Method and system for positioning leakage position of water supply and drainage pipeline

Abstract

The invention provides a water supply and drainage pipeline leakage position positioning method and system, and relates to the technical field of pipeline detection, and the method comprises the steps: building a pipe network model based on the geometric structure and fluid characteristics of a target pipeline; analyzing pressure, flow and sound wave signal changes, and setting a perturbation introduction point; introducing a micro-disturbance signal to generate dynamic characteristic data; arranging a sensor array to collect monitoring data; performing fitting analysis on the data by using the simulation model; and the leakage point position is accurately positioned through an intelligent algorithm in combination with micro-disturbance propagation characteristics. According to the method, the leakage point can be efficiently and accurately positioned, the pipe network detection and maintenance efficiency is improved, and resource waste and safety risks caused by leakage are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of pipeline detection, and in particular to a method and system for locating leakage positions in water supply and drainage pipelines. Background Art

[0002] Water supply and drainage pipelines are important infrastructure for urban water supply, drainage and industrial production. Their operational safety directly affects social and economic development and the quality of life of residents. However, in the long-term operation of pipelines, they are easily affected by factors such as aging, corrosion, and external construction, and are prone to leakage. Pipeline leakage not only leads to waste of water resources, but may also cause a series of secondary disasters such as insufficient water supply pressure, environmental pollution, and groundwater leakage, which seriously threaten the safety and reliability of urban operations.

[0003] At present, the methods of pipeline leakage detection mainly include manual inspection, static physical monitoring and dynamic simulation analysis. Manual inspection uses visual observation or listening equipment to find leakage points. It is easy to operate, but inefficient and difficult to cover complex pipeline networks. Static physical monitoring relies on pressure sensors, flow meters and other equipment to judge the leakage status by monitoring the changes in physical quantities, but its positioning accuracy is limited and it is difficult to adapt to pipelines with nonlinear and complex topological structures. Dynamic simulation analysis uses pipeline network models to predict the leakage location, which is of great significance to theoretical research, but in practical applications, there are still problems such as insufficient comprehensive analysis of multiple physical quantities and high modeling complexity, especially in scenarios with multiple leakage points or severe noise interference. It performs poorly.

[0004] Existing technologies still have obvious deficiencies in terms of real-time and accuracy of leak location and adaptability to complex pipe networks. For example, most technologies only focus on the changes in a single physical quantity (such as pressure or flow), and cannot fully reflect the dynamic impact of leaks on the entire pipe network; for large-scale or highly complex pipe network structures, existing methods lack adaptability in modeling and analysis; at the same time, factors such as environmental noise and sensor errors also make traditional methods less robust in practical applications.

[0005] In order to overcome the above technical deficiencies, the present invention proposes a method and system for locating the leakage position of water supply and drainage pipelines that combines multi-dimensional data acquisition and dynamic simulation. This method constructs a dynamic propagation model by comprehensively utilizing multi-source signals such as pressure, flow and sound waves, and combines intelligent algorithms to conduct in-depth analysis of monitoring data. It can quickly and accurately locate the leakage position, effectively improve the safety of pipeline operation and maintenance efficiency, and significantly reduce water resource waste, providing reliable technical support for modern pipe network management. Summary of the invention

[0006] In order to solve the technical problems in the prior art of insufficient multi-dimensional data fusion, poor adaptability to pipe network complexity, and poor real-time and robustness, the present invention provides a method and system for locating the leakage position of a water supply and drainage pipe.

