A method, system, storage medium, and intelligent terminal for detecting leaks in water supply pipelines.

Abstract

This application relates to a method, system, storage medium, and smart terminal for detecting leaks in water supply pipelines, and pertains to the field of leak detection and location technology. The method includes: acquiring a training sample dataset; training a model on the training sample dataset to obtain model output results; calculating the sum of feature correlation weights; calculating the correlation weights of features in each group of sample data; calculating correlation information; acquiring selected sample data features; constructing a sample training set and a sample test set; and training and acquiring a leak detection model based on the sample training set. This application has the effect of improving the accuracy of detection by selecting only highly correlated features, reducing interference from other features, overcoming the interference and constraints of complex conditions on the leak detection method, and eliminating interference from other features.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of water leakage detection and positioning technology, in particular to a water supply pipeline leakage detection method, system, storage medium and intelligent terminal. BACKGROUND

[0002] Statistical data shows that the leakage problem of water supply pipelines is widespread, causing a large waste of water resources and huge economic losses. Not only that, a large amount of water seeps through the pipe network and underground space, not only causing waste of water resources, but also changing the surrounding soil structure, which is easy to form a large area of subsidence, posing a great threat to life and health. Therefore, it is urgent to solve this problem.

[0003] The traditional method for detecting leakage of urban water supply pipelines is to have experienced workers use special sound listening equipment to listen to the sound of water flowing through the pipeline along the pipeline at night, so as to determine whether the water pipe is leaking and the location of the leakage. Since this method can achieve a relatively high accuracy, even in developed countries, it is still the mainstream method for detecting leakage. The complex conditions in the real environment can greatly affect the effectiveness of this method, such as pipe material, pipe diameter, environmental noise, soil structure, buried depth, etc. These factors will affect the effectiveness of the sound listening equipment and the judgment of the workers.

[0004] There are problems in the prior art. At present, the model detection method is basically used, but due to the influence of complex conditions, the calculation cost and time cost of the model training process are greatly increased, and there is still room for improvement. SUMMARY

[0005] In order to improve the problem that the complex conditions in the real environment can greatly affect the effectiveness of the method and the effectiveness of the sound listening equipment and the judgment of the workers, the present application provides a water supply pipeline leakage detection method, system, storage medium and intelligent terminal.

[0006] In a first aspect, the present application provides a water supply pipeline leakage detection method, which adopts the following technical solution:

[0007] A water supply pipeline leakage detection method, comprising:

[0008] Obtaining a training sample data set, the training sample data set comprising a plurality of sets of sample data features;

[0009] Using a preset initial support vector machine algorithm to train the training sample data set to obtain a model output result and retain various model parameter information in the training model process;

[0010] Calculating the total sum of feature correlation weights according to the various model parameter information;

[0011] According to the model output result and each model parameter information, the correlation degree weight of each set of sample data features is calculated;

[0012] The ratio of the correlation degree weight of each set of sample data features to the total sum of feature correlation degree weights is calculated to obtain the correlation degree information of each set of sample data features;

[0013] According to the preset filtering mode, the correlation degree information is filtered to obtain the selected sample data features;

[0014] Based on the selected sample data features, a sample training set and a sample test set are constructed, and a leakage detection model is trained and obtained according to the sample training set.

[0015] By using the above technical scheme, the correlation degrees of various features of the leakage sound sample signal in the leakage detection task are calculated, a feature subset is selected, a support vector machine model is trained, and then a leakage detection result is obtained. On the one hand, only the features with high correlation degrees are selected, the interference of other features is reduced, the interference and constraints of complex conditions on the leakage detection method are overcome, and the detection accuracy is improved. On the other hand, the reduction of features effectively reduces the calculation cost and time cost in the model training process, thereby realizing real-time detection of the water supply network.

[0016] Optionally, before the step of using the preset initial support vector machine algorithm to train the training sample data set, the following steps are further included:

[0017] The sample data features are pre-emphasized, and the calculation method of pre-emphasis is:

[0018]

[0019] wherein, represents the output sample data features after pre-emphasis is completed, represents the obtained original sample data features, represents the i th original sample data feature, represents the i th sampling point of the original sample data feature. represents the i th sampling point of the original sample data feature. represents the i th sampling point of the original sample data feature.

