A cross-correlation positioning method, device and electronic equipment for water supply network leakage point

Abstract

The embodiments of this specification disclose a method, device and electronic device for cross-correlation positioning of leaks in a water supply network. The method includes calculating each leakage detection result based on a correlation vector machine; when there are target leakage detection results that exceed a preset first credibility threshold, calculating the correlation coefficient; when the correlation coefficient is greater than a preset second credibility threshold, filtering each target signal data based on at least two preset groups of bandpass filters, performing envelope calculation on the filtered target signal data, and determining at least one suspected positioning point based on a time delay estimate; calculating the positioning score of each suspected positioning point, and determining the suspected positioning point with the highest positioning score as the target positioning point. The embodiments of this specification are less affected by the environment, and relatively accurate positioning calculations can be performed regardless of the frequency band of the signal.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to sound source localization technology, and more particularly to a method, device, and electronic device for cross-correlation localization of leaks in a water supply network. Background Art

[0002] When a pipeline leaks, the fluid in the pressure pipe passes through the leakage gap at high speed. Due to factors such as vibration, friction, and impact, the fluid will generate stress or shear force to form a leakage sound. The sound wave is propagated through the pipeline and the fluid in the pipeline as the medium, and due to the attenuation characteristics, the sound intensity of the leakage sound will rapidly weaken with increasing distance.

[0003] For the sound waves generated by leakage, noise monitors installed on the pipeline are generally used for data collection and leakage analysis. However, most of the existing noise monitors can only warn of pipeline leakage, but do not have the function of locating the leakage point. After the leakage point is discovered manually, it is necessary to go to the site to actively control the leak detector, related instruments and other equipment to locate it. The leakage point response has a lag and the positioning accuracy is not high. In addition, although a small number of existing noise detection equipment can also locate the leakage point, the leakage point positioning algorithm is only based on the time delay estimation algorithm of the cross-spectrum. This type of algorithm is greatly affected by the environment, the gain after processing is limited, and the positioning accuracy is still not high. Summary of the invention

[0004] In order to solve the above problems, one or more embodiments of this specification describe a method, device and electronic device for cross-correlation positioning of leakage points in a water supply network.

[0005] According to a first aspect, a cross-correlation positioning method for a leak in a water supply network is provided, the method comprising:

[0006] Based on the correlation vector machine, the signal data of each noise monitor is calculated respectively to obtain each leakage detection result;

[0007] When the target leakage detection results corresponding to two adjacent target noise monitors both exceed a preset first credibility threshold, calculating a correlation coefficient between the two target noise monitors based on a cross-correlation function;

[0008] When the correlation coefficient is greater than a preset second credibility threshold, filtering is performed on each target signal data based on at least two preset groups of bandpass filters, envelope calculation is performed on the filtered target signal data based on a generalized cross-spectrum phase transform weighted algorithm, and at least one suspected positioning point is determined based on a time delay estimation value corresponding to an envelope peak value;

[0009] The positioning scores corresponding to the suspected positioning points are weighted and calculated based on the envelope features, and the suspected positioning point with the highest positioning score is determined as the target positioning point.

[0010] Preferably, the leakage detection result includes a first leakage detection result and a second leakage detection result;

[0011] The signal data of each noise monitor is calculated based on the correlation vector machine to obtain each leakage detection result, including:

[0012] After each preset time period, the signal data of each noise monitor is calculated based on the correlation vector machine to obtain each of the first leakage detection results;

[0013] A leakage point troubleshooting instruction is obtained, and the noise monitor to be tested corresponding to the leakage point troubleshooting instruction is determined. The signal data of each noise monitor to be tested is respectively calculated based on a correlation vector machine to obtain each second leakage detection result.

[0014] Preferably, before calculating the correlation coefficient between the two target noise monitors based on the cross-correlation function, the method further includes:

[0015] Sending a first control instruction to each of the target noise monitors, wherein the first control instruction is used to control each of the target noise monitors to receive satellite positioning data and perform time synchronization with a pulse per second signal;

[0016] A second control instruction is sent to each of the target noise monitors, where the second control instruction is used to control each of the target noise monitors to collect the signal data at a preset collection time.

