Urban gas pipeline leakage detection method and system based on continuous infrasonic waves

Abstract

The invention relates to an urban gas pipeline leakage detection method and system based on continuous infrasonic waves, and the method comprises the steps: receiving a leakage detection instruction, and collecting the continuous infrasonic wave data in a preset group number of gas pipes and the continuous infrasonic wave data of the wall of the gas pipes based on a preset time interval as to-be-detected data; de-noising processing is carried out on the to-be-detected data; inputting the de-noised data to be detected into a pre-trained leakage detection model to obtain a plurality of groups of gas pipeline leakage detection results; and when the multiple groups of gas pipeline leakage detection results are consistent, reporting the gas pipeline leakage detection results to a superior platform. By continuously collecting infrasonic wave signals, the system can monitor the condition of the pipeline in real time, and the limitation that in a traditional method, sudden change signals cannot be detected in time after missing is avoided. No matter when the pipeline leaks, the system can acquire signals at any time and make judgment, and real-time discovery and response of leakage are ensured.

Description

Technical Field

[0001] This application relates to the technical field of pipeline leakage detection, and particularly to a method and system for detecting leakage of urban gas pipelines based on continuous infrasound waves. Background Art

[0002] Natural gas is an important source of fuel or raw materials in manufacturing and residences, and pipelines are crucial in the transportation, collection, and distribution of natural gas. Affected by factors such as non-compliance with pipeline construction quality specifications, corrosion and wear, human damage, and sudden natural disasters (earthquakes, debris flows), under the action of pressure difference, chemical gases in the pipeline are prone to leakage, causing destructive impacts on the human environment, production and life, and the safety of life and property. Therefore, detecting and locating leaks in gas transmission pipelines is of great significance for the safe operation and management of gas transmission pipelines.

[0003] Currently, the main methods for detecting leaks in gas transmission pipelines include the helium mass spectrometry method, the negative pressure wave method, the infrared detection method, the infrasound wave method, etc., among which the infrasound wave method is the most widely used.

[0004] The infrasound wave method monitors the acoustic wave signals of the pipeline in real time. At the moment of pipeline leakage, high-pressure gas is rapidly released, causing transient pressure fluctuations in the pipeline or the surrounding medium, manifested as a mutation in the infrasound wave signal, and based on this, it is judged as a leakage signal. However, the mutation is a transient signal. After the sudden leakage point is missed, the monitoring system can no longer detect leaks, and it does not have the characteristics of collecting signals at any time and judging whether there is a leak at any time. Summary of the Invention

[0005] To at least overcome to some extent the problem in the related art that when detecting leaks in gas transmission pipelines by the infrasound wave method, signals cannot be collected at any time and it cannot be judged whether there is a leak at any time, this application provides a method and system for detecting leaks in urban gas pipelines based on continuous infrasound waves.

[0006] The solution of this application is as follows:

[0007] According to the first aspect of the embodiments of this application, a method for detecting leaks in urban gas pipelines based on continuous infrasound waves is provided, including:

[0008] Receiving a leak detection instruction, and collecting a preset number of groups of continuous infrasound wave data in the gas pipeline and continuous infrasound wave data on the gas pipeline wall at preset time intervals as data to be detected;

[0009] Performing denoising processing on the data to be detected;

[0010] Inputting the denoised data to be detected into a pre-trained leak detection model to obtain multiple groups of gas pipeline leak detection results;

[0011] When the leakage detection results of multiple groups of gas pipelines are consistent, report the leakage detection results of the gas pipelines to the superior platform.

[0012] Preferably, the leakage detection instruction is automatically triggered by the system based on a period or actively triggered by the user.

[0013] Preferably, the method further includes:

[0014] When the leakage detection results of multiple groups of gas pipelines are inconsistent, report that there is an abnormality in the leakage detection of the gas pipelines to the superior platform.