[0020] By using the above technical scheme, the high-frequency components of the signal are enhanced by pre-emphasizing the monitoring signal, the original waveform when the leakage occurs is restored, the energy loss signal in the transmission process is compensated, the excessive attenuation of the high-frequency component signal is compensated in the compensation process, and the noise is not affected by the pre-emphasis, thereby improving the signal-to-noise ratio.

[0021] Optionally, before the step of using the preset initial support vector machine algorithm to train the training sample data set after pre-emphasizing the sample data features, the following steps are further included:

[0022] The sample data features in the training sample data set are standardized, and the standardization formula is:

[0023]

[0024] wherein, represents the original single sample data feature, represents the processed single sample data feature, represents the mean of the original sample data features in the same group, represents the standard deviation of the original sample data features in the same group.

[0025] By using the above technical solution, the feature data is standardized, so that all data are in the same order of magnitude, eliminating the influence of different dimensions between different features, and improving the comparability of data.

[0026] Optionally, the step of calculating the correlation weight of each group of sample data features according to the model output result and the model parameter information includes:

[0027] Obtaining the kernel function type of the support vector machine;

[0028] Determining the kernel function calculation formula based on the kernel function type;

[0029] Filling the kernel function calculation formula according to the retained model parameter information to obtain an adaptive kernel function calculation formula;

[0030] Inputting the model output result into the adaptive kernel function calculation formula to calculate the correlation weight of each group of sample data features.

[0031] By using the above technical solution, the feature correlation is calculated, so that there is a numerical comparison between each feature vector, so that the contribution of the feature is obtained, the user can easily select the feature that can best reflect the leakage condition, and the accuracy of feature identification of the leakage condition is improved.

[0032] Optionally, the step of constructing a sample training set and a sample test set based on the selected sample data features, and training and obtaining a leakage detection model according to the sample training set includes:

[0033] Model training is performed on the feature training sub-set to correct the original parameter information, and the corrected original parameter information is defined as corrected parameter information;

[0034] Adjusting the model parameters based on the corrected parameter information to obtain a corrected detection model;

[0035] The model is validated based on the modified detection model and the feature test subset to obtain the optimal detection model, which is then output as the leakage detection model.

[0036] By adopting the above technical solution, a support vector machine model is trained using a training set, and the model parameters are continuously adjusted during the process. The effectiveness of the model is verified using a test set, and the optimal leakage detection model is finally obtained, which improves the detection accuracy and the model training speed.

[0037] Optionally, the steps for determining the kernel function calculation formula based on the kernel function type include:

[0038] Determine if the kernel function type is a preset and decomposable type;

[0039] If so, the kernel function calculation formula is as follows:

[0040]

[0041] in, For support vectors, Represents the kernel function. The feature number;

[0042] If not, the kernel function calculation formula is as follows:

[0043]

[0044] in, satisfy , For pre-training results, and arrive The distance value is less than the preset order of magnitude.

[0045] By adopting the above technical solution and analyzing different kernel function types, an appropriate calculation method can be adopted for each data type, thereby improving the accuracy of calculation results for different data.

[0046] Optionally, the step of calculating the relevance weights of each set of sample data features based on the model output and various model parameter information further includes:

[0047] The protection parameters are determined based on the formula of the adaptation kernel function and the sum of the feature correlation weights.

[0048] The correlation information of each sample data feature in the signal feature set is calculated using the following formula:

[0049]

[0050] in, The feature relevance of a feature in the feature vector. The calculation result is obtained from the corresponding kernel function calculation formula. For the pre-training results, To protect parameters.

[0051] By adopting the above technical solution and setting protection parameters, the feature correlation is protected when the sum of feature correlation weights is too small or the feature correlation is too large, thereby improving feature correlation. The output is reasonable; at the same time, the settings of the protection parameters have played a role in suppressing noise interference.

[0052] Secondly, this application provides a water supply pipeline leak detection system, which adopts the following technical solution:

[0053] A water supply pipeline leak detection system, comprising:

[0054] The acquisition module is used to obtain the training sample dataset and kernel function type;

[0055] The memory is used to store the program of the control method for any of the above-mentioned water supply pipeline leakage detection methods;

[0056] The processor and the program in the memory can be loaded and executed by the processor to implement the control method of any of the above-mentioned water supply pipeline leakage detection methods.