[0017] Preferably, the filtering process on each target signal data based on at least two preset groups of bandpass filters includes:

[0018] Performing frame processing on the target signal data corresponding to each of the target noise monitors based on a preset overlap ratio to obtain frame data;

[0019] The frame data are filtered based on at least two preset groups of bandpass filters.

[0020] Preferably, the determining at least one suspected positioning point based on the delay estimation value corresponding to the envelope peak value includes:

[0021] The peak time point corresponding to at least one envelope peak is used as a time delay estimation value, and each suspected positioning point corresponding to each time delay estimation value is determined based on the pipeline length between each target noise monitor and the time delay estimation value.

[0022] Preferably, the weighted calculation of the positioning scores corresponding to the suspected positioning points based on the envelope features includes:

[0023] Determine the envelope features corresponding to each of the suspected positioning points respectively, wherein the envelope features include envelope peak value, envelope time domain peak coefficient, envelope main lobe width and the number of valid positioning results of each channel of filtered data;

[0024] A weighted calculation is performed on each of the envelope features based on a preset envelope feature weight to obtain a positioning score corresponding to each of the suspected positioning points.

[0025] Preferably, the method further comprises:

[0026] Leakage point location information is generated based on the target location point, and the leakage point location information is sent to a preset target terminal, where the leakage point location information is chart information.

[0027] According to a second aspect, a cross-correlation positioning device for a water supply network leakage point is provided, the device comprising:

[0028] A first calculation module, used to calculate the signal data of each noise monitor based on a correlation vector machine to obtain each leakage detection result;

[0029] A second calculation module is used to calculate the correlation coefficient between the two target noise monitors based on the cross-correlation function when the target leakage detection results corresponding to two adjacent target noise monitors both exceed the preset first credibility threshold;

[0030] A third calculation module is used for filtering each target signal data based on at least two preset groups of bandpass filters when the correlation coefficient is greater than a preset second credibility threshold, performing envelope calculation on the filtered target signal data based on a generalized cross-spectrum phase transform weighted algorithm, and determining at least one suspected positioning point based on a time delay estimation value corresponding to an envelope peak;

[0031] The positioning module is used to weight and calculate the positioning scores corresponding to each of the suspected positioning points based on the envelope feature, and determine the suspected positioning point with the highest positioning score as the target positioning point.

[0032] According to a third aspect, there is provided an electronic device, comprising a processor and a memory;

[0033] The processor is connected to the memory;

[0034] The memory is used to store executable program code;

[0035] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0036] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a processor, cause the computer or the processor to execute the method provided in the first aspect or any possible implementation of the first aspect.

[0037] The methods and devices provided in the embodiments of this specification can achieve the following technical effects:

[0038] 1. It can intelligently calculate the leak point location without manual operation. When detecting leak points, it not only performs leakage detection on the signal data of a single noise monitor, but also combines the correlation coefficient between noise monitors to assist in judgment, further reducing the system's false detection rate, ensuring the reliability of key parameters, and improving positioning accuracy.

[0039] 2. By combining multiple preset bandpass filters with the generalized cross-spectral phase transform weighted algorithm, the scope of application of the method and the overall signal-to-noise ratio are improved, and the impact of the environment is small. No matter which frequency band the signal is in, more accurate positioning calculations can be performed. In addition, each suspected positioning result will be weighted and scored according to the envelope characteristics, which is more robust and can more objectively, accurately and reasonably select the correct item from multiple alternative results.

[0040] 3. It has both active and passive working modes, which provides greater operational flexibility and enables more timely response to leaks. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 It is a flow chart of a cross-correlation positioning method for a leak point in a water supply network in one embodiment of the present specification.

[0043] Figure 2 It is a structural schematic diagram of a cross-correlation positioning device for a leak point in a water supply network in one embodiment of the present specification.

[0044] Figure 3 It is a structural diagram of an electronic device in one embodiment of this specification. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0046] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application, and different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments recorded. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, although the embodiment may not be clearly recorded in the following text.

[0047] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present application. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described in some examples may be combined in other examples.

[0048] See also Figure 1 , Figure 1 : is a flow chart of a cross-correlation positioning method for a water supply network leak point provided in an embodiment of the present application. In an embodiment of the present application, the method includes:

[0049] S101. Calculate the signal data of each noise monitor based on a correlation vector machine to obtain each leakage detection result.

[0050] The execution entity of this application can be a cloud server.

