a second leakage loss estimate and a second leakage location based on second basic data of the raw water pipe network, wherein the second basic data of the raw water pipe network includes but is not limited to pipe diameter, pipe material, pressure monitoring data, and flow monitoring data.

[0149] In this embodiment, the leak location and amount are both used as decision variables, relying solely on pressure monitoring data to determine the potential leak location and amount using an improved Grey Wolf optimization algorithm. Specifically, the algorithm detects pressure wave propagation characteristics; calculates the leak location using the time-of-day location method; and calculates a second leak amount estimate using the pressure decay rate.

[0150] Specifically, this embodiment calculates the possible leak locations and leakage amounts based on pressure monitoring data; processing is performed using the leakage location and leakage amount as decision variables. Specifically, a hydraulic model and objective function are first established. The objective function is constructed using the residual sum of squares between the actual monitored pressure and the simulated pressure, with the leak location (pipeline number) and leakage amount as decision variables. Next, gray wolf individuals are randomly generated, encoding the leak location (discrete variable) and leakage amount (continuous variable). An exponential convergence factor is introduced to adjust the weight distribution of the α, β, and δ wolves to enhance global search capabilities. Local search is optimized through information exchange between neighboring gray wolf packs to avoid premature convergence. A sigmoid transformation function is then used to map the continuous location variable to a discrete pipeline number. Next, simulated pressure data under leakage conditions is dynamically updated using EPANET, and individual fitness is calculated. The top three optimal solutions (α, β, and δ wolves) are selected to guide population updates, and a new solution is generated using the DLH strategy. Finally, the leak location (accurate to a single pipeline) and leakage amount (flow rate per unit time) corresponding to the global optimal solution are output.

[0151] S6: Compare the first leakage estimate and the first leakage location with the second leakage amount estimate and the second leakage location to determine a final leakage location and leakage amount.

[0152] In this embodiment, a leakage threshold is preset; when the difference between the first leakage estimate value and the first leakage location and the second leakage amount estimate value and the second leakage location is less than or equal to the leakage threshold, the leakage estimate value and the leakage location are determined to be the final leakage location result; when the difference between the first leakage estimate value and the first leakage location and the second leakage amount estimate value and the second leakage location is greater than the leakage threshold, the leakage estimate value and the leakage location are determined to be the final leakage location result.

[0153] In summary, the two schemes are run simultaneously, and the consistency of the positioning results is compared to determine the validity of the positioning results. If the positioning results of the two schemes are consistent or similar, the positioning results are considered reliable. If the results differ significantly, further analysis and verification are required to enhance the robustness of the algorithm and improve the accuracy of leak location.

[0154] The following is a detailed description of the optimization method for energy-saving operation of a speed-regulating pump station of the same model.

[0155] Example 1

[0156] Assume that the total water supply capacity of the raw water network in the target area M is 2.08 million m 3 The total length of the pipeline network is 163 km, with pipe diameters ranging from DN1000 to DN4000. The pumping stations include the No. 5 Gou Pumping Station, the Jinhai Pumping Station, and the Nanhui North Pumping Station. The No. 5 Gou Pumping Station has seven pumps, the Jinhai Pumping Station has ten, and the Nanhui North Pumping Station has five. In addition, there are six major receiving water plants.

[0157] Combined with the above data, EPANET software was used to establish a hydraulic model of the raw water network. The hydraulic model consists of 345 nodes, 290 pipe sections, 1 water source, 22 water pumps, and 93 valves.

[0158] First, through water balance analysis, it is found that the amount of water entering the raw water network is greater than the sum of the amount of water leaving the system and the change in the water pool, then it is determined that there is leakage in the network.

[0159] Then, the collected traffic data is processed by Kalman filtering to remove noise.

[0160] Then, use Scheme 1 and Scheme 2 to locate the leakage. Specifically, they include:

[0161] Option 1: Determine the leakage amount through water balance technology, and then use the improved Grey Wolf optimization algorithm to solve the leakage location; Option 2: Use the leakage location and leakage amount as decision variables, only use pressure monitoring data, and use the improved Grey Wolf optimization algorithm to solve the leakage location and leakage amount.

[0162] Finally, compare the positioning results of the two schemes. If the results are consistent or similar, the positioning results are considered reliable; if the results are significantly different, further analysis and verification are required.