[0057] By adopting the above technical solution, the correlation of various features of the leakage acoustic signal in the leakage detection task is calculated, a feature subset is selected, a support vector machine model is trained, and then the leakage detection result is obtained. On the one hand, only features with high correlation are selected, reducing the interference of other features, overcoming the interference and constraints of complex conditions on the leakage detection method, and improving the detection accuracy. On the other hand, the reduction of features effectively reduces the computational cost and time cost in the model training process, thereby realizing real-time detection of water supply networks.

[0058] Thirdly, this application provides a smart terminal, which adopts the following technical solution:

[0059] The intelligent terminal includes a memory and a processor, and the memory stores a computer program that can be loaded by the processor and executed any of the above-mentioned water supply pipeline leak detection methods.

[0060] By adopting the above technical solution, the correlation of various features of the leakage acoustic signal in the leakage detection task is calculated, a feature subset is selected, a support vector machine model is trained, and then the leakage detection result is obtained. On the one hand, only features with high correlation are selected, reducing the interference of other features, overcoming the interference and constraints of complex conditions on the leakage detection method, and improving the detection accuracy. On the other hand, the reduction of features effectively reduces the computational cost and time cost in the model training process, thereby realizing real-time detection of water supply networks.

[0061] Fourthly, this application provides a computer storage medium capable of storing corresponding programs, which features fast and accurate analysis and processing, and efficient training.

[0062] Computer-readable storage media adopt the following technical solutions:

[0063] A computer-readable storage medium storing a computer program that can be loaded by a processor and executed any of the above-described water supply pipeline leak detection methods.

[0064] By adopting the above technical solution, the correlation of various features of the leakage acoustic signal in the leakage detection task is calculated, a feature subset is selected, a support vector machine model is trained, and then the leakage detection result is obtained. On the one hand, only features with high correlation are selected, reducing the interference of other features, overcoming the interference and constraints of complex conditions on the leakage detection method, and improving the detection accuracy. On the other hand, the reduction of features effectively reduces the computational cost and time cost in the model training process, thereby realizing real-time detection of water supply networks.

[0065] In summary, this application includes at least the following beneficial technical effects:

[0066] 1. By selecting only highly relevant features and reducing interference from other features, the interference and constraints of complex conditions on leak detection methods are overcome, thereby improving the accuracy of detection.

[0067] 2. By training a support vector machine model using a training set and continuously adjusting the model parameters during the process, and verifying the model's effectiveness using a test set, the optimal leak detection model is finally obtained, which improves the detection accuracy and the model training speed. Attached Figure Description

[0068] Figure 1 This is a flowchart of a water supply pipeline leakage detection method according to an embodiment of this application.

[0069] Figure 2 This is a flowchart illustrating the steps in this application embodiment to calculate the relevance weights of each set of sample data features based on the model output results and various model parameter information.

[0070] Figure 3 This is a flowchart illustrating the steps in this application embodiment of constructing a sample training set and a sample test set based on selected sample data features, and training and obtaining a leakage detection model based on the sample training set.

[0071] Figure 4 This is a flowchart illustrating the steps of determining the kernel function calculation formula based on the kernel function type in an embodiment of this application.

[0072] Figure 5 This is a flowchart illustrating a further step in calculating the relevance weights of each set of sample data features based on the model output and various model parameter information in this embodiment of the application.

[0073] Figure 6 This is a system module diagram of a water supply pipeline leakage detection method according to an embodiment of this application. Implementation

[0074] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1-6 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0075] This application discloses a method for detecting leaks in water supply pipelines. (Refer to...) Figure 1 A method for detecting leaks in water supply pipelines includes:

[0076] Step 100: Obtain the training sample dataset, which includes several sets of sample data features.