[0015] Preferably, the method further includes:

[0016] Obtain the continuous infrasonic wave data in the normal gas pipeline, the continuous infrasonic wave data on the normal gas pipeline wall, the continuous infrasonic wave data in the leaking gas pipeline, and the continuous infrasonic wave data on the leaking gas pipeline wall as sample data;

[0017] Denoise the sample data;

[0018] Perform empirical mode decomposition on the denoised sample data;

[0019] Calculate the entropy value through multi-scale permutation of the sample data after empirical mode decomposition, and extract signal features;

[0020] Train a leakage detection model according to the extracted signal features.

[0021] Preferably, before extracting the signal features, the method further includes:

[0022] Perform dimensionality reduction processing according to the multi-scale permutation entropy value.

[0023] Preferably, the denoising process for the data to be detected includes:

[0024] Decompose the data to be detected into different scales through wavelet transform;

[0025] Determine an adaptive threshold using the noise standard deviation of the data to be detected;

[0026] Filter and denoise the decomposed data to be detected through the adaptive threshold;

[0027] Perform inverse wavelet transform on the filtered and denoised data to be detected.

[0028] Preferably, when the leakage detection results of multiple groups of gas pipelines are all pipeline leaks, the method further includes:

[0029] Judge the position of the leakage point according to the waveforms of the continuous infrasonic wave data in the gas pipeline and the continuous infrasonic wave data on the gas pipeline wall.

[0030] Preferably, the method further includes:

[0031] Apply a leakage signal to the adjacent port of the gas pipeline and the leakage point location.

[0032] Collect the continuous infrasonic data inside the gas pipeline and the continuous infrasonic data on the gas pipeline wall as verification data.

[0033] Determine the number of spike points in the verification data according to the waveform of the verification data.

[0034] Determine the number of spike points in the data to be detected according to the waveform of the data to be detected.

[0035] If the number of spike points in the verification data is greater than the number of spike points in the data to be detected, it is determined that a pipeline leak has occurred.

[0036] Preferably, the method further includes:

[0037] Calculate the actual distance between the leakage point location and the adjacent port of the gas pipeline according to the time interval between the appearances of the spike points in the waveform of the verification data.

[0038] According to the second aspect of the embodiments of the present application, a city gas pipeline leakage detection system based on continuous infrasound is provided, including:

[0039] A cloud platform and edge computers set at each gas pipeline.

[0040] The cloud platform is wirelessly communicatively connected to each edge computer.

[0041] The edge computer is configured to execute a city gas pipeline leakage detection method based on continuous infrasound as described in any one of the above.

[0042] The technical solution provided by the present application may include the following beneficial effects:

[0043] The city gas pipeline leakage detection method based on continuous infrasound in the present application includes: receiving a leakage detection instruction, collecting a preset number of groups of continuous infrasonic data inside the gas pipeline and continuous infrasonic data on the gas pipeline wall at a preset time interval as data to be detected; performing denoising processing on the data to be detected; inputting the denoised data to be detected into a pre-trained leakage detection model to obtain multiple groups of gas pipeline leakage detection results; when the multiple groups of gas pipeline leakage detection results are consistent, reporting the gas pipeline leakage detection results to a superior platform.

[0044] Since the characteristics of the continuous leakage signal are different from those of the non-leakage signal, in this application, the continuous infrasonic data in the gas pipeline and the continuous infrasonic data on the gas pipeline wall are used to detect whether the gas pipeline leaks. By continuously collecting infrasonic signals, the system can monitor the pipeline condition in real time, avoiding the limitation of the traditional method that the mutation signal cannot be detected in time after being missed. No matter when the pipeline leaks, the system can obtain the signal at any time and make a judgment to ensure the real-time discovery and response of the leakage.

[0045] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with this application, and are used together with the specification to explain the principles of this application.

[0047] Figure 1 is a schematic flowchart of a method for detecting leakage of urban gas pipelines based on continuous infrasound provided by an embodiment of this application;

[0048] Figure 2 is a schematic structural diagram of a system for detecting leakage of urban gas pipelines based on continuous infrasound provided by an embodiment of this application.