[0007] The technical solution provided by the present invention is as follows:

[0008] First aspect:

[0009] The present invention provides a method for locating a leakage position of a water supply and drainage pipeline, comprising:

[0010] S1. Based on the logistics structure and physical characteristics of the target water supply and drainage pipeline, the geometric structure, pipe diameter, material, node connection method and fluid characteristics of the pipeline system are collected to build a pipeline network model containing pipeline network topology information and fluid dynamics characteristics;

[0011] S2. By analyzing the changing patterns of pipe network pressure, flow and acoustic wave signals, key nodes sensitive to leak detection are identified and set as micro-disturbance introduction points;

[0012] S3. Introduce controllable pressure, flow or acoustic wave micro-disturbance signals at key nodes, record the dynamic characteristics of micro-disturbance signals propagating in the pipe network, and generate micro-disturbance signal simulation data;

[0013] S4. Deploy sensor arrays at multiple nodes in the pipe network model to collect real-time monitoring data of various physical parameters including pressure, flow and sound waves;

[0014] S5. Combining signal processing and data analysis techniques, the propagation process of the perturbation signal is simulated through the simulation model, and the simulation data is dynamically fitted using the propagation anisotropy factor (PAF) and the leakage characteristic coefficient (LCC);

[0015] S6. Compare and analyze the monitoring data collected by the sensor with the simulation prediction data, identify abnormal changes in the monitoring data based on intelligent algorithms, and accurately locate the leakage point by combining the dynamic relationship between abnormal nodes and micro-disturbance propagation characteristics;

[0016] S7. Generate a leak location report, including the location of the leak point, the estimated value of the leak scale and its dynamic change trend, to optimize the subsequent pipeline maintenance plan.

[0017] Second aspect:

[0018] The present invention provides a water supply and drainage pipeline leakage location positioning system, comprising:

[0019] processor;

[0020] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for locating a leakage position of a water supply and drainage pipeline as described in the first aspect is implemented.

[0021] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0022] (1) In the present invention, by adopting the propagation anisotropy factor (PAF) and the leakage characteristic coefficient (LCC) combined with the multi-dimensional signal dynamic analysis of pressure, flow and sound waves in the pipeline, the problem of insufficient integration of multi-parameter information in the prior art is effectively solved, and the accuracy of leak location in complex pipe networks is significantly improved;

[0023] (2) In the present invention, by referring to the mathematical model based on the propagation of sound waves and flow signals, and the deep learning algorithm for the identification of abnormal data and the prediction of the leakage location, a real-time and intelligent leakage detection mechanism is constructed, which improves the detection efficiency and enhances the system's adaptability to complex environments;

[0024] (3) In the present invention, by calculating the anisotropy factor and leakage characteristic coefficient during the propagation of micro-disturbance, and further combining multi-dimensional curve fitting and multi-parameter optimization technology, the leakage point position is accurately calibrated and corrected, thereby effectively solving the problems of insufficient robustness and accuracy in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A schematic diagram of a flow chart of a method for locating a leakage position of a water supply and drainage pipeline provided by an embodiment of the present invention;

[0027] Figure 2 A schematic structural diagram of a water supply and drainage pipeline leakage location positioning system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0029] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0030] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0031] In the embodiments of the present invention, sometimes the subscripts such as W 1 It may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0032] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0033] Reference Manual Attached Figure 1 , showing a flow chart of a method for locating a leakage position in a water supply and drainage pipeline provided by an embodiment of the present invention.

[0034] The embodiment of the present invention provides a method for locating a leakage position of a water supply and drainage pipeline. The method can be implemented by a device for locating a leakage position of a water supply and drainage pipeline. The device for locating a leakage position of a water supply and drainage pipeline can be a terminal or a server. The processing flow of the method for locating a leakage position of a water supply and drainage pipeline can include the following steps:

[0035] S1. Based on the logistics structure and physical characteristics of the target water supply and drainage pipeline, the geometric structure, pipe diameter, material, node connection method and fluid characteristics of the pipeline system are collected to build a pipeline model containing pipeline network topology information and fluid dynamics characteristics.

[0036] It should be noted that by collecting basic data such as the geometric structure, diameter, material, node connection method and fluid characteristics of the target pipeline, and building a model containing the pipeline network topology information and fluid dynamics characteristics, it is the basis for subsequent leak detection and positioning. This step can accurately describe the physical properties of the pipeline network and the law of fluid distribution, provide a reliable mathematical and physical basis for the simulation analysis of micro-disturbance signal propagation, and improve the adaptability of the entire system in different pipeline network structures.

