A method, apparatus, medium, and equipment for locating pipeline leaks.

Abstract

This invention discloses a method, apparatus, medium, and equipment for locating pipeline leaks, relating to the field of pipeline leak location technology. The invention first acquires pressure pulsation signals from both upstream and downstream ends of the pipeline. Then, it converts these signals from time-domain data to frequency-domain data and segments them using wavelet packet decomposition to obtain more detailed local frequency information. Based on this, the maximum amplitude is used as a feature selection criterion, and the frequency bands exhibiting the maximum amplitude are selected as the feature frequency bands for both upstream and downstream ends. Furthermore, each feature frequency band is segmented according to its maximum amplitude within a preset segmentation range to obtain three feature sub-frequency bands. Finally, cross-correlation analysis is performed on each corresponding frequency band or feature sub-frequency band at both upstream and downstream ends. This narrows the range of frequency bands with the maximum amplitude during cross-correlation analysis, highlighting the effective information in the signal and thus improving the accuracy of cross-correlation analysis in locating the leak point.

Description

Technical Field

[0001] This invention relates to the field of pipeline leak location technology, and in particular to a pipeline leak location method, apparatus, medium and equipment. Background Technology

[0002] Currently, pipeline transportation is characterized by large transport capacity and low cost. However, due to long-term underground burial, pipelines suffer from varying degrees of wear, corrosion, aging, and other damage, leading to various forms of leakage. Failure to detect leaks in a timely manner can result in significant property damage, environmental pollution, and safety hazards to people's living environment. Therefore, accurately locating pipeline leaks and improving the efficiency of fault identification are crucial for effective leak detection.

[0003] In recent years, a scheme for locating pipeline leaks through cross-correlation analysis has been proposed in the existing technology. When a pipeline leaks, the leak point will generate specific sound waves or vibrations that propagate in the pipeline. Based on this, cross-correlation analysis can be performed on the signals collected at different locations in the pipeline to determine the time delay between the sound wave signals received at different locations, thereby locating the pipeline leak point.

[0004] However, compared to the large number of signals collected, the effective signals are often not prominent enough, resulting in poor accuracy when locating leak points based on cross-correlation analysis. Summary of the Invention

[0005] Therefore, it is necessary to provide a pipeline leak location method, device, medium, and equipment to address the aforementioned technical problems.

[0006] The present invention adopts the following technical solution:

[0007] This invention provides a method for locating pipeline leaks, comprising:

[0008] The pressure pulsation signals at both the upstream and downstream ends of the pipeline are acquired, and the corresponding frequency domain signals are obtained by performing fast Fourier transform on the pressure pulsation signals at both ends respectively.

[0009] Wavelet packet decomposition is performed on the frequency domain signals corresponding to the pressure pulsation signals at both ends to determine the number of decomposition layers and the frequency bands obtained from the decomposition. The frequency bands with the largest amplitude are then obtained as the characteristic frequency bands at both the upstream and downstream ends.

[0010] The characteristic frequency bands at both the upstream and downstream ends are segmented according to the maximum amplitude based on a preset segmentation range to obtain three characteristic sub-frequency bands; the characteristic frequency bands at both the upstream and downstream ends are replaced with the corresponding three characteristic sub-frequency bands;

[0011] By performing cross-correlation analysis on each frequency band or characteristic sub-frequency band corresponding to the upstream and downstream ends, the maximum cross-correlation coefficient of the pressure pulsation signals at the upstream and downstream ends of the pipeline is obtained, so as to determine the location of pipeline leakage.

[0012] Optionally, the characteristic frequency bands at both the upstream and downstream ends are segmented based on the maximum amplitude within a preset segmentation range to obtain three characteristic sub-frequency bands, specifically including:

[0013] The characteristic frequency bands at both the upstream and downstream ends are segmented according to a preset segmentation range using the following formula to obtain multiple sub-frequency bands: B h = (n, n+p), p>200,

[0014] The effective sub-bands containing the largest amplitude values ​​in the characteristic frequency bands at both the upstream and downstream ends are determined from each sub-band using the following formula:

[0015] The sub-bands before the effective sub-bands in the characteristic frequency bands at both the upstream and downstream ends are merged, and the sub-bands after the effective sub-bands are merged to obtain three corresponding characteristic sub-bands respectively.