[0077] The training sample dataset consists of sound signals from water supply pipes collected by users, used to train the detection model. The sample data features include time-domain features (skewness, kurtosis, waveform factor, peak factor, impulse factor, margin factor, zero-crossing rate, root mean square, power spectral entropy, singular spectral entropy, etc.), frequency-domain features (linear prediction coefficients, signal-to-noise ratio, spectral centroid, spectral bandwidth, spectral roll-off, spectral contrast, spectral flatness, etc.), and time-frequency-domain features (short-time Fourier spectrum, Mel spectrum, Mel cepstral coefficients, etc.). All data is acquired using listening devices.

[0078] Step 101: Pre-emphasize the features of the sample data.

[0079] Pre-emphasis enhances the high-frequency components of the sample data signal to compensate for excessive attenuation of these components during transmission. Since the energy of the sample data signal gradually diminishes during transmission, and the higher the signal frequency, the greater the energy loss, compensation is needed to restore the original waveform at the time of leakage. The pre-emphasis calculation method is as follows:

[0080]

[0081] in, This represents the characteristics of the sample data output after pre-emphasis is completed. This represents the characteristics of the received sample data to be processed. The first feature of the sample data to be processed One sampling point, The value of is between 0.9 and 1, and is determined by those skilled in the art based on experience. In embodiments of the present invention, The value is 0.97.

[0082] Step 102: Standardize the features of the sample data in the training sample dataset.

[0083] The purpose of standardization is to eliminate the influence of different dimensions between different features.

[0084] For example, using the most commonly used z-score normalization method, the calculation method is as follows:

[0085]

[0086] in Represents the original data. This indicates the processed data. This represents the mean of the original data. This represents the standard deviation of the original data, ultimately resulting in a data distribution with a mean of 0 and a variance of 1.

[0087] Step 103: Use the preset initial support vector machine algorithm to train the model on the training sample dataset to obtain the model output results and retain the model parameter information during the training process.

[0088] The pre-training result is the result obtained after training the model, and the model output is regarded as the correlation of various features. The sum of , its formula is:

[0089]

[0090] in, The feature number, The relevance of each feature vector will be explained in subsequent steps. At this stage, the model is not modified; that is, the parameters in the model do not need to be changed.

[0091] Step 104: Calculate the sum of feature relevance weights based on the model parameter information.

[0092] The calculation formula is as follows:

[0093]

[0094] in, This indicates the number of support vectors. These represent the support vectors, the labels corresponding to the support vectors, and the original parameters, respectively. Represents the kernel function.

[0095] Step 105: Calculate the relevance weights of the features of each set of sample data based on the model output and the model parameter information.

[0096] Feature correlation is the contribution of each feature vector to the classification task, where the classification task is to classify whether it is a leakage signal.

[0097] Reference Figure 2 The specific steps for calculating the relevance weights are as follows:

[0098] Step 1051: Obtain the kernel function type of the support vector machine.

[0099] The kernel function type corresponds to the type of the Support Vector Machine (SVM) algorithm, such as the linear kernel function, histogram crossover kernel function, chi-square kernel function, and Gaussian kernel function. Different kernel function types are used depending on the features, and the specific method for obtaining these types can be done by searching a database.

[0100] Step 1052: Determine the kernel function calculation formula based on the kernel function type.

[0101] The kernel function calculation formula is used to calculate the kernel function of a certain dimension of the feature vector.

[0102] Reference Figure 3 The specific steps to determine the kernel function calculation formula are as follows:

[0103] Step 10521: Determine whether the kernel function type is a preset and decomposable type.

[0104] The decomposable type is a type in which multiple values ​​can be added together and then split.

[0105] Step 105211: If so, the kernel function calculation formula is as follows:

[0106]

[0107] in, For support vectors, Represents the kernel function. The feature number.

[0108] If so, for example, a linear kernel function and a histogram cross kernel function, then it means that the kernel function of the feature vector is equal to the sum of the kernel functions of each feature dimension in the feature vector.

[0109] Step 105212: If not, the kernel function calculation formula is as follows:

[0110]

[0111] in, satisfy , For pre-training results, and arrive The distance value is less than the preset order of magnitude.

[0112] If not, for example, the chi-square kernel function and the Gaussian kernel function, then it means that the kernel function is differentiable, and the above formula can be used. To make the kernel function differentiable, at this time... arrive The distance value is less than the preset order of magnitude. arrive The distance between them is very close.