[0037] S2. By analyzing the changing patterns of pipeline network pressure, flow and acoustic wave signals, key nodes sensitive to leak detection are identified and set as micro-disturbance introduction points.

[0038] It should be noted that by analyzing the changing patterns of pressure, flow and acoustic wave signals in the pipeline network, identifying key nodes that are sensitive to leak detection, and setting them as micro-disturbance introduction points, it is helpful to concentrate detection resources on areas most likely to be affected by leaks. This step can not only reduce unnecessary signal interference, but also significantly improve the effectiveness of signal propagation, providing a scientific basis for subsequent signal simulation and anomaly identification.

[0039] S3. Introduce controllable pressure, flow or acoustic wave micro-disturbance signals at key nodes, record the dynamic characteristics of micro-disturbance signals propagating in the pipe network, and generate micro-disturbance signal simulation data.

[0040] It should be noted that by introducing controllable pressure, flow or acoustic micro-disturbance signals at key nodes and recording their propagation dynamic characteristics, the generated simulation data can reflect the leakage response behavior of the pipeline network under different physical conditions. This step provides real dynamic input for the simulation model, helps to accurately describe the propagation law of micro-disturbance in the pipeline network, and lays the foundation for the subsequent comparative analysis of abnormal data.

[0041] S4. Sensor arrays are deployed at multiple nodes in the pipe network model to collect real-time monitoring data of various physical parameters including pressure, flow and sound waves.

[0042] It should be noted that by deploying sensor arrays at multiple nodes of the pipeline network and collecting real-time monitoring data of physical parameters such as pressure, flow and sound waves, it is possible to effectively capture local anomalies caused by leakage events. This step provides real-time data support for the rapid location of leakage points by establishing a high-density monitoring network, while enhancing the robustness and accuracy of the detection system.

[0043] S5. Combining signal processing and data analysis techniques, the propagation process of the micro-disturbance signal is simulated through a simulation model, and the simulation data is dynamically fitted using the propagation anisotropy factor (PAF) and leakage characteristic coefficient (LCC).

[0044] It should be noted that combining signal processing and data analysis technology, using simulation models to simulate the propagation process of micro-disturbance signals, and dynamically fitting simulation data through propagation anisotropy factor (PAF) and leakage characteristic coefficient (LCC) helps to accurately restore the propagation trajectory of micro-disturbance. This step significantly improves the matching degree between abnormal signals and leakage events by optimizing simulation accuracy, providing strong mathematical support for accurately locating leakage points.

[0045] S6. Compare and analyze the monitoring data collected by the sensor with the simulation prediction data, identify abnormal changes in the monitoring data based on intelligent algorithms, and accurately locate the leakage point by combining the dynamic relationship between abnormal nodes and micro-disturbance propagation characteristics.

[0046] It should be noted that by comparing and analyzing the monitoring data collected by the sensor with the simulation prediction data, identifying abnormal changes through intelligent algorithms, and combining the dynamic relationship between abnormal nodes and micro-disturbance propagation characteristics, the leakage point can be located quickly and accurately. This step uses the dynamic correlation between data to comprehensively improve the accuracy and efficiency of positioning, and provides technical support for adaptive detection of multiple leakage point scenarios.

[0047] S7. Generate a leak location report, including the location of the leak point, the estimated value of the leak scale and its dynamic change trend, to optimize the subsequent pipeline maintenance plan.

[0048] It should be noted that generating a leak location report, including the location of the leak point, the estimated value of the leak scale and its dynamic change trend, helps to visually present the leak situation and provide a scientific basis for the network maintenance personnel to optimize the subsequent maintenance plan. This step converts complex detection results into clear and actionable information, which not only improves the efficiency of network operation and management, but also effectively reduces maintenance costs and resource waste.

