Gas pipeline detection system based on acoustic analysis
Through the gas pipeline detection system based on acoustic analysis, real-time monitoring and analysis of the impact of road vibration on gas PE pipelines, the problem of inaccurate leakage risk prediction in the existing technology is solved, and higher monitoring accuracy and timeliness are achieved, avoiding the A leak accident.
Patent Information
- Application Number
- CN202411210425.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-30
AI Technical Summary
The prior art fails to effectively consider the impact of vibration of vehicles passing through road surfaces on gas PE pipelines, resulting in inaccurate prediction of leakage risks.
Design a gas pipeline detection system based on acoustic analysis, and use data acquisition module, vibration data analysis module, acoustic signal data analysis module, leakage risk prediction module and leakage risk warning module to monitor and analyze the impact of road vibration on gas PE pipelines in real time, and predict the Risk of leakage.
It improves the accuracy and timeliness of monitoring the risk of gas pipeline leakage, and avoids leakage accidents.
Smart Images

Figure CN118705558B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of gas pipeline detection, and in particular to a gas pipeline detection system based on acoustic analysis. Background Art
[0002] Acoustic analysis plays a vital role in gas pipeline detection. Acoustic detection technology uses the propagation characteristics of sound in the medium to identify the existence, status and potential problems of the pipeline by receiving and analyzing the reflection, refraction, transmission and other signals of sound waves. In gas pipeline detection, when gas leaks, ultrasonic waves with frequencies higher than audible frequencies are generated. Equipment such as acoustic imagers can detect these ultrasonic waves to determine the location and scope of the leak. This non-contact detection method not only improves the detection efficiency, but also ensures the safety of the inspectors. At the same time, with the acceleration of urbanization, the passage of various types of vehicles will cause vibrations on the road surface. These vibrations will not only damage the road surface, but may also be transmitted to underground pipelines through the soil, causing potential damage to them. Especially when there are problems such as aging and corrosion in the pipeline, vibrations may cause or aggravate the risk of leakage. It is of great significance to monitor and analyze the vibration of the road surface caused by the passage of vehicles and predict its impact on gas pipelines and leakage risks.
[0003] However, the prior art does not take into account that the road vibration caused by vehicles passing through the road will be transmitted to the gas PE pipeline through the soil, thereby causing the gas PE pipeline to vibrate, thereby increasing the risk of gas leakage in the gas PE pipeline; therefore, the data generated by road vibration is ignored in the data analysis, resulting in the inability of the prior art to accurately predict the risk of gas PE pipeline leakage caused by road vibration when performing gas pipeline detection.
[0004] In order to solve these problems, the present application designs a gas pipeline detection system based on acoustic analysis. Summary of the invention
[0005] In order to overcome the defects and shortcomings of the prior art, the present invention provides a gas pipeline detection system based on acoustic analysis, which analyzes the road vibration data caused by the passing of vehicles and the acoustic wave signal of the gas PE pipeline, and then predicts the risk of pipeline gas leakage caused by road vibration. It realizes real-time monitoring of the gas PE pipeline, improves the accuracy and timeliness of monitoring, and avoids the occurrence of leakage accidents.
[0006] In order to achieve the above object, the present invention adopts the following technical solutions:
[0007] An embodiment of the present invention provides a gas pipeline detection system based on acoustic analysis, including a data acquisition module, a vibration data analysis module, an acoustic signal data analysis module, a gas PE pipeline leakage risk prediction module, a leakage risk warning module and a control module, wherein the data acquisition module is used to collect vibration detection data and acoustic signal detection data within multiple historical detection cycles, the vibration data analysis module is used to analyze the vibration of the gas PE pipeline according to the vibration detection data, the acoustic signal data analysis module is used to analyze the acoustic signal of the gas PE pipeline according to the acoustic signal detection data, the gas PE pipeline leakage risk prediction module is used to predict the gas leakage risk of the gas PE pipeline in the next detection cycle according to the gas PE pipeline vibration analysis results and the gas PE pipeline acoustic signal analysis results, the leakage risk warning module is used to issue a leakage risk warning according to the gas leakage risk prediction result of the gas PE pipeline in the next detection cycle, and the control module is used to control the operation of the data acquisition module, the vibration data analysis module, the acoustic signal data analysis module, the gas PE pipeline leakage risk prediction module, and the leakage risk warning module.