[0113] Step 10522: Fill in the kernel function calculation formula according to the retained model parameter information to obtain the adapted kernel function calculation formula.

[0114] To reduce computational complexity caused by changes in the kernel function calculation formula due to parameter variations, the parameters in the kernel function calculation formula remain unchanged, and only its contribution is calculated.

[0115] Step 10523: Input the model output results into the adaptation kernel function calculation formula to calculate the correlation weight of each group of sample data features.

[0116] Step 106: Calculate the ratio of the relevance weight of each group of sample data features to the sum of the feature relevance weights to obtain the relevance information of each group of sample data features.

[0117] Reference Figure 4 The specific steps for calculating the relevance weights of each set of sample data features by inputting the model output into the adaptation kernel function calculation formula are as follows:

[0118] Step 1061: Determine the protection parameters based on the formula of the adaptation kernel function and the sum of the feature correlation weights.

[0119] The protection parameter is to prevent the summation of feature relevance weights. The parameters corresponding to protective measures implemented with excessively small values ​​can also suppress noise interference. The set values ​​can be obtained by looking up a table, or by setting fixed values ​​manually, or by setting a fixed proportion manually, so that the sum of the protection parameters, kernel function, and feature correlation weights is on the same order of magnitude.

[0120] Step 1062: Calculate the correlation information of each sample data feature in the signal feature set. The formula for calculating the correlation information is as follows:

[0121]

[0122] in, The feature relevance of a feature in the feature vector. The calculation result is obtained from the corresponding kernel function calculation formula. For the pre-training results, To protect parameters.

[0123] Step 107: Filter the relevance information according to the preset filtering method to obtain the selected sample data features.

[0124] The filtering method can be manually set to filter based on the relevance of features. For example, a threshold can be set, meaning that features with a relevance greater than a certain threshold can be selected; or the number of features can be set, for example, 20 features, meaning that 20 features with the highest relevance can be selected.

[0125] Step 108: Construct a sample training set and a sample test set based on the selected sample data features, and train and obtain the leakage detection model based on the sample training set.

[0126] The feature training subset is the set of feature vectors from the signal feature subset used to train the support vector machine model. The feature test subset is the set of feature vectors from the signal feature subset used to verify the effectiveness of the trained detection model. The allocation can be done manually, with the training subset containing more feature vectors than the test subset, to ensure a more accurate final leak detection model. The leak detection model is a model capable of detecting whether a signal is leaking.

[0127] Reference Figure 5 The specific steps are as follows:

[0128] Step 1081: Train the model on the feature training subset to correct the original parameter information, and define the corrected original parameter information as the corrected parameter information.

[0129] The corrected parameter information refers to the parameters in the support vector machine model that have been adjusted after training.

[0130] Step 1082: Adjust the model parameters based on the correction parameter information to obtain the corrected detection model.

[0131] The detection model was corrected to a support vector machine model with adjusted model parameters.

[0132] Step 1083: Perform model validation based on the modified detection model and feature test subset to obtain the optimal detection model, and output the optimal detection model as the leakage detection model.

[0133] The purpose of validation is to test the effectiveness of all adjusted models. Then, based on each validation result, the optimal detection model is output.

[0134] Based on the same inventive concept, embodiments of the present invention provide a water supply pipeline leakage detection system.

[0135] Reference Figure 6 A water supply pipeline leak detection system, comprising:

[0136] The acquisition module is used to obtain the training sample dataset and kernel function type;

[0137] A memory for storing a program for a control method of a water supply pipeline leak detection method;

[0138] A processor is a control method for detecting leaks in water supply pipelines. The program in the memory can be loaded and executed by the processor.

[0139] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0140] This invention provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as a method for detecting leaks in a water supply pipeline.

[0141] Computer storage media include, for example, USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media that can store program code.

[0142] Based on the same inventive concept, embodiments of the present invention provide a smart terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded and executed by the processor to perform a method for detecting leaks in a water supply pipeline.