[0016] In the formula, B h Let n be the starting frequency of the characteristic frequency band where the maximum amplitude exists at both the upstream and downstream ends, n+p be the ending frequency of the characteristic frequency band, and i be the total number of sub-bands. ATF S is the effective sub-band with the largest amplitude among the characteristic frequency bands at both the upstream and downstream ends. j (f) represents the local maximum amplitude value of the j-th sub-band.

[0017] Optionally, the characteristic frequency bands at both the upstream and downstream ends are segmented based on the maximum amplitude within a preset segmentation range to obtain three characteristic sub-frequency bands, specifically including:

[0018] The characteristic frequency bands at both the upstream and downstream ends are segmented based on the maximum amplitude within a preset segmentation range using the following formula to obtain three characteristic sub-frequency bands:

[0019] Feature sub-band 1: (n,f max -100);

[0020] Feature sub-band 2: (f max -100,f max +100);

[0021] Feature sub-band 3: (f max +100,n+p);

[0022] Where n is the starting frequency of the characteristic frequency band with the maximum amplitude at both the upstream and downstream ends, and n+p is the ending frequency of the characteristic frequency band with the maximum amplitude at both the upstream and downstream ends, f maxThis represents the frequency corresponding to the maximum amplitude.

[0023] Optionally, cross-correlation analysis is performed on each frequency band or characteristic sub-band corresponding to the upstream and downstream ends to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at both ends of the pipeline, in order to determine the location of the pipeline leak. Specifically, this includes:

[0024] The upstream and downstream ends are decomposed into time-domain signals corresponding to each frequency band or each characteristic sub-frequency band by an empirical wavelet filter bank.

[0025] Correlation analysis is performed on the waveforms of the time-domain signals corresponding to each frequency band or characteristic sub-frequency band upstream and the time-domain signals corresponding to each frequency band or characteristic sub-frequency band downstream to obtain the time-domain signals corresponding to the frequency band / characteristic sub-frequency band with the highest correlation between upstream and downstream.

[0026] Cross-correlation analysis was performed on the time-domain signals corresponding to the frequency bands / characteristic sub-frequency bands with the highest correlation between upstream and downstream to obtain the maximum correlation coefficient of the pressure pulsation signals at both ends of the pipeline and the corresponding signal propagation delay time at the leakage point.

[0027] The location of the leak point in the pipeline is determined by the propagation delay time of the leak point signal corresponding to the maximum cross-correlation coefficient of the pressure pulsation signals at the upstream and downstream ends of the pipeline, the distance between the sensors used to collect the pressure pulsation signals at the upstream and downstream ends of the pipeline, and the propagation speed of the pulsation signal.

[0028] This invention provides a pipeline leak locating device, comprising:

[0029] The acquisition module is used to acquire the pressure pulsation signals at both ends of the pipeline, and to perform fast Fourier transform on the pressure pulsation signals at both ends to obtain the corresponding frequency domain signals.

[0030] The decomposition module is used to perform wavelet packet decomposition on the frequency domain signals corresponding to the pressure pulsation signals at both ends, determine the number of decomposition layers and the frequency bands obtained by the decomposition, and obtain the frequency band with the largest amplitude as the characteristic frequency bands of the upstream and downstream ends.

[0031] The segmentation module is used to segment the characteristic frequency bands at both the upstream and downstream ends according to the maximum amplitude based on a preset segmentation range to obtain three characteristic sub-frequency bands; and to replace the characteristic frequency bands at both the upstream and downstream ends with the corresponding three characteristic sub-frequency bands.

[0032] The analysis module is used to perform cross-correlation analysis on each frequency band or characteristic sub-frequency band corresponding to the upstream and downstream ends to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at the upstream and downstream ends of the pipeline, so as to determine the location of pipeline leakage.

[0033] The present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described pipeline leak location method.

[0034] The present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned pipeline leak location method.