[0051] In the embodiment of the present specification, the cloud server obtains the signal data collected by each noise monitor installed on the water supply network, and calculates each signal data through a relevance vector machine (RVM) to obtain a leakage detection result corresponding to each signal data.

[0052] Among them, RVM is a Bayesian sparse kernel algorithm for regression and classification, which uses the kernel function to convert the linear inseparable problem in low-dimensional space into a linear partition problem in high-dimensional space. RVM is a learning machine built on the Bayesian framework, which can calculate the output probability distribution and is suitable for multi-classification problems. Hyperparameters do not need to be obtained through cross-validation, and the kernel function can be specified arbitrarily and does not have to be positive. In addition, this application will also normalize the feature data set of the signal data, linearly scale each attribute to the interval [0, 1], avoid the attributes of the large numerical interval over-dominance of the attributes of the small numerical interval, and avoid numerical complexity in the calculation process.

[0053] Specifically, since the waveform of the leakage sound signal is extremely complex and is a combination of multiple component signals, it is a time-varying non-stationary random signal and has no obvious distinguishable features intuitively; from the spectrum, the leakage signal has a wide distribution band, concentrated in 200~2500Hz; this type of signal is difficult to characterize with a single feature parameter, and the pipeline leakage detection conditions are poor and are easily affected by surrounding interference sounds (such as rain, car sounds, electromagnetic interference, etc.). Therefore, this application extracts feature quantities from different angles, fully and accurately characterizes the characteristics of various signal data, and ensures low missed detection rate and false detection rate for leakage identification, as follows:

[0054] Time domain feature quantities: time domain rms, time domain dimensionless features (peak coefficient, kurtosis).

[0055] Frequency domain features: effective bandwidth, spectral kurtosis, and spectral entropy.

[0056] Other characteristic quantities: correlation approximate entropy, Hurst exponent, and fractal dimension.

[0057] In the application scenario of pipeline leakage detection, there may be many types of sounds in the scene, such as leakage sound, rain sound, car sound, water meter sound, electromagnetic interference sound, white noise, etc. This application will use the RVM classifier to distinguish the various types of sounds in the signal data to distinguish and obtain the sound size data corresponding to the leakage sound, that is, the leakage detection result.

[0058] The calculation formula of the RVM model can be:

[0059]

[0060] Among them, y is the classification label vector, x is the input vector (that is, the vector data corresponding to the signal data), is the basis function after x is mapped to high dimension, is the weight parameter matrix (the superscript T represents the matrix transpose operation).

[0061] In the case of the relevance vector machine, the basis function is given by the selected kernel function, and each data point in the training set is associated with a kernel function, so the above formula can be interpreted as:

[0062]

[0063] Where N is the number of samples in the input vector, b is the bias, is the kernel function, and u is the relevant vector relevanceVectors in the model.

[0064] The kernel function can use Gaussian radial basis function, and the corresponding calculation formula can be:

[0065]

[0066] in, is the Euclidean distance between two vectors, is the Gaussian kernel width.

[0067] In one possible implementation, the leakage detection result includes a first leakage detection result and a second leakage detection result;

[0068] The signal data of each noise monitor is calculated based on the correlation vector machine to obtain each leakage detection result, including:

[0069] After each preset time period, the signal data of each noise monitor is calculated based on the correlation vector machine to obtain each of the first leakage detection results;

[0070] A leakage point troubleshooting instruction is obtained, and the noise monitor to be tested corresponding to the leakage point troubleshooting instruction is determined. The signal data of each noise monitor to be tested is respectively calculated based on a correlation vector machine to obtain each second leakage detection result.

[0071] In the embodiment of the present specification, the cloud server can calculate and determine the leakage detection result through two modes of active detection and passive detection. Among them, the specific process of active detection is that the cloud server will actively calculate the signal data obtained from the noise monitor every preset time (for example, 24 hours) to obtain the first leakage detection result. The specific process of passive detection is that the staff can query the obtained signal data through the cloud server, and after analyzing the signal data, manually determine the noise monitor to be tested that needs to be calculated for the leakage detection result. After the staff completes the selection of the noise monitor to be tested, a leakage point investigation instruction will be generated. The cloud server will determine the noise monitor to be tested that needs to be investigated according to the leakage point investigation instruction, and calculate the various signal data of the noise monitor to be tested according to the relevant vector machine to obtain the second leakage detection result. Through the two detection modes of active detection and passive detection, the leakage point can be found more timely, thereby making the responsiveness of this scheme to the occurrence of leakage points more timely.