[0049] Reference numerals: Cloud platform - 21; Edge computer - 22. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] Here, the exemplary embodiments will be described in detail, and the examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numerals in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. On the contrary, they are only examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.

[0051] Figure 1 is a schematic flowchart of a method for detecting leakage of urban gas pipelines based on continuous infrasound provided by an embodiment of this application. Referring to Figure 1 , a method for detecting leakage of urban gas pipelines based on continuous infrasound includes:

[0052] S11: Receive a leakage detection instruction, and collect a preset number of groups of continuous infrasonic data in the gas pipeline and continuous infrasonic data on the gas pipeline wall at a preset time interval as data to be detected;

[0053] In specific practice, the preset time interval can be but is not limited to 1 minute, and the preset number of groups can be but is not limited to 5 groups.

[0054] S12: Denoise the data to be detected;

[0055] S13: Input the denoised data to be detected into a pre-trained leakage detection model to obtain multiple sets of gas pipeline leakage detection results;

[0056] S14: When the multiple sets of gas pipeline leakage detection results are consistent, report the gas pipeline leakage detection results to the superior platform.

[0057] It should be noted that the leakage detection instruction is triggered automatically by the system based on a period or triggered actively by the user.

[0058] In this technical solution, the triggering methods of the leakage detection instruction include two methods: automatic triggering by the system based on a period and active triggering by the user. The specific explanations are as follows:

[0059] 1. Automatic triggering by the system based on a period

[0060] The system automatically triggers the leakage detection instruction within a preset time interval. This means that the system will regularly collect data and perform leakage detection according to a predetermined time period, without relying on external intervention or event triggering. For example, the system can be set to automatically trigger the leakage detection instruction every certain time (such as every hour or every 24 hours), perform the acquisition of infrasonic wave data inside and on the wall of the pipeline, denoise the data, and perform leakage detection analysis. Triggering the leakage detection instruction regularly can ensure that the pipeline can be monitored in a timely manner at any time, ensuring that potential leaks are detected as early as possible.

[0061] Automatic triggering by the system based on a period can also reduce manual intervention, reduce the possibility of human oversight, and ensure that the safety of the pipeline is continuously monitored. During long-term operation, the system can continuously and stably monitor, which helps to detect possible abnormalities or progressive leaks in the pipeline in a timely manner.

[0062] 2. Active triggering by the user

[0063] The user can actively trigger the leakage detection instruction according to needs, usually when the system alarms or suspects that there is a problem with the pipeline, the user can manually start the leakage detection program. For example, when the user finds abnormal noise, pressure change or other signs of suspected leakage in the pipeline, the user can manually trigger the leakage detection by operating the system.

[0064] Advantages of the combination of the two:

[0065] The combination of system - automatic triggering and user - initiative triggering can maximize the efficiency and security of the system. The system's periodic automatic triggering can ensure regular monitoring of pipelines, while users can actively trigger detection instructions under specific circumstances to quickly respond to emergencies or special situations. The two complement each other, ensuring continuous monitoring of pipeline leaks and emergency response.

[0066] Moreover, through the combination of system - automatic triggering and user - initiative triggering, there is no need to monitor the pipeline in real - time, which can reduce the consumption of device battery power and extend the working hours of the device.

[0067] It should be noted that the method also includes:

[0068] When the leakage detection results of multiple groups of gas pipelines are inconsistent, report that there is an abnormality in the gas pipeline leakage detection to the superior platform.

[0069] In this technical solution, by collecting multiple groups of infrasonic signals, the system can verify the pipeline status multiple times. The data of multiple groups of signals can verify each other, reducing misjudgments caused by errors or noise interference in single - data, and improving the accuracy of the system. For example, collecting signals from different positions or angles within the same time period can comprehensively reflect the true situation of the pipeline.

[0070] Since the signal of gas leakage may be relatively weak or affected by external interference, by comparing multiple groups of signals, the detection sensitivity of the system to minor leaks can be improved. If a single signal is affected by noise or emergencies, other signal groups can be used as a supplement to help identify potential leakage situations.