[0035] The above-mentioned at least one technical solution adopted in this invention can achieve the following beneficial effects:

[0036] This invention first acquires pressure pulsation signals from both upstream and downstream ends of a pipeline. Then, it converts these signals from time-domain data to frequency-domain data and segments them using wavelet packet decomposition to obtain more detailed local frequency information. Based on this, the maximum amplitude is used as a feature selection criterion, and the frequency bands with the maximum amplitude are selected as the feature frequency bands for both upstream and downstream ends. Furthermore, the feature frequency bands are further segmented according to the maximum amplitude based on a preset segmentation range to obtain three feature sub-frequency bands. Finally, cross-correlation analysis is performed on each frequency band or feature sub-frequency band corresponding to both upstream and downstream ends. This narrows the range of frequency bands with the maximum amplitude during the cross-correlation analysis process, highlights the effective information in the signal, and thus improves the accuracy of leak point location based on cross-correlation analysis. Attached Figure Description

[0037] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0038] Figure 1 This is a schematic diagram of a pipeline leak location method provided by the present invention;

[0039] Figure 2 A schematic diagram for locating a pipeline leak provided by the present invention;

[0040] Figure 3 A schematic diagram of effective frequency band extraction provided by the present invention;

[0041] Figure 4 A schematic diagram of a pipeline leak location device provided by the present invention;

[0042] Figure 5 A schematic diagram of a computer device for implementing a pipeline leak location method provided by the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0044] Several methods for detecting pipeline leaks have been proposed, such as using machine learning and other technologies to identify leak characteristics for localization. Although these methods can handle complex data and are highly adaptable, they often require a large amount of data to train the model, placing high demands on the computing power of the equipment and resulting in high investment costs. In addition, there are schemes for locating pipeline leaks through cross-correlation analysis. However, compared to the large amount of signals collected, the effective signals are often not prominent enough, resulting in poor accuracy in locating leak points when using cross-correlation analysis.

[0045] The technical solutions provided by the various embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0046] Figure 1 This is a schematic diagram of a pipeline leak location method according to the present invention, which specifically includes the following steps:

[0047] S101: Obtain the pressure pulsation signals at both the upstream and downstream ends of the pipeline, and perform fast Fourier transform on the pressure pulsation signals at both ends to obtain the corresponding frequency domain signals.

[0048] S102: Perform wavelet packet decomposition on the frequency domain signals corresponding to the pressure pulsation signals at both ends, determine the number of decomposition layers and the frequency bands obtained from the decomposition, and obtain the frequency bands with the largest amplitude as the characteristic frequency bands of the upstream and downstream ends.

[0049] S103: Divide the characteristic frequency bands at both the upstream and downstream ends into three characteristic sub-frequency bands based on the maximum amplitude and a preset segmentation range; replace the characteristic frequency bands at both the upstream and downstream ends with the corresponding three characteristic sub-frequency bands.

[0050] S104: Based on cross-correlation analysis of each frequency band or characteristic sub-frequency band corresponding to the upstream and downstream ends, the maximum cross-correlation coefficient of the pressure pulsation signals at the upstream and downstream ends of the pipeline is obtained to determine the location of pipeline leakage.

[0051] For ease of explanation, the following description focuses solely on the server as the executing entity. The server mentioned in this invention can be a server set up on a business platform, or a device such as a desktop computer or laptop computer capable of executing the solution of this invention.

[0052] When locating a pipeline leak, sensors are typically installed upstream and downstream of the pipeline to receive pressure pulsation signals from the leak sound as it propagates along the pipeline. Cross-correlation analysis is then performed to determine the time lag of the pressure pulsation signals at both ends. Combined with the speed of sound propagation, the leak point can be located. Figure 2 As shown, Figure 2 This is a schematic diagram of a pipeline leak location method according to the present invention.

[0053] Based on this, in one or more embodiments of the present invention, the server can first obtain the pressure pulsation signals at both ends of the pipeline, and perform Fast Fourier Transform (FFT) on the pressure pulsation signals at both ends to obtain the corresponding frequency domain signals, thereby obtaining the total frequency band frequency domain signal map at both ends.