[0072] S102: When target leakage detection results corresponding to two adjacent target noise monitors both exceed a preset first credibility threshold, calculate a correlation coefficient between the two target noise monitors based on a cross-correlation function.

[0073] In the embodiments of the present specification, the leakage detection result can characterize the size of the detected leakage data signal. The cloud server will pre-set a first credibility threshold based on manual experience. If the leakage detection result is greater than the first credibility threshold, it is considered that the leakage detection result is characterized by the sound of leakage at the leakage point. If there are two adjacent target noise monitors that detect that the target leakage detection results exceed the first credibility threshold, that is, the two adjacent target noise monitors have detected the sound of leakage at the leakage point, then the cloud server can believe that there is a high probability of a leakage point between the two target noise monitors. Since the data detection results are easily affected by environmental factors, in order to improve the accuracy of the detection, the present application will adopt a dual detection mechanism. After determining that there is a high probability of a leakage point between the two target noise monitors based on the unilateral independent detection results of the target noise monitor and the first credibility threshold, the cloud server will also calculate the correlation coefficient between the two target noise monitors to further determine whether there is a leakage point between the two based on the joint detection results of both parties.

[0074] The specific calculation process of the correlation coefficient can be:

[0075] Two signals for two target noise monitors and Perform fft processing to obtain frequency domain data , , then, the cross power spectrum is calculated by the following formula:

[0076]

[0077] Among them, K is the number of fft points, is the angular frequency, is the phase difference, is the time delay between two signals.

[0078] Next, the cross power spectrum is subjected to inverse Fourier transform ifft to obtain the cross correlation function , the calculation formula is as follows:

[0079]

[0080] The cross-correlation coefficient is the normalized cross-correlation function value, so the cross-correlation function The normalization process is performed to obtain the mutual correlation coefficient, and the calculation formula is as follows:

[0081]

[0082] in, , are the sum of squares of the x and y sequences respectively.

[0083] It is used to measure the time domain correlation between two signals. The closer the value is to 1, the greater the commonality between the two sequences; the closer the correlation coefficient is to 0, the lower the correlation between the two.

[0084] In one possible implementation manner, before calculating the correlation coefficient between the two target noise monitors based on the cross-correlation function, the method further includes:

[0085] Sending a first control instruction to each of the target noise monitors, wherein the first control instruction is used to control each of the target noise monitors to receive satellite positioning data and perform time synchronization with a pulse per second signal;

[0086] A second control instruction is sent to each of the target noise monitors, where the second control instruction is used to control each of the target noise monitors to collect the signal data at a preset collection time.

[0087] In the embodiment of the present specification, before calculating the correlation coefficient between the two target noise monitors, in order to improve the accuracy of the calculation results, the two target noise monitors need to be synchronized first to ensure that the two target noise monitors collect data at the same time. Specifically, the cloud server will control the two target noise monitors through the first control instruction, so that the two target noise monitors are turned on in advance and receive Beidou satellite positioning data, and then perform time synchronization according to the pulse per second signal (1PPS) corresponding to the received Beidou satellite positioning data. After completing the time synchronization, the cloud server will also determine a collection time for the two target noise monitors through the second control instruction, so that the two target noise monitors collect signal data at the same time when the current time reaches the collection time. Finally, the target noise monitor will transmit the data to the cloud server in the form of NB-IoT.

[0088] S103. When the correlation coefficient is greater than a preset second credibility threshold, each target signal data is filtered based on at least two preset groups of bandpass filters, an envelope calculation is performed on the filtered target signal data based on a generalized cross-spectral phase transform weighted algorithm, and at least one suspected positioning point is determined based on a time delay estimation value corresponding to an envelope peak.

[0089] In the embodiment of the present specification, the cloud server will also pre-set a second credibility threshold based on manual experience. If the calculated correlation coefficient is greater than the second credibility threshold, it means that the correlation between the two target noise monitors is high and both target noise monitors have detected leakage signals. At this time, the cloud server will determine that there is a leakage point between the two target noise monitors.