[0163] Therefore, in this embodiment, the online leakage location technology is applied and verified. In terms of leakage location accuracy, when the leakage amount is greater than 100m 3 When the leak rate is increased by 100%, the online leak location technology can guarantee positioning accuracy within 200 meters. In terms of algorithm robustness, the online leak location technology compares the positioning results of the two schemes, reducing over-reliance on monitoring data and thus enhancing the credibility of the positioning results.

[0164] It is worth noting that errors in flow and pressure monitoring data will affect positioning accuracy. To ensure positioning accuracy, the quality of monitoring data should be guaranteed as much as possible.

[0165] It should be noted that the online leakage positioning method of the pipeline network based on data fusion and intelligent optimization algorithm of the present application is not limited to the contents of the embodiments provided in the present application, that is, it is not limited to the online leakage positioning of the raw water pipeline network, but is also applicable to the online leakage positioning of the liquid pipeline network.

[0166] The online leakage location method for pipe networks based on data fusion and intelligent optimization algorithm provided in this application determines the leakage amount in the raw water pipe network system through water balance technology, and then uses the leakage location as the decision variable. According to the real-time monitoring data of each pressure measuring point, the improved gray wolf optimization algorithm is used to solve the possible location of the leakage; thereby improving the positioning accuracy.

[0167] The scope of protection of the online pipeline leakage positioning method based on data fusion and intelligent optimization algorithm described in the embodiment of the present application is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing or replacing steps in the existing technology based on the principles of the present application are included in the scope of protection of the present application.

[0168] An embodiment of the present application also provides an online pipeline leakage positioning system based on data fusion and intelligent optimization algorithm. The online pipeline leakage positioning system based on data fusion and intelligent optimization algorithm can implement the online pipeline leakage positioning method based on data fusion and intelligent optimization algorithm described in the present application. However, the implementation device of the online pipeline leakage positioning method based on data fusion and intelligent optimization algorithm described in the present application includes but is not limited to the structure of the online pipeline leakage positioning system based on data fusion and intelligent optimization algorithm listed in the present embodiment. All structural deformations and replacements of the existing technology made according to the principles of the present application are included in the protection scope of the present application.

[0169] The following will describe in detail the pipe network online leakage location system based on data fusion and intelligent optimization algorithm provided by this embodiment with reference to the drawings.

[0170] This embodiment provides a pipe network online leakage location system based on data fusion and intelligent optimization algorithm, including:

[0171] See also Figure 11 , which shows a schematic diagram of the principle structure of an embodiment of the pipe network online leakage location system based on data fusion and intelligent optimization algorithm described in this application. Figure 11 As shown, the pipeline online leakage location system based on data fusion and intelligent optimization algorithm includes: a data acquisition module 111, a leakage judgment module 112, a data filtering module 113, a first leakage location module 114, a second leakage location module 115 and a scheme comparison module 116.

[0172] The data acquisition module 111 is used to acquire first basic data of the raw water network; the first basic data of the raw water network includes but is not limited to: inlet flow, outlet flow, change in inlet and outlet water of the network, etc.

[0173] In this embodiment, several monitoring devices (e.g., flow sensors, pressure sensors, water quality sensors, etc.) are installed within the target area's pipeline network to monitor various parameters of the raw water pipeline equipment within the target area. Alternatively, raw water pipeline-related data can be extracted from control systems or databases associated with each device.

[0174] The leakage judgment module 112 is configured to perform a water balance analysis based on the first basic data of the raw water network, obtain a first leakage amount in a certain independent metering area, and judge whether leakage occurs in the raw water network.

[0175] In this embodiment, water balance analysis is used to determine whether leakage has occurred in the raw water network. Specifically, within a certain time period, if the inflow rate of the raw water network is greater than or equal to the sum of the outflow rate of the raw water network and the change in the network's inflow and outflow, the network is considered to have potential leakage, and the leakage amount within a certain independent metering area is calculated. If the inflow rate of the raw water network is less than the sum of the outflow rate of the raw water network and the change in the network's inflow and outflow, the network's leakage is considered to be within a normal range.

[0176] The data filtering module 113 is configured to filter the leakage amount in the independent metering area to obtain a first leakage estimation value in the independent metering area.

[0177] In this embodiment, a prediction is made based on the leakage amount in the independent metering area at a certain moment to obtain an estimated leakage amount in the independent metering area at the next moment; a Kalman gain matrix is ​​obtained based on the estimated leakage amount in the independent metering area at the next moment; and an updated prediction is made based on the Kalman gain matrix to obtain a first leakage estimate after filtering at the next moment.