[0071] Generally speaking, if the detection results of all signal groups are consistent, it can be more confidently determined that there is a leak in the pipeline.

[0072] However, in some cases, the detection results from different signal groups may be inconsistent, that is, some signal groups judge a leak, while other signal groups do not detect a leak. This inconsistent situation may stem from various reasons, such as:

[0073] External environmental noise interference;

[0074] The local state of the pipeline is different (such as local damage or external force influence);

[0075] Equipment failure or sensor problems;

[0076] Errors or insufficient adaptability in model judgment, etc.

[0077] When the system detects inconsistent multiple groups of detection results, further processing must be carried out to prevent false alarms or missed alarms. The system reports abnormal situations to notify the superior platform and avoid the consequences caused by incorrect judgments. Specifically, the processing steps for abnormal reporting include:

[0078] Reporting abnormality: The system sends an alarm or report to the superior platform, indicating that there are inconsistencies in the current leakage detection results and further analysis and intervention are required.

[0079] Manual intervention or further analysis: After receiving the abnormal report, the superior platform may require manual further investigation of the problem or on-site inspection of the pipeline to ensure whether there is a real risk of leakage.

[0080] System optimization and adjustment: In some cases, the reason for the inconsistent system detection may be due to deficiencies in the algorithm or model. Through the abnormal report, the system can be further optimized and adjusted to improve the accuracy and stability of subsequent detections.

[0081] In this technical solution, through this abnormal handling mechanism, false alarms or missed alarms caused by a single data source or local errors are avoided. Even if there are local interference factors or occasional technical problems, the system can be verified through this mechanism to reduce incorrect responses caused by abnormal situations.

[0082] It should be noted that the method also includes:

[0083] Obtaining continuous infrasonic data in the normal gas pipeline, continuous infrasonic data on the normal gas pipeline wall, continuous infrasonic data in the leaking gas pipeline, and continuous infrasonic data on the leaking gas pipeline wall as sample data;

[0084] Performing denoising processing on the sample data;

[0085] Performing empirical mode decomposition on the denoised sample data;

[0086] Calculating the entropy value of the sample data after empirical mode decomposition through multi-scale permutation to extract signal features;

[0087] Training a leakage detection model based on the extracted signal features.

[0088] Continuous infrasonic data in the normal gas pipeline: It refers to the infrasonic signal data generated by the gas flow in the pipeline under normal working conditions.

[0089] Continuous infrasonic data on the normal gas pipeline wall: It refers to the infrasonic signal data reflected by the pipeline wall under normal conditions.

[0090] Continuous infrasound data in the leaking gas pipeline: When a gas leak occurs in the pipeline, the infrasound signal near the leak point will change differently from the normal state. Collect the in-pipeline signal data under these leaking conditions.

[0091] Continuous infrasound data on the wall of the leaking gas pipeline: Similarly, the infrasound signal on the pipe wall will also change during leakage. Collect these signal data.

[0092] Since the collected infrasound data may be affected by noise interference (such as external environmental noise, equipment errors, etc.), denoising is a very important step. By removing noise, the quality of the signal and the accuracy of subsequent analysis can be improved. Common denoising methods include techniques such as wavelet transform.

[0093] Empirical mode decomposition is a signal analysis method used to decompose a complex signal into multiple intrinsic mode functions. Through empirical mode decomposition, the original infrasound signal can be decomposed into components in different frequency ranges, and each component represents the dynamic characteristics of the signal at different scales.

[0094] Empirical mode decomposition can decompose the complexity of the signal into simpler and easier-to-analyze components, laying a foundation for in-depth analysis and feature extraction of the signal. Through empirical mode decomposition, the different characteristics of the leakage signal and the normal signal can be presented more clearly.