[0143] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A method for detecting leaks in water supply pipelines, characterized in that, include: Obtain a training sample dataset, which includes several sets of sample data features; The model is trained on the training sample dataset using a preset initial support vector machine algorithm to obtain the model output results and retain the model parameter information during the training process. Calculate the sum of feature relevance weights based on the model parameter information; Calculate the correlation weight of each group of sample data features based on the model output and various model parameter information; Calculate the ratio of the relevance weight of each feature in each set of sample data to the sum of the feature relevance weights to obtain the relevance information of each feature in each set of sample data; The relevance information is filtered according to the preset filtering method to obtain the features of the selected sample data; Based on the selected sample data features, a sample training set and a sample test set are constructed, and a leak detection model is trained and obtained based on the sample training set.

2. The method for detecting leaks in a water supply pipeline according to claim 1, characterized in that, Before training the model on the training sample dataset using the pre-defined initial support vector machine algorithm, the following steps are also included: The features of the sample data are pre-emphasized, and the pre-emphasis is calculated as follows: in, This represents the characteristics of the sample data output after pre-emphasis is completed. This indicates that the original sample data features have been obtained. The first characteristic representing the original sample data. indivual, The first feature of the original sample data The parameters of each sampling point.

3. The method for detecting leaks in a water supply pipeline according to claim 2, characterized in that, Before training the model on the training sample dataset using a preset initial support vector machine algorithm after pre-emphasizing the features of the sample data, the following steps are also included: The features of the sample data in the training sample dataset are standardized using the following formula: in, Represents the features of a single, original sample data. This represents the characteristics of a single processed sample data. This represents the mean of the original sample data from the same group. It represents the standard deviation of the characteristics of the original sample data from the same group.

4. The method for detecting leaks in a water supply pipeline according to claim 1, characterized in that, The steps for calculating the relevance weights of each set of sample data features based on the model output and model parameter information include: Get the kernel function type of the support vector machine; Determine the kernel function calculation formula based on the kernel function type; The kernel function calculation formula is filled in based on the retained model parameter information to obtain the adapted kernel function calculation formula; The model output is input into the adaptation kernel function to calculate the relevance weights of each set of sample data features.

5. The method for detecting leaks in a water supply pipeline according to claim 1, characterized in that, The steps for constructing a sample training set and a sample test set based on the selected sample data features, and then training and obtaining the leakage detection model based on the sample training set include: The model is trained on a subset of features to correct the original parameter information, and the corrected original parameter information is defined as the corrected parameter information. The model parameters are adjusted based on the correction parameter information to obtain the corrected detection model; The model is validated based on the modified detection model and the feature test subset to obtain the optimal detection model, which is then output as the leakage detection model.

6. The method for detecting leaks in a water supply pipeline according to claim 4, characterized in that, The steps to determine the kernel function calculation formula based on the kernel function type include: Determine if the kernel function type is a preset and decomposable type; a decomposable type is a type in which multiple values ​​can be added together and then split. If so, the kernel function calculation formula is as follows: in, For support vectors, Represents the kernel function. The feature number; If not, the kernel function calculation formula is as follows: in, satisfy , For pre-training results, and arrive The distance value is less than the preset order of magnitude.

7. The method for detecting leaks in a water supply pipeline according to claim 4, characterized in that, The step of calculating the relevance weights of each set of sample data features based on the model output and various model parameter information further includes: The protection parameters are determined based on the formula of the adaptation kernel function and the sum of the feature correlation weights. The correlation information of each sample data feature in the signal feature set is calculated using the following formula: in, The feature relevance of a feature in the feature vector. The calculation result is obtained from the corresponding kernel function calculation formula. For the pre-training results, To protect parameters.

8. A water supply pipeline leak detection system, characterized in that, include: The acquisition module is used to obtain the training sample dataset and kernel function type; A memory for storing a program of a control method for a water supply pipeline leakage detection method as described in any one of claims 1 to 7; The processor and the program in the memory can be loaded and executed by the processor to implement the control method of the water supply pipeline leakage detection method as described in any one of claims 1 to 7.

9. A smart terminal, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed as claimed in any one of claims 1 to 7 for detecting leaks in a water supply pipeline.

10. A computer-readable storage medium, characterized in that, The computer program is stored and can be loaded by a processor and executed as described in any one of claims 1 to 7, for detecting leaks in a water supply pipeline.

Images