CN-122015026-A - Water supply network leakage identification and positioning method and device based on surface array sampling

CN122015026ACN 122015026 ACN122015026 ACN 122015026ACN-122015026-A

Abstract

The invention discloses a water supply network leakage identification and positioning method based on surface array sampling, which comprises the steps of obtaining working condition parameters of an area where a water supply network is located, arranging sensor arrays at intervals on the surface of the ground along the axial direction of a pipeline of the water supply network based on the working condition parameters, collecting vibration signals in the pipeline through the sensor arrays, carrying out space domain Fourier change on the collected vibration signals at preset time steps to construct a corresponding wave number-frequency spectrum, and carrying out data analysis based on a waveform image of the wave number-frequency spectrum to obtain whether the pipeline leaks or not and the relative positions of leakage points and the sensor arrays. The invention also provides a water supply network leakage identifying and positioning device. When the method is applied to the ground surface, the technical bottleneck that the leakage of the buried pipeline is not detected and is inaccurate is broken through, and an efficient solution capable of being popularized in an engineering way is provided for reducing the leakage rate of the pipe network.

Inventors

YU TINGCHAO
WANG PENG
BAI CHENGLING
ZHOU LILI
CHEN XIAOYAN
Lin Wanhao
SHAO ZEYAN

Assignees

浙江大学长三角智慧绿洲创新中心
宁波市水务环境集团股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260213

Claims (8)

1.A water supply network leakage identification and positioning method based on surface array sampling is characterized by comprising the following steps: Acquiring working condition parameters of an area where the water supply network is located, and arranging sensor arrays at intervals on the ground surface along the axial direction of a pipeline of the water supply network based on the working condition parameters; collecting vibration signals in a pipeline through the sensor array, and performing time-space domain two-dimensional Fourier transform on the collected vibration signals at a preset time step to construct a corresponding wave number-frequency spectrum; labeling the wave number-frequency spectrum image according to whether the wave number-frequency spectrum image is a leakage signal or not, and the relative positions of the leakage signal and the sensing array, and forming a data set by the vibration signal, the wave number-frequency spectrum of the signal and the label; Constructing a leakage identification network, which comprises a feature extraction module and an analysis module; The feature extraction module is used for extracting wave number-frequency spectrum features in the input vibration signals; The analysis module is used for carrying out data analysis based on the wave number-frequency spectrum characteristics so as to obtain an identification result; training a leakage identification network by utilizing a data set to obtain a water supply pipeline leakage identification model for pipeline leakage identification and positioning; and inputting the vibration signal to be identified into a water supply pipeline leakage identification model to output whether the pipeline leaks or not and the relative positions of the leakage points and the sensing array.
2. The method for identifying and locating leakage of a water supply network based on surface array sampling according to claim 1, wherein the leakage location of the pipeline is obtained by moving the position of the sensing array a plurality of times and combining the relative positions of the leakage points and the sensing array.
3. The water supply network leakage identification and localization method based on surface array sampling as claimed in claim 1, wherein the interval distance expression of the sensor array is as follows: ; Where L represents the spacing between adjacent sensors, vF represents the pipeline fluid wave velocity, vW represents the pipeline housing wave velocity, vS represents the soil shear wave velocity, vP represents the soil compressional wave velocity, and f max represents the maximum observed frequency.
4. The method for identifying and locating water supply network leaks based on surface array sampling of claim 1, wherein the expression of the mounting aperture of each sensor in the sensor array is as follows: ; Wherein f min represents the minimum observation frequency, when the axial distance between the sensing array and the leakage point is more than 2m, c 1 and c 2 are vF and vW, the axial distance between the sensing array and the leakage point is less than or equal to 2m, and c 1 and c 2 are vS and vP.
5. The water supply network leakage identification and positioning method based on surface array sampling of claim 1, wherein the expression of the time-space domain two-dimensional Fourier transform is as follows: ; Wherein, the Is that Fourier transforms in the x and t directions, x pointing axially of the pipe, The axial wave number of the pipeline is represented, i represents an imaginary unit, and f represents frequency.
6. The surface array sampling-based water supply network leak identification and localization method of claim 1, wherein the data analysis includes leak identification and leak localization.
7. The water supply network leak identification and localization method based on surface array sampling of claim 1, wherein the leak identification network is constructed based on a pre-trained neural network model SqueezeNet framework and a convolutional neural network model framework.
8. A water supply network leakage identifying and positioning device, characterized by being used for executing the steps of the water supply network leakage identifying and positioning method based on surface array sampling according to any one of claims 1-7.