[0095] Multi-scale permutation is to perform permutation calculations on the signal at multiple scales, considering the signal behavior at different time scales and frequency scales. This helps to capture the dynamic change characteristics of the leakage signal at different time frequencies.

[0096] Entropy value calculation: Entropy is an index to measure the complexity and uncertainty of a signal. By calculating the entropy values of the signal at different scales, the system can extract the significant differences between the leakage signal and the normal signal. The leakage signal often shows higher complexity and irregularity, so the change in entropy value can reflect whether there is a leak in the pipeline.

[0097] In this technical solution, by calculating the entropy value through multi-scale permutation, valuable features in the signal can be comprehensively captured. These features help the leakage detection model better distinguish between the leakage signal and the normal signal, improving the detection accuracy.

[0098] After extracting the features of the signal through processing means such as denoising, empirical mode decomposition, and entropy value calculation, these feature data are used as inputs to train the leakage detection model. The leakage detection model is usually a machine learning algorithm (such as support vector machine, neural network, etc.) model. By learning the relationship between the signal features and the leakage state in the sample data, it can finally achieve the automatic detection of pipeline leakage.

[0099] It should be noted that before extracting the signal features, the method also includes:

[0100] Perform dimensionality reduction processing according to the multi-scale permutation entropy value.

[0101] After calculating the multi-scale permutation entropy value, the signal features often show a high-dimensional state. Without dimensionality reduction, subsequent model training may need to process a large number of data features, which will lead to a significant increase in computational cost, especially when the sample data volume is large. Dimensionality reduction can effectively reduce the dimension of the feature space, reduce the complexity of model training and calculation, and improve the operating efficiency of the system.

[0102] It should be noted that the mutant infrasonic wave signal is easily interfered by environmental noise, and these noises may cause false alarms or missed alarms.

[0103] Based on this, in this embodiment, noise reduction processing is also performed on the data to be detected, including:

[0104] Decompose the data to be detected into different scales through wavelet transform;

[0105] Determine the adaptive threshold using the noise standard deviation of the data to be detected;

[0106] Filter and denoise the decomposed data to be detected through the adaptive threshold;

[0107] Perform inverse wavelet transform on the filtered and denoised data to be detected.

[0108] Wavelet denoising is a signal denoising method based on wavelet transform. Different from the traditional Fourier transform, wavelet transform can provide local information of the signal in time and frequency, so it is especially suitable for processing signals with instantaneous mutations or non-stationary characteristics.

[0109] First, decompose the original signal into different scales (levels) through wavelet transform. Wavelet transform decomposes the signal into two parts: low frequency (approximation coefficient) and high frequency (detail coefficient).

[0110] The selection of the threshold is crucial for the denoising effect. If the threshold is too small, enough noise may not be removed; if the threshold is too large, useful signals may be lost.

[0111] In this technical solution, the adaptive threshold is dynamically calculated according to the local characteristics of each wavelet coefficient, and the decomposed data to be detected is filtered and denoised through the adaptive threshold.

[0112] It should be noted that the method of performing noise reduction processing on the data to be detected in this embodiment is also applicable to the process of performing noise reduction processing on sample data during model training.

[0113] It should be noted that when the detection results of multiple groups of gas pipeline leaks are all pipeline leaks, the method further includes:

[0114] Judge the location of the leakage point according to the waveforms of the continuous infrasonic wave data in the gas pipeline and the continuous infrasonic wave data on the gas pipeline wall.

[0115] Generally, sensors are arranged inside and on the pipe wall at both ends of the gas pipeline to collect the continuous infrasonic wave data in the gas pipeline and the continuous infrasonic wave data on the gas pipeline wall as the data to be detected.

[0116] The waveform of the leakage point is generally a spike point. When leakage occurs, the signal in the pipe first reaches the sensor closest to the leakage point, and then fluctuates and propagates to other positions. In this embodiment, the location of the leakage point can be roughly judged according to the sensor closest to the leakage point.