[0090] This application takes into account that the pipeline leakage positioning environment is relatively harsh, and the delay estimation accuracy is affected by multiple factors, including noise, reverberation, and signal bandwidth. The main frequency band of the signal will also vary with the sound propagation medium. Therefore, the use of fixed filtering will not be able to meet the application of all scenarios. At present, some similar products will select the target frequency band based on the coherence function or the characteristic area on the phase spectrum, and then set the cutoff frequency for bandpass filtering. However, in reality, these characteristics are difficult to accurately quantify due to the influence of the environment, which will also seriously affect the positioning accuracy.

[0091] For the above reasons, this solution adopts a multi-path pre-filtering correlation processing method based on the generalized cross-spectral phase transform weighted algorithm (Gcc_PHAT), that is, the target signal data is filtered according to multiple preset groups of bandpass filters, and then envelope calculation and delay estimation are performed respectively in the Gcc_PHAT method to obtain all the alternative positioning results (that is, suspected positioning points), and then the final target positioning point is determined from each suspected positioning point through subsequent processing, rather than directly calculating and determining a final target positioning point, so as to improve the accuracy of the positioning result.

[0092] Specifically, if is the cutoff frequency of the 𝑖th group of filters, and the filtering method adopts a 4th-order Butterworth bandpass filter, then , They are , The filtered signal.

[0093] Next, , Perform FFT calculation to obtain frequency domain data , , the calculation formula of the generalized cross-spectral phase transform weighted algorithm is as follows:

[0094]

[0095] in, for The conjugation of.

[0096] From the above formula, we can see that the cross-spectrum phase transform weighting function is essentially a whitening filter, which makes the cross-power spectrum between signals smoother, thereby sharpening the generalized cross-correlation function. In this way, after subsequent PHAT weighting, the cross-power spectrum is similar to the expression of the unit impulse response, highlighting the delay peak, which can effectively suppress the reverberation noise and improve the precision and accuracy of the delay estimation.

[0097] Next, Perform inverse Fourier transform ifft to obtain the weighted cross-correlation function , and Perform Hilbert transform to get the corresponding envelope. is the envelope data of the 𝑛th frame signal after the 𝑖th group of filters. Assuming there are 𝑁 frames of data, the cloud server will perform time-series superposition on them. The final superposition envelope obtained after the 𝑖th group of filters is The envelope superposition operation reduces the influence of random interference or noise, and obtains signal-to-noise ratio gain. In theory, the more times the superposition is performed, the better the effect. The calculation formula of envelope superposition is as follows:

[0098]

[0099] Finally, the cloud server will calculate the result based on the envelope The envelope peak value is selected, and then the time delay estimate value is determined based on the envelope peak value, and the distance length between the two target noise monitors and the leakage point is calculated based on the time delay estimate value, and then the position of the suspected positioning point is determined.

[0100] In one possible implementation manner, the filtering process on each target signal data based on at least two preset groups of bandpass filters includes:

[0101] Performing frame processing on the target signal data corresponding to each of the target noise monitors based on a preset overlap ratio to obtain frame data;

[0102] The frame data are filtered based on at least two preset groups of bandpass filters.

[0103] In the embodiments of this specification, in order to make full use of the data length and eliminate the sudden interference during data acquisition, the target signal data will be framed according to a preset overlap ratio to obtain framed data, which will be filtered by a bandpass filter. , It can also be a frame of data at the same time after frame processing.

[0104] In one possible implementation manner, determining at least one suspected positioning point based on the delay estimation value corresponding to the envelope peak value includes:

[0105] The peak time point corresponding to at least one envelope peak is used as a time delay estimation value, and each suspected positioning point corresponding to each time delay estimation value is determined based on the pipeline length between each target noise monitor and the time delay estimation value.

[0106] In the embodiment of this specification, the envelope calculation result There will be at least one envelope peak in the data, and the peak time point corresponding to the envelope peak will be used as the delay estimate by the cloud server. That is to say, a delay estimate can determine a suspected positioning point. The cloud server will , pipeline length L and sound wave propagation speed v to calculate the suspected positioning points corresponding to each time delay estimation value. The specific calculation formula is as follows:

[0107]

[0108]

[0109] in, Noise monitor for suspected positioning points and targets The distance Same reason.