[0178] The first leakage locating module 114 is configured to construct a raw water network hydraulic model based on the first leakage estimation value, and to obtain a first leakage location using an improved grey wolf optimization algorithm.

[0179] Fitting is performed based on the first leakage loss estimate to construct a hydraulic model of the raw water network.

[0180] In this embodiment, a fitting is performed with the goal of minimizing the mean square error between the monitored value and the simulated value at the pressure measuring point when leakage occurs, and a hydraulic model of the raw water pipe network for online leakage location is constructed.

[0181] An improved grey wolf optimization algorithm is used to iteratively update the position of the first leakage estimate to obtain an updated first leakage area.

[0182] Specifically, an improved gray wolf optimization algorithm is used to initialize the population and set population parameters; the population parameters include: population size, maximum number of iterations, and random vector parameters; the fitness of each gray wolf individual in the population is obtained based on the population parameters; the position of the first leakage estimate is updated according to the maximum number of iterations and the fitness to obtain an updated first leakage area.

[0183] In this embodiment, IGWO (Improved Grey Wolf Optimizer) is preferably used for processing.

[0184] That is, chaotic mapping (such as Logistic mapping) or Latin hypercube sampling is used to generate an initial gray wolf population to cover areas where the pipeline network may leak.

[0185] In this embodiment, a retrieval model is used to search and optimize the position of the first leakage area to obtain a first leakage location. This includes: using the L2 norm to calculate the distance between the current gray wolf position and the updated gray wolf position; constructing a neighboring gray wolf group based on the distance between the current gray wolf position and the updated gray wolf position; updating the position of the neighboring gray wolf group to obtain an updated gray wolf position; comparing the updated gray wolf position and fitness value with the fitness of the position obtained through neighbor learning, updating the gray wolf position to the position with the best fitness, and using the position with the best fitness as the first leakage location.

[0186] The second leakage locating module 115 is configured to calculate a second leakage estimation value and a second leakage location based on second basic data of the raw water pipe network; the second basic data of the raw water pipe network includes: pipe diameter, pipe material, pressure monitoring data, and flow monitoring data.

[0187] In this embodiment, the leak location and amount are both used as decision variables, relying solely on pressure monitoring data to determine the potential leak location and amount using an improved Grey Wolf optimization algorithm. Specifically, the algorithm detects pressure wave propagation characteristics; calculates the leak location using the time-of-day location method; and calculates a second leak amount estimate using the pressure decay rate.

[0188] The solution comparison module 116 is configured to compare the first leakage estimate and the first leakage location with the second leakage amount estimate and the second leakage location to determine a final leakage location and leakage amount.

[0189] In this embodiment, a leakage threshold is preset; when the difference between the first leakage estimate value and the first leakage location and the second leakage amount estimate value and the second leakage location is less than or equal to the leakage threshold, the leakage estimate value and the leakage location are determined to be the final leakage location result; when the difference between the first leakage estimate value and the first leakage location and the second leakage amount estimate value and the second leakage location is greater than the leakage threshold, the leakage estimate value and the leakage location are determined to be the final leakage location result.

[0190] The online leakage location model of the pipeline network based on data fusion and intelligent optimization algorithm is built. The online leakage location system of the pipeline network based on data fusion and intelligent optimization algorithm can run synchronously by combining two leakage location schemes and effectively enhance the robustness of the algorithm by consistency comparison of the positioning results, so that it can operate stably in complex data environments.

[0191] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices or methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0192] The modules / units described as separate components may or may not be physically separate, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into a processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into a single module / unit.

[0193] Those skilled in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0194] See also Figure 12 , which is a schematic diagram showing the structure of the electronic device described in the embodiment of the present application. Figure 12 As shown, this embodiment provides an electronic device, where the electronic device 120 includes a memory 121 and a processor 122 .

[0195] The memory 121 is used to store computer programs; preferably, the memory 121 includes: ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk, etc., various media that can store program codes.

[0196] Specifically, the memory 121 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The electronic device 120 may further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 121 may include at least one program product having a set (e.g., at least one) program modules that are configured to perform the functions of the various embodiments of the present application. It is understood that the memory 121 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM) or a programmable read-only memory (PROM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable categories of memory.