[0054] Then, for each acquired signal, wavelet packet decomposition is performed using Empirical Wavelet Transform (EWT) to obtain the corresponding decomposition level and frequency band. Effective feature extraction is then performed using the λτωη-π method. Specifically, for feature frequency band B... h Further segmentation, and based on the maximum amplitude, the characteristic frequency band B h It is divided into three characteristic sub-bands.

[0055] In one or more embodiments of the present invention, when the server divides the characteristic frequency bands at both upstream and downstream ends into three characteristic sub-frequency bands based on the maximum amplitude value and a preset segmentation range, it refers to... Figure 3 , Figure 3 This is a schematic diagram of an effective frequency band extraction method in this invention.

[0056] The characteristic frequency bands at both the upstream and downstream ends can be segmented according to a preset segmentation range using the following formula to obtain multiple sub-frequency bands: B h = (n, n+p), p>200,

[0057] In the formula, B h The characteristic frequency band with the maximum amplitude exists at both the upstream and downstream ends, n is the starting frequency of the characteristic frequency band, n+p is the ending frequency of the characteristic frequency band, and i is the total number of sub-bands.

[0058] Then, each sub-band f can be... i and the local maximum amplitude S of the corresponding sub-band i (f) As a calculation index, calculate the effective sub-band i ATF Used for locating pipeline leaks, each sub-band f i and the local maximum amplitude S of the corresponding sub-band i (f) and B h Maximum amplitude S iMAX(f) The expression is as follows:

[0059]

[0060] S iMAX (f) = max{S1, S2, S3, ..., S... i}

[0061] In the formula, f i For each frequency band after the pipeline is divided into frequency bands, S i (f) is the maximum amplitude value corresponding to each frequency band.

[0062] Then, the effective sub-frequency bands containing the largest amplitude values ​​in the characteristic frequency bands at both the upstream and downstream ends are determined from each sub-frequency band using the following formula:

[0063] In the formula, i ATF S is the effective sub-band with the largest amplitude among the characteristic frequency bands at both the upstream and downstream ends. j (f) represents the local maximum amplitude value of the j-th sub-band.

[0064] Finally, the sub-bands before the effective sub-bands in the characteristic frequency bands at both the upstream and downstream ends are merged, and the sub-bands after the effective sub-bands are merged to obtain the three corresponding characteristic sub-bands.

[0065] Furthermore, in one or more embodiments of the present invention, the characteristic frequency bands at both upstream and downstream ends can be segmented based on the maximum amplitude value within a preset segmentation range using the following formula to obtain three characteristic sub-frequency bands:

[0066] Feature sub-band 1: (n,f max -100);

[0067] Feature sub-band 2: (f max -100,f max +100);

[0068] Feature sub-band 3: (f max +100,n+p).

[0069] In the formula, n is the starting frequency of the characteristic frequency band with the maximum amplitude at both the upstream and downstream ends, n+p is the ending frequency of the characteristic frequency band with the maximum amplitude at both the upstream and downstream ends, and f max This represents the frequency corresponding to the maximum amplitude.

[0070] Finally, in the EWT wavelet packet decomposition to obtain the corresponding decomposition levels and frequency bands, the characteristic frequency bands at both the upstream and downstream ends are replaced with the corresponding three characteristic sub-frequency bands. Cross-correlation analysis is then performed on each frequency band or characteristic sub-frequency band at both the upstream and downstream ends to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at both ends of the pipeline, thus determining the location of the pipeline leak. That is, characteristic frequency band B... h After processing, three characteristic sub-bands were obtained. Cross-correlation analysis was performed on each characteristic band or sub-band to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at both ends of the pipeline. By combining the speed of sound propagation and calculating the delay time τ0, the location of the pipeline leak is determined using the formula for the location of the pipeline leak point.