[0117] Furthermore, the method further includes:

[0118] Apply a leakage signal to the adjacent port of the gas pipeline and the leakage point location;

[0119] Collect the continuous infrasonic wave data in the gas pipeline and the continuous infrasonic wave data on the gas pipeline wall as verification data;

[0120] According to the waveform of the verification data, determine the number of spike points in the verification data;

[0121] According to the waveform of the data to be detected, determine the number of spike points in the data to be detected;

[0122] If the number of spike points in the verification data is greater than the number of spike points in the data to be detected, it is determined that pipeline leakage has occurred.

[0123] In the case of existing leakage, artificially applying a leakage signal will interfere with the original leakage, thereby generating acoustic fluctuations. This method is the shock wave method. In the above steps, the approximate location of the leakage point has been judged according to the waveforms of the continuous infrasonic wave data in the gas pipeline and the continuous infrasonic wave data on the gas pipeline wall. At this time, a leakage signal is applied to the adjacent port of the gas pipeline and the leakage point location.

[0124] To avoid the possibility of multiple leakage points in the same pipeline, in this embodiment, first count the number of spike points before applying the leakage signal, that is, the number of spike points in the data to be detected. Then count the number of spike points after applying the leakage signal, and then judge whether the number of spike points in the verification data is greater than the number of spike points in the data to be detected.

[0125] If the number of spike points in the verification data should be one more than the number of spike points in the data to be detected, it is determined that pipeline leakage has occurred.

[0126] Based on this, the method further includes:

[0127] According to the time interval between the occurrences of the peak points in the waveform of the verification data, calculate the actual distance between the leakage point and the adjacent port of the gas pipeline.

[0128] Since the wave has a certain propagation speed, in this embodiment, it is also possible to calculate the actual distance between the leakage point and the adjacent port of the gas pipeline according to the time interval between the occurrences of the peak points in the waveform of the verification data.

[0129] As mentioned above, the peak point is a mutation point in the waveform of the infrasonic wave signal, usually appearing in the instantaneous change caused by the pressure fluctuation during pipeline leakage. The infrasonic wave signal generated by the leakage point will cause fluctuations inside and outside the pipeline, and these fluctuations are manifested as peak points in the waveform, usually indicating the position of the leakage point or the occurrence of the leakage process.

[0130] Since the speed of signal propagation along the pipeline is known (usually the propagation speed of infrasonic waves), the specific position of the leakage point can be calculated according to the time interval of the peak points using the wave speed formula.

[0131] In this technical solution, by calculating the time interval between the occurrences of the peak points in the verification data, the actual distance of the leakage point relative to the adjacent port of the gas pipeline can be deduced. By combining the propagation speed of the leakage signal, the time interval, and the waveform characteristics of the peak points, the system can accurately determine the position of the leakage point. This method not only improves the accuracy of leakage detection but also provides very valuable information for pipeline maintenance and safety monitoring, helping to quickly locate the leakage source, thereby reducing losses and enhancing the efficiency of pipeline management.

[0132] In summary, this technical solution detects whether the gas pipeline leaks through the continuous infrasonic wave data inside the gas pipe and the continuous infrasonic wave data on the gas pipe wall. By continuously collecting the infrasonic wave signal, the system can monitor the pipeline condition in real time, avoiding the limitation of the traditional method that the mutation signal cannot be detected in time after being missed. No matter when the pipeline leaks, the system can obtain the signal at any time and make a judgment to ensure the real-time discovery and response of the leakage.

[0133] This technical solution performs leakage detection through a pre-trained leakage detection model, with the characteristics of high accuracy, low false alarm rate, low missed alarm rate, and measurable at any time.

[0134] Embodiment 2

[0135] A city gas pipeline leakage detection system based on continuous infrasonic waves, referring to Figure 2 , includes:

[0136] A cloud platform 21, and edge computers 22 arranged at each gas pipeline;

[0137] The cloud platform 21 is wirelessly communicatively connected to each edge computer 22;

[0138] The edge computing device 22 is used to execute a method for detecting leakage of urban gas pipelines based on continuous infrasound as described in the above embodiments.