[0197] The processor 122 is connected to the memory 121 and is used to execute the computer program stored in the memory 121 so that the electronic device 120 executes the detection model training method described in any embodiment of the present application and / or the line detection method described in the embodiment of the present application.

[0198] Optionally, the processor 122 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0199] Optionally, the electronic device 120 in this embodiment may further include a display 113. The display 113 is communicatively connected to the memory 121 and the processor 122, and is used to display a graphical user interface (GUI) interaction interface related to the detection model training method described in the embodiment of the present application and / or the line detection method described in other embodiments of the present application.

[0200] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the detection model training method described in any embodiment of the present application and / or the line detection method described in other embodiments of the present application are implemented.

[0201] As used in this specification, the terms "component," "module," "system," and the like are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. By way of illustration, both an application running on a computing device and a computing device can be a component. One or more components can reside in a process and / or an execution thread, and a component can be located on a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures stored thereon. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component on a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0202] In summary, the online leakage location method for pipe networks based on data fusion and intelligent optimization algorithm provided by this application has the following beneficial effects:

[0203] The present application provides an online leak location method for pipe networks based on data fusion and intelligent optimization algorithms, which can improve the accuracy and robustness of leak location. This method first determines whether a leak has occurred within the pipe network through water balance analysis and uses Kalman filtering to reduce noise on the flow rate data, improving data reliability. Next, a high-precision hydraulic model of the raw water pipe network is constructed, employing two simultaneous leak location schemes: Scheme 1 determines the leak amount through water balance technology, uses the leak location as a decision variable, and solves the leak location using an improved Grey Wolf optimization algorithm; Scheme 2 uses both the leak location and the leak amount as decision variables, relying solely on pressure monitoring data and solving the leak location and amount using an improved Grey Wolf optimization algorithm. Finally, by comparing the consistency of the location results from the two schemes, the validity of the location results is determined, enhancing the robustness of the algorithm. This invention enables real-time monitoring of pipe network status, quickly and accurately locating leaks, reducing water waste and safety hazards, and possesses significant practical application value.

[0204] The descriptions of the processes or structures corresponding to the above figures have different emphases. For parts that are not described in detail in a certain process or structure, please refer to the relevant descriptions of other processes or structures.

[0205] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A method for online leakage location in a pipe network based on data fusion and intelligent optimization algorithm, characterized in that: include: Obtain the first basic data of the raw water network; The first basic data of the raw water pipe network includes: water inlet flow, water outlet flow, and water inlet and outlet changes of the pipe network; Performing a water balance analysis based on the first basic data of the raw water pipe network to obtain a first leakage amount in a certain independent metering area and determining whether leakage occurs in the raw water pipe network; Performing filtering on the leakage amount in the independent metering area to obtain a first leakage estimation value in the independent metering area; Building a raw water network hydraulic model based on the first leakage loss estimate, and using an improved Grey Wolf optimization algorithm to obtain a first leakage loss location; Calculating a second leakage amount estimate and a second leakage location based on second basic data of the raw water pipe network; The first leakage estimate and the first leakage location are compared with the second leakage amount estimate and the second leakage location to determine a final leakage location and leakage amount.

2. The method for online pipe network leakage location based on data fusion and intelligent optimization algorithm according to claim 1 is characterized in that: Performing water balance analysis based on the raw water network basic data to obtain leakage within a certain independent metering area and determine whether leakage occurs in the raw water network includes: Determine whether leakage occurs in the original pipe network through water balance analysis; include: During a certain period of time, when the inlet flow rate of the raw water network is greater than or equal to the sum of the outlet flow rate of the raw water network and the change in the inlet and outlet water of the network, it is determined that there may be leakage in the raw water network, and the leakage amount in a certain independent metering area is calculated; when the inlet flow rate of the raw water network is less than the sum of the outlet flow rate of the raw water network and the change in the inlet and outlet water of the network, it is determined that the leakage of the raw water network is within the normal range.

3. The method for online pipe network leakage location based on data fusion and intelligent optimization algorithm according to claim 1 is characterized in that: Filtering the leakage amount in the independent metering area to obtain a first leakage estimation value in the independent metering area includes: Predicting the leakage amount in the independent metering area at a certain moment to obtain an estimated value of the leakage amount in the independent metering area at a next moment; Obtaining a Kalman gain matrix based on the estimated value of leakage in the independent metering area at the next moment; An updated prediction is performed based on the Kalman gain matrix to obtain a first leakage estimation value after filtering at the next moment.