[0049] In a possible implementation, during the micro-disturbance injection process, a preset disturbance amplitude and frequency range are used, and a frequency band that has a significant impact on the sound wave propagation path is preferentially selected to improve the sensitivity of the leakage signal.

[0050] Specifically, in order to improve the sensitivity of the detection system to leakage signals, the sound wave frequency band with small propagation attenuation in the pipeline and significant leakage signal response is preferred. According to the physical characteristics of sound wave propagation in the pipeline, the propagation speed c can be calculated by the following formula:

[0051]

[0052] Where E represents the elastic modulus of the pipe material, t is the pipe wall thickness, and ρ f represents the fluid density in the pipe, and D is the inner diameter of the pipe. And the central frequency f of sound wave propagation can be determined according to the following formula c :

[0053]

[0054] Where λ is the optimized propagation wavelength of pipeline sound waves, which is determined by simulation experiments. Frequency range [f min ,f max ] is set at [0.8f c ,1.2f c ] to ensure the significance of the leakage response signal.

[0055] In a possible implementation manner, the propagation of the micro-disturbance signal in the pipe network follows the following formula:

[0056] P(x,t)=P 0 e -αx cos(2πft-kx)

[0057] Among them, P(x,t) represents the sound pressure at position x at time t, which is used to describe the propagation process of the sound wave signal. 0 is the initial sound pressure, which is used to calibrate the initial intensity of the sound wave signal. α is the sound wave attenuation coefficient, which is determined by the pipe material and fluid characteristics. It reflects the energy loss of the sound wave when it propagates in the pipeline and is related to the pipe material, fluid characteristics and leakage conditions. x is the spatial distance of sound wave propagation, which is used to establish the spatial association between propagation and leakage points. f is the sound wave frequency, which is optimized to 100Hz to 300Hz and is used to improve signal sensitivity. k is the wave number, which satisfies k=2πf / c, where c is the propagation speed of the sound wave in the pipeline. The above formula describes the propagation law of sound waves in the pipeline. Analyzing the characteristic changes of sound waves near the leakage point through the attenuation coefficient α and the propagation wave number k helps to accurately locate the leakage point.

[0058] In a possible implementation, traffic signal propagation satisfies the following formula:

[0059] Q(x)=Q 0 e -βx

[0060] Where Q(x) represents the flow at position x, which is used to quantify the impact of the leak on the flow. 0 is the initial flow rate, which is used to calibrate the input flow rate of the system. β is the flow attenuation coefficient, which is determined by the friction characteristics of the pipeline and the distribution of leakage points. It reflects the influence of leakage points and friction on the flow rate and is closely related to the pipeline material and fluid characteristics. x is the spatial distance of the flow monitoring position, which is used to analyze the change law of flow at different positions. The above formula is used to model the change of flow in the pipeline. By measuring the flow at different positions and fitting the attenuation curve β, flow anomalies can be identified and leakage points can be located.

[0061] In a possible implementation, during the anomaly detection and leakage location process, a multi-layer convolutional neural network algorithm is used to generate a leakage location prediction probability distribution map by inputting multi-dimensional spatiotemporal signal features collected by the sensor.

[0062] Specifically, the multi-dimensional spatiotemporal signal feature data collected by the sensor is first organized into a three-dimensional input tensor Where T represents the time step, N represents the number of sensor nodes, and F represents the characteristic dimension of each node (such as pressure, flow, acoustic amplitude, etc.);

[0063] Then, a convolutional neural network is constructed, which includes multiple convolutional layers, pooling layers, and fully connected layers. The convolutional layer extracts local features in spatial and temporal dimensions, the pooling layer is used for dimensionality reduction and noise reduction, and the fully connected layer is used for global feature integration and classification. The calculation process of the convolutional layer is as follows:

[0064]

[0065] in, is the output of the kth convolution kernel in the lth layer, is the convolution kernel weight, * indicates the convolution operation, b (k) is the bias, and σ is the activation function (such as ReLU).