[0071] For cross-correlation analysis, the principle is to solve the cross-correlation function to obtain the delay time of the signal from the leak point reaching the sensors at both ends. The pressure pulsation signals at the upstream and downstream ends of the pipeline reach their maximum correlation coefficient. The correlation is strongest, therefore, the delay time of the leak point signal is equal to the time corresponding to the position where the pressure pulsation signals at both the upstream and downstream ends have the highest correlation, which is the time corresponding to the peak position of the cross-correlation function.

[0072] Specifically, the upstream and downstream ends can first be decomposed into individual frequency bands or characteristic sub-bands using an empirical wavelet filter bank to obtain the time-domain signals corresponding to each frequency band or characteristic sub-band at each end. Then, correlation analysis is performed on the waveforms of the upstream and downstream time-domain signals corresponding to each frequency band or characteristic sub-band to obtain the time-domain signal corresponding to the frequency band / characteristic sub-band with the highest correlation. Next, cross-correlation analysis is performed on the two time-domain signals with the highest correlation to obtain the maximum correlation coefficient of the pressure pulsation signals at both ends of the pipeline and the corresponding leakage point signal propagation delay time. Therefore, based on the leakage point signal propagation delay time corresponding to the maximum cross-correlation coefficient of the pressure pulsation signals at both ends of the pipeline, the distance between the sensors used to collect the pressure pulsation signals at both ends of the pipeline, and the pulsation signal propagation speed, the location of the leakage point in the pipeline can be determined.

[0073] The correlation analysis mentioned here refers to performing correlation analysis on the amplitude waveforms of the time-domain signals corresponding to each upstream frequency band or characteristic sub-frequency band and the time-domain signals corresponding to each downstream frequency band or characteristic sub-frequency band. If the amplitude waveforms of the time-domain signals of two sub-frequency bands have the highest similarity, it can be said that the two sub-frequency bands have the maximum correlation coefficient. The time-domain signals corresponding to the two frequency bands / characteristic sub-frequency bands with the maximum correlation coefficient are used for subsequent cross-correlation analysis.

[0074] For example, suppose the time-domain signals corresponding to the upstream and downstream ends of a pipeline in a certain frequency band or a certain characteristic sub-frequency band are x(t) and y(t), respectively, and their mathematical models are as follows: x(t)=s(t)+n1(t); y(t)=αs(t-τ)+n2(t).

[0075] In the formula, s(t) is the leak point signal, which can be considered as a steady process when the pressure inside the pipe and the size of the leak point remain unchanged; α is the attenuation factor; τ is the delay time, ms; n1(t) and n2(t) are the environmental noise.

[0076] Assuming that the leak point signal and the environmental noise are both zero-mean and uncorrelated random signals, and that the environmental noise signals n1(t) and n2(t) are also uncorrelated, the correlation function of the leak point signal after separation from the finite integration time T is as follows: In the formula, Let T be the cross-correlation function, T be the sampling time, and τ0 be the delay time corresponding to the maximum cross-correlation function.

[0077] After correlation analysis, the time-domain signals corresponding to the two frequency bands / characteristic sub-bands with the highest correlation can be obtained. Then, cross-correlation analysis is performed on these signals to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at both the upstream and downstream ends of the pipeline. Generally, this maximum correlation coefficient is often obtained from the time-domain signal corresponding to the middle characteristic sub-band among the three characteristic sub-bands at both the upstream and downstream ends. Therefore, the pipeline leak can be further located based on the maximum cross-correlation coefficient of the pressure pulsation signals at both the upstream and downstream ends of the pipeline.

[0078] This invention first collects pressure pulsation signals from both upstream and downstream ends of a pipeline. The signals are then subjected to Fast Fourier Transform (FFT) at a set sampling rate and analysis time to obtain frequency domain signals. Each acquired signal is decomposed into wavelet packets using EWT to obtain the corresponding decomposition level and frequency band. The effective frequency band i is then extracted using a pipeline leak location method based on λτωη-π feature extraction. ATF In the EWT wavelet packet decomposition, which yields the corresponding decomposition level and frequency band, the previous frequency band B is... h After dividing the frequency into three sub-bands, cross-correlation analysis is performed on each frequency band / sub-band to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at both ends of the pipeline. Combined with the speed of sound propagation, the delay time τ0 is calculated, and the location of the pipeline leak is determined by the formula for the location of the leak point in the water supply pipeline.