Description

Water supply network leakage identification and positioning method and device based on surface array sampling Technical Field The invention belongs to the technical field of municipal water supply systems, and particularly relates to a water supply network leakage identification and positioning method and device based on surface array sampling. Background In the water supply process, about 20-30% of the treated water is lost due to leakage of the pipeline, so that huge water resource waste is caused, secondary disasters such as drinking water pollution and ground collapse can be caused, and the safety and social stability of people are threatened. Among the numerous leak detection methods, acoustic detection has become the dominant method in the world today due to its advantages of non-invasiveness, high sensitivity, and low cost. Acoustic-based leak detection targets include leak identification and leak location. In the aspect of leakage identification, the traditional acoustic leakage identification is to analyze the time domain, the frequency domain or the time-frequency domain of leakage signals acquired by a single-point sensor in an attempt to extract characteristics (such as entropy, standard deviation, root mean square and the like) of the leakage sound signals so as to judge whether leakage exists or not. However, this approach faces a serious challenge in that the leakage vibration source intensity is close to the background noise, greatly reducing the leakage identification accuracy. In terms of leak location, correlation analysis methods are also widely used for water supply pipe leak location by calculating the time delay of a leak signal to reach sensors on both sides of the leak to achieve location. However, correlation analysis method positioning requires leak location estimation by means of wave velocity. In buried pipeline systems, the propagation speed of vibration is related to pipeline and soil properties, and the wave speed of leakage noise in a specific system is not single, and the characteristics of multi-mode wave aliasing are provided, so that the wave speed is difficult to calculate. At present, the empirical wave velocity of the fluid wave or the shell wave mode is measured, so that the positioning accuracy is insufficient. In addition, for nonmetallic pipelines, due to damping of the pipe wall, the attenuation rate experienced by the wave when propagating along the pipeline is relatively high, the propagation distance of leakage noise on the pipeline is generally less than 50m, and at the moment, correlation calculation positioning by means of a fire hydrant cannot be carried out. The patent CN120488150A discloses a water network pipeline leakage positioning method and system, wherein the method comprises the steps of collecting pressure data and flow data of a water network pipeline, carrying out data analysis on the pressure data and the flow data, judging whether a pipeline to be detected is leaked, dispersing a pipeline system in a pre-constructed mathematical model of the leakage pipeline under the condition that the pipeline to be detected is leaked, determining a calculation area, selecting the positions of pressure detection points of the water network pipeline, calculating the pressure values of the obtained pressure detection points under the condition that the pipeline is leaked differently, carrying out sensitivity analysis on each node of a main pipeline and a branch pipeline of the water network by adopting a correlation function method, comparing the correlation coefficient of each node, and determining the positions of pipeline leakage points based on the correlation coefficient. Patent document CN117628421a discloses a leakage positioning method in a water supply network environment, which comprises the steps of respectively obtaining a detection signal Sa and a detection signal Sb, respectively placing the detection signal Sa and the detection signal Sb on two sides of a leakage point, respectively carrying out aggregate empirical mode decomposition and decomposition on the detection signal Sa and the detection signal Sb to correspondingly obtain a plurality of component signals a and a plurality of component signals B, respectively selecting a component signal containing a leakage source from time-frequency domain information of the plurality of component signals a and the plurality of component signals B to correspondingly obtain the leakage component signals a and the leakage component signals B, respectively carrying out signal reconstruction according to the leakage component signals a and the leakage component signals B to correspondingly obtain the leakage source signals a and the leakage source signals B, respectively determining time delay information according to time domain waveforms of the leakage source signals a and the leakage source signals B, and determining a leakage position on a water supply pipe according to the time delay information. Dis