[0066] Next, we use the output of the last layer of the convolutional neural network to generate the probability distribution P of each node as a leakage point through the Softmax function. leak (n):

[0067]

[0068] Among them, z n is the prediction score of the nth node.

[0069] Finally, based on the generated leakage location prediction probability distribution, a probability heat map on the pipe network topology is drawn. The heat map intuitively shows the location of potential leakage points and their probability weights, assisting subsequent decision-making.

[0070] In a possible implementation, the propagation anisotropy factor (PAF) is calculated as follows:

[0071]

[0072] Among them, PAF is the propagation anisotropy factor, which is used to quantify the directional change of the micro-disturbance signal in the pipeline, ΔP is the change in pressure during the propagation of the micro-disturbance signal, which is used to reflect the pressure fluctuation near the leak point, ΔL is the propagation path length corresponding to the pressure change, which is used to calculate the directional change of the propagation path, μ is the dynamic viscosity of the pipeline fluid, which is the resistance that affects the signal propagation, ρ is the density of the pipeline fluid, which is used to correct the propagation characteristics of the signal, and v is the average flow rate of the pipeline fluid, which is related to the pipe network material and fluid characteristics. The above formula quantifies the directional change in the micro-disturbance propagation process by combining pressure changes, distance and fluid characteristics, providing a reliable basis for locating the leak point.

[0073] In a possible implementation manner, the calculation formula of the leakage characteristic coefficient (LCC) is:

[0074]

[0075] Among them, LCC is the leakage characteristic coefficient, which is used to quantify the dynamic impact of the leakage point on the flow, Q in and Q out are the flow rates entering and leaving the network, respectively, Δt is the observation time interval, which is used to smooth the impact of dynamic changes, and A is the cross-sectional area of ​​the pipe, which is used to standardize the impact of leakage on flow. The above formula calculates the impact of leakage on flow based on the flow difference between the inlet and outlet, and combines the time interval and cross-sectional area to provide a standardized assessment for determining the leakage intensity and location of the leak point.

[0076] In a possible implementation, the possible position of the leakage point is further calibrated by a multi-dimensional curve fitting method in combination with the dynamic change trend of the PAF or the LCC.

[0077] Specifically, the real-time PAF value and LCC value of each monitoring node are collected to form a dynamic change trend sequence, which are expressed as:

[0078] PAF(t) = {PAF 1 (t),PAF 2 (t),...,PAF N (t)}

[0079] LCC(t) = {LCC 1 (t),LCC 2 (t),...,LCC N (t)}

[0080] Where N is the number of nodes and t is the time step.

[0081] Construct a multidimensional curve fitting model based on node geometric distribution and dynamic change characteristics, assuming that the leakage point is located at node n *, then the fitting equation is as follows:

[0082]

[0083] Among them, F(x,y,t) represents the surface function, φ i is the basis function, c i is the fitting coefficient, M is the number of basis functions, and (x, y) represents the plane coordinates of the node.

[0084] Substitute the known PAF and LCC data into the fitting model and optimize the fitting coefficients by minimizing the error function E:

[0085]

[0086] Finally, the possible position of the leakage point (x * ,y * ). Through this implementation, the dynamic change trend of PAF and LCC can be fully utilized to further optimize the preliminary predicted leakage position and significantly improve the accuracy of leakage location.

[0087] In a possible implementation, a multi-parameter optimization algorithm is used to perform a secondary correction on the predicted leakage position, thereby improving the positioning accuracy.

[0088] Specifically, key characteristic parameters closely related to the leakage location are selected, including P 1 : Nodal pressure gradient, P 2 : Flow deviation, P 3 : Sound wave propagation delay. Construct a multi-parameter feature set {P 1 ,P 2 ,P 3}, and the initial predicted position (x 0 ,y 0 ) association.

[0089] Construct an error objective function based on multiple parameters:

[0090] J(x,y)=w 1 ΔP 1 (x,y)+w 2 ΔP 2 (x,y)+w 3 ΔP 3 (x,y)

[0091] Where ΔP 1 (x, y) is the deviation between the predicted value and the monitored value at the leakage location (x, y), w i is the feature weight.