[0139] It can be understood that the same or similar parts in the above embodiments can be referred to each other, and the content not detailed in some embodiments can be referred to the same or similar content in other embodiments.

[0140] It should be noted that in the description of the present application, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present application, unless otherwise specified, the meaning of "a plurality of" refers to at least two.

[0141] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more executable instructions for implementing a specific logical function or process. The scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in the reverse order according to the functions involved, rather than in the order shown or discussed. This should be understood by those skilled in the technical field of the embodiments of the present application.

[0142] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0143] Those of ordinary skill in the technical field of the present application can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0144] In addition, each functional unit in various embodiments of the present application may be integrated into a processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0145] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, or the like.

[0146] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples.

[0147] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A city gas pipeline leakage detection method based on continuous infrasound, characterized in that: include: Receive a leak detection instruction, and collect a preset number of groups of continuous infrasound wave data in the gas pipe and continuous infrasound wave data on the gas pipe wall as data to be detected based on a preset time interval; Performing denoising processing on the data to be detected; The denoised data to be detected is input into a pre-trained leakage detection model to obtain multiple groups of gas pipeline leakage detection results; When multiple sets of gas pipeline leakage detection results are consistent, report the gas pipeline leakage detection results to the superior platform.

2. The method according to claim 1, characterized in that The leakage detection instruction is automatically triggered by the system based on a period, or actively triggered by the user.

3. The method according to claim 1, characterized in that The method further comprises: When the results of multiple sets of gas pipeline leakage detection are inconsistent, report the abnormality of gas pipeline leakage detection to the superior platform.

4. The method according to claim 1, characterized in that: The method further comprises: Acquire continuous infrasound data in a normal gas pipe, continuous infrasound data on a normal gas pipe wall, continuous infrasound data in a leaking gas pipe, and continuous infrasound data on a leaking gas pipe wall as sample data; Performing denoising processing on the sample data; Perform empirical mode decomposition on the denoised sample data; The sample data after empirical mode decomposition is arranged at multiple scales to calculate the entropy value and extract signal features; The leakage detection model is trained based on the extracted signal features.

5. The method according to claim 4, characterized in that Before extracting the signal features, the method further includes: Dimensionality reduction is performed based on the multi-scale permutation entropy value.

6. The method according to claim 1, characterized in that The denoising process is performed on the data to be detected, including: Decompose the data to be detected into different scales through wavelet transform; The adaptive threshold is determined using the noise standard deviation of the data to be detected; The decomposed data to be detected is filtered and denoised through an adaptive threshold; Perform inverse wavelet transform on the data to be detected after filtering and denoising.

7. The method according to claim 1, characterized in that When the multiple groups of gas pipeline leakage detection results are all pipeline leakage, the method further includes: The location of the leakage point is determined based on the waveform of the continuous infrasonic wave data in the gas pipe and the continuous infrasonic wave data on the gas pipe wall.

8. The method according to claim 7, characterized in that The method further comprises: Apply a leakage signal to the port adjacent to the gas pipeline and the leakage point; Collect continuous infrasound data in the gas pipe and continuous infrasound data on the gas pipe wall as verification data; Determining the number of peak points in the verification data according to the waveform of the verification data; Determining the number of peak points in the data to be detected according to the waveform of the data to be detected; If the number of peak points in the verification data is greater than the number of peak points in the data to be detected, it is determined that a pipeline leak occurs.

9. The method according to claim 8, characterized in that The method further comprises: According to the time interval of the peak points in the waveform of the verification data, the actual distance between the leakage point and the adjacent port of the gas pipeline is calculated.

10. A city gas pipeline leak detection system based on continuous infrasound, characterized in that: include: Cloud platform and edge computing devices installed at each gas pipeline; The cloud platform is wirelessly connected to each edge computing device; The edge computing device is used to execute the urban gas pipeline leakage detection method based on continuous infrasound waves as described in any one of claims 1 to 9.

Images