[0079] based on Figure 1The pipeline leak location method shown in this invention first acquires the pressure pulsation signals at both the upstream and downstream ends of the pipeline. Then, it converts the pressure pulsation signals from time-domain data to frequency-domain data and segments them using wavelet packet decomposition to obtain more detailed local frequency information. Based on this, the maximum amplitude is used as the feature selection criterion, and the frequency band with the maximum amplitude is taken as the feature frequency band at both the upstream and downstream ends. Furthermore, the feature frequency band is segmented according to the maximum amplitude based on a preset segmentation range to obtain three feature sub-frequency bands. Finally, cross-correlation analysis is performed on each frequency band or each feature sub-frequency band corresponding to the upstream and downstream ends. This narrows the frequency band range with the maximum amplitude during the cross-correlation analysis process, highlights the effective information in the signal, and thus improves the accuracy of leak point location based on cross-correlation analysis.

[0080] When applying the pipeline leak location method provided by this invention, it is not necessary to rely on... Figure 1 The steps shown are executed in sequence. The specific execution order of each step can be determined as needed, and this invention does not impose any restrictions on it.

[0081] The above describes a pipeline leak location method provided by one or more embodiments of the present invention. Based on the same idea, the present invention also provides a corresponding pipeline leak location device, such as... Figure 4 As shown.

[0082] Figure 4 A schematic diagram of a pipeline leak location device provided by the present invention includes:

[0083] The acquisition module 201 is used to acquire the pressure pulsation signals at both ends of the pipeline, and to perform fast Fourier transform on the pressure pulsation signals at both ends to obtain the corresponding frequency domain signals.

[0084] The decomposition module 202 is used to perform wavelet packet decomposition on the frequency domain signals corresponding to the pressure pulsation signals at both ends, determine the number of decomposition layers of the wavelet packet decomposition and the frequency bands obtained by the decomposition, and obtain the frequency band with the largest amplitude as the characteristic frequency bands of the upstream and downstream ends respectively.

[0085] The segmentation module 203 is used to segment the characteristic frequency bands at both the upstream and downstream ends according to the maximum amplitude based on a preset segmentation range to obtain three characteristic sub-frequency bands; and to replace the characteristic frequency bands at both the upstream and downstream ends with the corresponding three characteristic sub-frequency bands.

[0086] Analysis module 204 is used to perform cross-correlation analysis on each frequency band or characteristic sub-frequency band corresponding to the upstream and downstream ends to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at the upstream and downstream ends of the pipeline, so as to determine the location of pipeline leakage.

[0087] Specific limitations regarding pipeline leak location devices can be found in the limitations of pipeline leak location methods described above, and will not be repeated here. Each module in the aforementioned pipeline leak location device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0088] The present invention also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 The provided method for locating pipeline leaks.

[0089] The present invention also provides Figure 5 The schematic diagram of the computer device shown is as follows: Figure 5 As shown, at the hardware level, this computer device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for business operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then executes it to achieve the above. Figure 1 The provided method for locating pipeline leaks.

[0090] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0091] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this invention.

Claims

1. A method of pipeline leak location, characterized by, The method comprises the following steps: obtaining pressure pulsation signals at both ends of the pipeline, and performing fast Fourier transform on the pressure pulsation signals at both ends to obtain corresponding frequency domain signals; performing wavelet packet decomposition on the frequency domain signals corresponding to the pressure pulsation signals at both ends to determine the decomposition level of the wavelet packet decomposition and each frequency band obtained by the decomposition, and obtaining a frequency band with the maximum amplitude as a characteristic frequency band at each end; segmenting the characteristic frequency band at each end into three characteristic sub-frequency bands according to the maximum amplitude and a preset segmentation range, and replacing the characteristic frequency band at each end with the corresponding three characteristic sub-frequency bands; performing cross-correlation analysis on the characteristic sub-frequency bands corresponding to both ends to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at both ends of the pipeline, so as to determine the position of the pipeline leakage; the characteristic frequency band at each end is segmented into three characteristic sub-frequency bands according to the maximum amplitude and a preset segmentation range, which specifically comprises: the characteristic frequency band at each end is segmented into three characteristic sub-frequency bands according to the maximum amplitude and a preset segmentation range by the following formula: Feature sub-band 1 : (n, f max -100); Feature sub-band 2: (f max -100, f max +100) Feature sub-band 3: (f max +100, n+p) wherein n is the starting frequency of the characteristic frequency band with the maximum amplitude at both upstream and downstream ends, n+p is the ending frequency of the characteristic frequency band with the maximum amplitude at both upstream and downstream ends, f max is the frequency corresponding to the maximum amplitude.