[0092] The objective function J(x,y) is iteratively optimized using gradient descent or particle swarm optimization (PSO) algorithm to obtain the optimal solution (x * ,y * ).

[0093] Finally, the optimized leakage location is output as the final result to further improve the prediction accuracy. Through the secondary correction of the multi-parameter optimization algorithm, multi-dimensional feature information can be comprehensively utilized to effectively reduce the error on the basis of the original leakage location prediction, thereby significantly improving the reliability and accuracy of pipeline network leakage positioning.

[0094] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0095] (1) In the present invention, by adopting the propagation anisotropy factor (PAF) and the leakage characteristic coefficient (LCC) combined with the multi-dimensional signal dynamic analysis of pressure, flow and sound waves in the pipeline, the problem of insufficient integration of multi-parameter information in the prior art is effectively solved, and the accuracy of leak location in complex pipe networks is significantly improved;

[0096] (2) In the present invention, by referring to the mathematical model based on the propagation of sound waves and flow signals, and the deep learning algorithm for the identification of abnormal data and the prediction of the leakage location, a real-time and intelligent leakage detection mechanism is constructed, which improves the detection efficiency and enhances the system's adaptability to complex environments;

[0097] (3) In the present invention, by calculating the anisotropy factor and leakage characteristic coefficient during the propagation of micro-disturbance, and further combining multi-dimensional curve fitting and multi-parameter optimization technology, the leakage point position is accurately calibrated and corrected, thereby effectively solving the problems of insufficient robustness and accuracy in the prior art.

[0098] Reference Manual Attached Figure 2 , showing a schematic structural diagram of a water supply and drainage pipeline leakage location positioning system provided by an embodiment of the present invention.

[0099] The present invention further provides a water supply and drainage pipeline leakage location positioning system 20, which is applied to the water supply and drainage pipeline leakage location positioning method, comprising:

[0100] Processor 201.

[0101] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the method for locating the leakage position of the water supply and drainage pipeline as described in the method embodiment is implemented.

[0102] A water supply and drainage pipe leakage location positioning system provided by the present invention can execute the water supply and drainage pipe leakage location positioning method described above, and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0103] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0104] (1) In the present invention, by adopting the propagation anisotropy factor (PAF) and the leakage characteristic coefficient (LCC) combined with the multi-dimensional signal dynamic analysis of pressure, flow and sound waves in the pipeline, the problem of insufficient integration of multi-parameter information in the prior art is effectively solved, and the accuracy of leak location in complex pipe networks is significantly improved;

[0105] (2) In the present invention, by referring to the mathematical model based on the propagation of sound waves and flow signals, and the deep learning algorithm for the identification of abnormal data and the prediction of the leakage location, a real-time and intelligent leakage detection mechanism is constructed, which improves the detection efficiency and enhances the system's adaptability to complex environments;

[0106] (3) In the present invention, by calculating the anisotropy factor and leakage characteristic coefficient during the propagation of micro-disturbance, and further combining multi-dimensional curve fitting and multi-parameter optimization technology, the leakage point position is accurately calibrated and corrected, thereby effectively solving the problems of insufficient robustness and accuracy in the prior art.

[0107] The above contents are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0108] There are a few points to note:

[0109] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0110] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0111] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0112] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for locating a leakage position of a water supply and drainage pipeline, characterized in that: include: S1. Based on the logistics structure and physical characteristics of the target water supply and drainage pipeline, the geometric structure, pipe diameter, material, node connection method and fluid characteristics of the pipeline system are collected to build a pipeline network model containing pipeline network topology information and fluid dynamics characteristics; S2. By analyzing the changing patterns of pipe network pressure, flow and acoustic wave signals, key nodes sensitive to leak detection are identified and set as micro-disturbance introduction points; S3. Introduce controllable pressure, flow or acoustic wave micro-disturbance signals at key nodes, record the dynamic characteristics of micro-disturbance signals propagating in the pipe network, and generate micro-disturbance signal simulation data; S4. Deploy sensor arrays at multiple nodes in the pipe network model to collect real-time monitoring data of various physical parameters including pressure, flow and sound waves; S5. Combining signal processing and data analysis techniques, the propagation process of the perturbation signal is simulated through the simulation model, and the simulation data is dynamically fitted using the propagation anisotropy factor (PAF) and the leakage characteristic coefficient (LCC); S6. Compare and analyze the monitoring data collected by the sensor with the simulation prediction data, identify abnormal changes in the monitoring data based on intelligent algorithms, and accurately locate the leakage point by combining the dynamic relationship between abnormal nodes and micro-disturbance propagation characteristics; S7. Generate a leak location report, including the location of the leak point, the estimated value of the leak scale and its dynamic change trend, to optimize the subsequent pipeline maintenance plan.

2. A method for locating a leakage position of a water supply and drainage pipeline according to claim 1, characterized in that: include: During the micro-disturbance injection process, a preset disturbance amplitude and frequency range are used, and a frequency band that has a significant impact on the sound wave propagation path is preferentially selected to improve the sensitivity of the leakage signal.

3. A method for locating a leakage position of a water supply and drainage pipeline according to claim 2, characterized in that: include: The propagation of the micro-disturbance signal in the pipe network follows the following formula: P(x,t)=P0e -αx cos(2πft-kx) Among them, P(x,t) represents the sound pressure at position x at time t, P0 is the initial sound pressure, α is the sound wave attenuation coefficient, which is determined by the pipe material and fluid properties, f is the sound wave frequency, k is the wave number, and k=2πf / c is satisfied, where c is the propagation speed of the sound wave in the pipe.

4. A method for locating a leakage position of a water supply and drainage pipeline according to claim 3, characterized in that: include: Traffic signal propagation satisfies the following formula: Q(x)=Q0e -βx Where Q(x) represents the flow rate at position x, Q0 is the initial flow rate, and β is the flow attenuation coefficient, which is determined by the friction characteristics of the pipeline and the distribution of leakage points.

5. A method for locating a leakage position of a water supply and drainage pipeline according to claim 1, characterized in that: include: In the anomaly detection and leakage location process, a multi-layer convolutional neural network algorithm is used to generate a leakage location prediction probability distribution map by inputting multi-dimensional spatiotemporal signal features collected by the sensor.

6. A method for locating a leakage position of a water supply and drainage pipeline according to claim 1, characterized in that: include: The calculation formula of the propagation anisotropy factor (PAF) is: Among them, ΔP is the change in pressure during the propagation of the micro-disturbance signal, ΔL is the propagation path length corresponding to the pressure change, μ is the dynamic viscosity of the pipeline fluid, ρ is the density of the pipeline fluid, and v is the average flow velocity of the pipeline fluid.

7. A method for locating a leakage position of a water supply and drainage pipeline according to claim 1, characterized in that: include: The calculation formula of the leakage characteristic coefficient (LCC) is: Among them, Q in and Q out are the flow rates entering and leaving the pipe network respectively, Δt is the observation time interval, and A is the cross-sectional area of ​​the pipe.

8. A method for locating a leakage position of a water supply and drainage pipeline according to claim 6 or 7, characterized in that: include: Combined with the dynamic change trend of the PAF or the LCC, the possible position of the leakage point is further calibrated by a multi-dimensional curve fitting method.

9. A method for locating a leakage position of a water supply and drainage pipeline according to claim 8, characterized in that: include: A multi-parameter optimization algorithm is used to perform secondary correction on the predicted leak location to improve the positioning accuracy.

10. A water supply and drainage pipeline leakage location positioning system, characterized in that: include: processor; A memory, wherein computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, the method for locating a leakage position in a water supply and drainage pipeline as described in any one of claims 1 to 9 can be implemented.

Images