4. The method for online pipe network leakage location based on data fusion and intelligent optimization algorithm according to claim 1 is characterized in that: Building a raw water network hydraulic model based on the first leakage loss estimate and using an improved grey wolf optimization algorithm to obtain the first leakage loss location includes: Perform fitting based on the first leakage loss estimate to construct a raw water network hydraulic model; Using an improved grey wolf optimization algorithm, performing iterative position update on the first leakage estimate to obtain an updated first leakage area; The first leakage area is searched and the position is optimized using a retrieval model, thereby obtaining a first leakage position.

5. The method for online pipe network leakage location based on data fusion and intelligent optimization algorithm according to claim 4 is characterized in that: Fitting the first leakage loss estimate to construct a raw water network hydraulic model includes: The mean square error between the monitoring value and the simulation value at the pressure measuring point when the leakage occurs is minimized, and a hydraulic model of the raw water pipe network for online leakage positioning is constructed.

6. The method for online pipe network leakage location based on data fusion and intelligent optimization algorithm according to claim 4 is characterized in that: The improved grey wolf optimization algorithm is used to iteratively update the position of the first leakage estimate value, and the updated first leakage area includes: An improved grey wolf optimization algorithm is used to initialize the population and set population parameters, including population size, maximum number of iterations, and random vector parameters. Obtaining the fitness of each individual gray wolf in the population based on the population parameters; The first leakage estimation value is updated in position according to the maximum number of iterations and the fitness to obtain an updated first leakage area.

7. The method for online pipe network leakage location based on data fusion and intelligent optimization algorithm according to claim 4 is characterized in that: Searching and optimizing the position of the first leakage area using a retrieval model to obtain the first leakage position includes: Use the L2 norm to calculate and obtain the distance between the current position of the gray wolf and the updated position of the gray wolf; Constructing a neighboring gray wolf group based on the distance between the current position of the gray wolf and the updated position of the gray wolf; updating the position of the neighboring gray wolf pack to obtain an updated position of the gray wolf; The updated gray wolf position and fitness value are compared with the fitness of the position obtained through neighbor learning, the gray wolf position is updated to the position with the best fitness, and the position with the best fitness is used as the first leakage position.

8. The method for online pipe network leakage location based on data fusion and intelligent optimization algorithm according to claim 1 is characterized in that: Comparing the first leakage estimate and the first leakage location with the second leakage amount estimate and the second leakage location to determine a final leakage location and leakage amount includes: Preset a leakage threshold; When the difference between the first leakage estimation value and the first leakage location and the second leakage estimation value and the second leakage location is less than or equal to the leakage threshold, the leakage estimation value and the leakage location are determined to be the final leakage location result; When the difference between the first leakage estimation value and the first leakage location and the second leakage estimation value and the second leakage location is greater than the leakage threshold, the leakage estimation value and the leakage location are determined to be the final leakage location result.

9. A pipe network online leakage location system based on data fusion and intelligent optimization algorithm, characterized in that: include: A data acquisition module, used to acquire first basic data of the raw water pipe network; The first basic data of the raw water pipe network includes: water inlet flow, water outlet flow, and water inlet and outlet changes of the pipe network; a leakage judgment module, configured to perform a water balance analysis based on the first basic data of the raw water pipe network, obtain a first leakage amount in a certain independent metering area, and judge whether leakage occurs in the raw water pipe network; A data filtering module, configured to filter the leakage amount in the independent metering area to obtain a first leakage estimation value in the independent metering area; a first leakage locating module, configured to construct a raw water network hydraulic model based on the first leakage estimation value and obtain a first leakage location using an improved grey wolf optimization algorithm; A second leakage locating module, configured to calculate a second leakage amount estimate and a second leakage location based on second basic data of the raw water pipe network; The scheme comparison module is used to compare the first leakage estimation value and the first leakage location with the second leakage amount estimation value and the second leakage location to determine the final leakage location and leakage amount.

10. An electronic device, characterized in that: include: memory for storing computer programs; A processor, wherein the processor is used to execute the computer program stored in the memory so that the electronic device executes the pipeline online leakage positioning method based on data fusion and intelligent optimization algorithm as described in any one of claims 1 to 8.

Images