[0110] S104: Weightedly calculate the positioning scores corresponding to the suspected positioning points based on the envelope features, and determine the suspected positioning point with the highest positioning score as the target positioning point.

[0111] In the embodiment of the present specification, in order to determine the final target positioning point from the multiple suspected positioning points calculated, the cloud server will also obtain corresponding envelope features, such as envelope peak value, envelope main lobe width, etc., during the aforementioned envelope calculation process. Different suspected positioning points have different corresponding envelope features due to different corresponding envelope peak values. In addition, different feature weights are set for each envelope feature based on experience in advance. The cloud server can obtain the positioning score of each suspected positioning point by weighted calculation of each envelope feature of each suspected positioning point. The suspected positioning point with the highest positioning score is determined by the cloud server as the final target positioning point. By performing envelope calculation on the filtering results of multiple groups of bandpass filters, and determining multiple suspected positioning points from the envelope calculation results, and then calculating the positioning score of each suspected positioning point by weight, the target positioning point can be accurately determined without the assistance of other instruments and equipment, and the positioning accuracy is high compared to the method of directly calculating and determining a positioning point.

[0112] In one possible implementation, the weighted calculation of the positioning scores corresponding to the respective suspected positioning points based on the envelope features includes:

[0113] Determine the envelope features corresponding to each of the suspected positioning points respectively, wherein the envelope features include envelope peak value, envelope time domain peak coefficient, envelope main lobe width and the number of valid positioning results of each channel of filtered data;

[0114] A weighted calculation is performed on each of the envelope features based on a preset envelope feature weight to obtain a positioning score corresponding to each of the suspected positioning points.

[0115] In the embodiment of this specification, the feature value of the envelope feature involved in scoring may be as follows:

[0116] Envelope peak value Peak, that is, the approximate positioning reliability, the larger the value, the higher the reliability;

[0117] The time domain peak factor of the envelope peakFactor: This parameter directly reflects whether the envelope peak shape is sharp. Generally, the sharper the envelope shape, the higher the credibility. The calculation formula is as follows:

[0118]

[0119] in, , are the maximum value and effective value of the 𝑖th envelope, respectively.

[0120] Envelope main lobe width lobeWidth: Generally speaking, the smaller the main lobe width is, the higher the correlation between the data involved in the processing is, and the less interference is received. The calculation method is: the lobe width is intercepted with the peak value of -3db as the threshold;

[0121] The number of valid positioning results of frame data corresponding to each filtering data is validCnt: Taking the i-th group of data as an example, the positioning result of each frame is , by calculating the average , standard deviation , if the following logic is met, the frame result is considered valid:

[0122]

[0123] in It is set based on experience, and the value range is generally 1.2~2.0.

[0124] Different weights W are assigned according to the contribution of each eigenvalue to leakage identification, and the scoring method is calculated by the following formula:

[0125]

[0126] in, , , , are the scores corresponding to each feature.

[0127] In one embodiment, the method further comprises:

[0128] Leakage point location information is generated based on the target location point, and the leakage point location information is sent to a preset target terminal, where the leakage point location information is chart information.

[0129] In the embodiment of this specification, in order to allow the staff to intuitively see the location and situation of the leakage, the cloud server will generate leakage point location information in the form of icon information according to the target location point, and send it to the target terminal corresponding to the staff to automatically display the location of the leakage point to the staff. The staff can intuitively obtain the leakage situation and make subsequent decisions based on it.

[0130] The following will be combined with the attached Figure 2 , the cross-correlation positioning device for water supply network leakage points provided by the embodiment of the present application is introduced in detail. It should be noted that the attached Figure 2The cross-correlation positioning device for leak points in a water supply network shown in the present application is used to implement Figure 1 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 1 The embodiment shown.

[0131] See also Figure 2 , Figure 2 Schematic diagram of a cross-correlation positioning device for leak points in a water supply network provided in an embodiment of the present application. Figure 2 As shown, the device comprises:

[0132] The first calculation module 201 is used to calculate the signal data of each noise monitor based on the correlation vector machine to obtain each leakage detection result;

[0133] A second calculation module 202 is used to calculate the correlation coefficient between the two adjacent target noise monitors based on the cross-correlation function when the target leakage detection results corresponding to the two adjacent target noise monitors both exceed the preset first credibility threshold;

[0134] The third calculation module 203 is used to filter the target signal data based on at least two preset bandpass filters when the correlation coefficient is greater than a preset second credibility threshold, perform envelope calculation on the filtered target signal data based on a generalized cross-spectrum phase transform weighted algorithm, and determine at least one suspected positioning point based on a time delay estimation value corresponding to an envelope peak;

[0135] The positioning module 204 is used to weight and calculate the positioning scores corresponding to each of the suspected positioning points based on the envelope feature, and determine the suspected positioning point with the highest positioning score as the target positioning point.