2. The pipeline leak locating method of claim 1 wherein, performing cross-correlation analysis on the characteristic sub-frequency bands corresponding to both ends to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at both ends of the pipeline, so as to determine the position of the pipeline leakage, which specifically comprises: performing decomposition on the characteristic sub-frequency bands corresponding to both ends by using an empirical wavelet filter bank to obtain time domain signals corresponding to each characteristic sub-frequency band at both ends; performing correlation analysis on the waveforms of the time domain signals corresponding to each characteristic sub-frequency band at the upstream and downstream to obtain time domain signals corresponding to the characteristic sub-frequency band with the highest correlation between the upstream and downstream; performing cross-correlation analysis on the time domain signals corresponding to the characteristic sub-frequency band with the highest correlation between the upstream and downstream to obtain the maximum correlation coefficient of the pressure pulsation signals at both ends of the pipeline and the signal propagation delay time of the leakage point; determining the position of the leakage point in the pipeline according to the signal propagation delay time of the leakage point corresponding to the maximum cross-correlation coefficient of the pressure pulsation signals at both ends of the pipeline, the distance between the sensors used to collect the pressure pulsation signals at both ends of the pipeline, and the pulsation signal propagation speed.

3. A pipeline leak locating apparatus characterized by, The method comprises the following steps: an acquisition module is configured to obtain pressure pulsation signals at both ends of the pipeline, and perform fast Fourier transform on the pressure pulsation signals at both ends to obtain corresponding frequency domain signals; a decomposition module is configured to perform wavelet packet decomposition on the frequency domain signals corresponding to the pressure pulsation signals at both ends to determine the decomposition level of the wavelet packet decomposition and each frequency band obtained by the decomposition, and obtain a frequency band with the maximum amplitude as a characteristic frequency band at each end; a segmentation module is configured to segment the characteristic frequency band at each end into three characteristic sub-frequency bands according to the maximum amplitude and a preset segmentation range, and replace the characteristic frequency band at each end with the corresponding three characteristic sub-frequency bands; an analysis module is configured to perform cross-correlation analysis on the characteristic sub-frequency bands corresponding to both ends to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at both ends of the pipeline, so as to determine the position of the pipeline leakage; the analysis module is configured to perform cross-correlation analysis on the characteristic sub-frequency bands corresponding to both ends to obtain the maximum cross-correlation coefficient of the pressure pulsation signals at both ends of the pipeline, so as to determine the position of the pipeline leakage. The characteristic frequency band at the upstream and downstream ends is segmented into three characteristic sub-frequency bands according to the maximum amplitude based on a preset segmentation range, and specifically includes: The characteristic frequency band at the upstream and downstream ends is segmented into three characteristic sub-frequency bands according to the maximum amplitude based on a preset segmentation range, and specifically includes: Feature sub-band 1: (n, f max -100); Feature sub-band 2: (f max -100, f max +100) Feature sub-band 3: (f max +100, n+p) wherein n is the starting frequency of the characteristic frequency band with the maximum amplitude at both upstream and downstream ends, n+p is the ending frequency of the characteristic frequency band with the maximum amplitude at both upstream and downstream ends, f max is the frequency corresponding to the maximum amplitude.

4. A computer-readable storage medium, characterized in that, The readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method in any one of claims 1-2.

5. A computer device, comprising: The readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method in any one of claims 1-2.

Images