[0136] In one possible implementation, the leakage detection result includes a first leakage detection result and a second leakage detection result;

[0137] The first calculation module 201 is specifically used for:

[0138] After each preset time period, the signal data of each noise monitor is calculated based on the correlation vector machine to obtain each of the first leakage detection results;

[0139] A leakage point troubleshooting instruction is obtained, and the noise monitor to be tested corresponding to the leakage point troubleshooting instruction is determined. The signal data of each noise monitor to be tested is respectively calculated based on a correlation vector machine to obtain each second leakage detection result.

[0140] In one possible implementation, the second calculation module 202 is specifically configured to:

[0141] Sending a first control instruction to each of the target noise monitors, wherein the first control instruction is used to control each of the target noise monitors to receive satellite positioning data and perform time synchronization with a pulse per second signal;

[0142] A second control instruction is sent to each of the target noise monitors, where the second control instruction is used to control each of the target noise monitors to collect the signal data at a preset collection time.

[0143] In one possible implementation, the third calculation module 203 is specifically used for:

[0144] Performing frame processing on the target signal data corresponding to each of the target noise monitors based on a preset overlap ratio to obtain frame data;

[0145] The frame data are filtered based on at least two preset groups of bandpass filters.

[0146] In one possible implementation, the third calculation module 203 is further configured to:

[0147] The peak time point corresponding to at least one envelope peak is used as a time delay estimation value, and each suspected positioning point corresponding to each time delay estimation value is determined based on the pipeline length between each target noise monitor and the time delay estimation value.

[0148] In one possible implementation, the positioning module 204 is specifically used for:

[0149] Determine the envelope features corresponding to each of the suspected positioning points respectively, wherein the envelope features include envelope peak value, envelope time domain peak coefficient, envelope main lobe width and the number of valid positioning results of each channel of filtered data;

[0150] A weighted calculation is performed on each of the envelope features based on a preset envelope feature weight to obtain a positioning score corresponding to each of the suspected positioning points.

[0151] In one embodiment, the device further comprises:

[0152] The sending module is used to generate leakage point location information based on the target location point, and send the leakage point location information to a preset target terminal, wherein the leakage point location information is chart information.

[0153] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0154] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0155] See also Figure 3 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, the electronic device can be used to implement Figure 1 The method in the embodiment shown. Figure 3 As shown, the electronic device 300 may include: at least one central processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0156] The communication bus 302 is used to realize the connection and communication between these components.

[0157] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0158] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0159] Among them, the central processing unit 301 may include one or more processing cores. The central processing unit 301 uses various interfaces and lines to connect various parts of the entire electronic device 300, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the central processing unit 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The central processing unit 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the central processing unit 301, and can be implemented separately through a chip.

[0160] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage device located away from the aforementioned central processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0161] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the central processor 301 can be used to call the cross-correlation positioning application of the water supply network leakage point stored in the memory 305, and specifically perform the following operations:

[0162] Based on the correlation vector machine, the signal data of each noise monitor is calculated respectively to obtain each leakage detection result;

[0163] When the target leakage detection results corresponding to two adjacent target noise monitors both exceed a preset first credibility threshold, calculating a correlation coefficient between the two target noise monitors based on a cross-correlation function;

[0164] When the correlation coefficient is greater than a preset second credibility threshold, filtering is performed on each target signal data based on at least two preset groups of bandpass filters, envelope calculation is performed on the filtered target signal data based on a generalized cross-spectrum phase transform weighted algorithm, and at least one suspected positioning point is determined based on a time delay estimation value corresponding to an envelope peak value;

[0165] The positioning scores corresponding to the suspected positioning points are weighted and calculated based on the envelope features, and the suspected positioning point with the highest positioning score is determined as the target positioning point.

[0166] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0167] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0168] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0169] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components 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 service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0170] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0171] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0172] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0173] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware. The program may be stored in a computer-readable memory, and the memory may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0174] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A cross-correlation positioning method for leak points in a water supply network, characterized in that: The method comprises: Based on the correlation vector machine, the signal data of each noise monitor is calculated respectively to obtain each leakage detection result; When the target leakage detection results corresponding to two adjacent target noise monitors both exceed a preset first credibility threshold, calculating a correlation coefficient between the two target noise monitors based on a cross-correlation function; When the correlation coefficient is greater than a preset second credibility threshold, filtering is performed on each target signal data based on at least two preset groups of bandpass filters, envelope calculation is performed on the filtered target signal data based on a generalized cross-spectrum phase transform weighted algorithm, and at least one suspected positioning point is determined based on a time delay estimation value corresponding to an envelope peak value; The positioning scores corresponding to the suspected positioning points are weighted and calculated based on the envelope features, and the suspected positioning point with the highest positioning score is determined as the target positioning point.

2. The method according to claim 1, characterized in that The leakage detection result includes a first leakage detection result and a second leakage detection result; The signal data of each noise monitor is calculated based on the correlation vector machine to obtain each leakage detection result, including: After each preset time period, the signal data of each noise monitor is calculated based on the correlation vector machine to obtain each of the first leakage detection results; A leakage point troubleshooting instruction is obtained, and the noise monitor to be tested corresponding to the leakage point troubleshooting instruction is determined. The signal data of each noise monitor to be tested is respectively calculated based on a correlation vector machine to obtain each second leakage detection result.

3. The method according to claim 1, characterized in that: Before calculating the correlation coefficient between the two target noise monitors based on the cross-correlation function, the method further includes: Sending a first control instruction to each of the target noise monitors, wherein the first control instruction is used to control each of the target noise monitors to receive satellite positioning data and perform time synchronization with a pulse per second signal; A second control instruction is sent to each of the target noise monitors, where the second control instruction is used to control each of the target noise monitors to collect the signal data at a preset collection time.

4. The method according to claim 1, characterized in that: The filtering process of each target signal data based on at least two preset groups of bandpass filters includes: Performing frame processing on the target signal data corresponding to each of the target noise monitors based on a preset overlap ratio to obtain frame data; The frame data are filtered based on at least two preset groups of bandpass filters.

5. The method according to claim 1, characterized in that The determining at least one suspected positioning point based on the delay estimation value corresponding to the envelope peak value includes: The peak time point corresponding to at least one envelope peak is used as a time delay estimation value, and each suspected positioning point corresponding to each time delay estimation value is determined based on the pipeline length between each target noise monitor and the time delay estimation value.

6. The method according to claim 1, characterized in that The weighted calculation of the positioning scores corresponding to the suspected positioning points based on the envelope features includes: Determine the envelope features corresponding to each of the suspected positioning points respectively, wherein the envelope features include envelope peak value, envelope time domain peak coefficient, envelope main lobe width and the number of valid positioning results of each channel of filtered data; A weighted calculation is performed on each of the envelope features based on a preset envelope feature weight to obtain a positioning score corresponding to each of the suspected positioning points.

7. The method according to claim 1, characterized in that The method further comprises: Leakage point location information is generated based on the target location point, and the leakage point location information is sent to a preset target terminal, where the leakage point location information is chart information.

8. A cross-correlation positioning device for leak points in a water supply network, characterized in that: The device comprises: A first calculation module, used to calculate the signal data of each noise monitor based on a correlation vector machine to obtain each leakage detection result; A second calculation module is used to calculate the correlation coefficient between the two target noise monitors based on the cross-correlation function when the target leakage detection results corresponding to two adjacent target noise monitors both exceed the preset first credibility threshold; A third calculation module is used for filtering each target signal data based on at least two preset groups of bandpass filters when the correlation coefficient is greater than a preset second credibility threshold, performing envelope calculation on the filtered target signal data based on a generalized cross-spectrum phase transform weighted algorithm, and determining at least one suspected positioning point based on a time delay estimation value corresponding to an envelope peak; The positioning module is used to weight and calculate the positioning scores corresponding to each of the suspected positioning points based on the envelope feature, and determine the suspected positioning point with the highest positioning score as the target positioning point.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium has instructions stored therein, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 7.

Images