[0008] In one implementation of the present invention, a vibration data analysis strategy is executed in the vibration data analysis module, and the vibration data analysis strategy includes the following specific steps:
[0009] S11, extracting vibration detection data collected by the data acquisition module;
[0010] S12, substituting the vibration detection data into a vibration risk coefficient calculation formula to calculate the vibration risk coefficient, the vibration risk coefficient calculation formula is:
[0011] ;
[0012] In the formula It represents the vibration risk coefficient of the ith equidistant detection point along the gas PE pipeline in a certain historical detection period, , They represent the average amplitude and average frequency of the vibration detection data of the ith equidistant detection point along the gas PE pipeline collected within the jth equal interval time within a certain historical detection period, , They represent the elastic modulus and yield strength of the gas PE pipeline respectively, n is the number of equal intervals in a certain historical detection cycle, MAX() and MIN() respectively represent the average amplitude and average frequency of the vibration detection data of all equidistant detection points along the gas PE pipeline collected in all equal intervals in a certain historical detection cycle. The maximum and minimum values of the calculation results obtained by calculation;
[0013] In one implementation of the present invention, the vibration data analysis strategy further includes the following specific steps:
[0014] S13, extracting the calculated vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in all historical detection periods, constructing the vibration time series of the i-th equidistant detection point in chronological order according to the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in all historical detection periods, and training the i-th risk prediction model for predicting the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in the next detection period based on the vibration time series of the i-th equidistant detection point;
[0015] S14, preset the sliding step size to 1 and the sliding window length to W; use the sliding window method to convert the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in all historical detection cycles in the vibration time series of the i-th equidistant detection point into multiple training samples, wherein each training sample is composed of a vibration risk coefficient sequence in the sliding window, and the training sample is used as the input of the i-th risk prediction model, and the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline after the preset sliding step size is 1 is used as the output, and the prediction accuracy is used as the training target to train the i-th risk prediction model; generate an i-th risk prediction model for predicting the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in the next detection cycle based on the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in all historical detection cycles; wherein the i-th risk prediction model is a recurrent neural network model;
[0016] In one implementation of the present invention, the acoustic wave signal data analysis module runs an acoustic wave signal data analysis strategy, and the acoustic wave signal data analysis strategy includes the following specific steps:
[0017] S21, acquiring the acoustic signal detection data collected by the data acquisition module;
[0018] S22, substituting the acoustic signal detection data into the acoustic signal risk coefficient calculation formula to calculate the acoustic signal risk coefficient, the acoustic signal risk coefficient calculation formula is:
[0019] ;
[0020] In the formula It represents the acoustic signal risk coefficient of the ith equidistant detection point along the gas PE pipeline in a certain historical detection period, It represents the average sound wave frequency in the sound wave signal detection data of the i-th equidistant detection point along the gas PE pipeline collected within the j-th equal interval time within a certain historical detection period;
[0021] S23. The calculated acoustic wave signal risk coefficient of the ith equidistant detection point along the gas PE pipeline in each detection cycle is used as the gas leakage risk coefficient of the ith equidistant detection point along the gas PE pipeline in each detection cycle.
[0022] In one implementation of the present invention, a leakage risk analysis strategy is run in the gas PE pipeline leakage risk prediction module, and the leakage risk analysis strategy includes the following specific steps:
[0023] S33, storing the calculated vibration risk coefficient and gas leakage risk coefficient of the ith equidistant detection point along the gas PE pipeline in all historical detection cycles into a historical detection data set, wherein the historical detection data set is used to train the gas leakage risk prediction model of the ith equidistant detection point, and the historical detection data set is divided into a 70% historical detection data training set and a 30% historical detection data test set;
[0024] S34, constructing a regression network model, taking the vibration risk coefficient in the historical detection data training set as the input of the regression network model, taking the gas leakage risk coefficient in the historical detection data training set as the output of the regression network model, and training the regression network model to obtain an initial regression network model;
[0025] S35. Test the initial regression network model using a historical detection data test set, and output an initial regression network model that meets the preset model accuracy as the gas leakage risk prediction model for the i-th equidistant detection point.
[0026] In one implementation of the present invention, the leakage risk warning module runs a leakage risk warning execution strategy, and the leakage risk warning execution strategy includes the following specific steps:
[0027] S41, obtaining the gas leakage risk coefficient of the i-th equidistant detection point in the next detection cycle predicted by the gas PE pipeline leakage risk prediction module;
[0028] S42. Preset a gas leakage risk threshold. When the predicted gas leakage risk coefficient of the i-th equidistant detection point in the next detection cycle is greater than the gas leakage risk threshold, execute the first warning operation, which is to issue a gas leakage risk warning for the i-th equidistant detection point along the gas PE pipeline to the maintenance personnel; when the predicted gas leakage risk coefficient of the i-th equidistant detection point in the next detection cycle is less than or equal to the gas leakage risk threshold, the first warning operation is not executed.
[0029] In one implementation of the present invention, the leakage risk warning execution strategy also includes the following contents:
[0030] S43, obtaining the gas leakage risk coefficients of all equally-distanced detection points in the next detection period predicted by the gas PE pipeline leakage risk prediction module, adding and averaging the gas leakage risk coefficients of all equally-distanced detection points to obtain the gas PE pipeline leakage risk coefficient for the next detection period;
[0031] S44. Preset a gas PE pipeline leakage risk threshold. When the gas PE pipeline leakage risk coefficient in the next detection cycle is greater than the gas PE pipeline leakage risk threshold, execute the second warning operation, which is to issue a gas PE pipeline leakage risk warning to maintenance personnel; when the gas PE pipeline leakage risk coefficient in the next detection cycle is less than or equal to the gas PE pipeline leakage risk threshold, the second warning operation is not executed.
[0032] In one implementation of the present invention, the data acquisition module includes a vibration detection data acquisition unit and an acoustic wave signal detection data acquisition unit. The vibration detection data acquisition unit is used to collect vibration detection data of multiple equidistant detection points along the gas PE pipeline at multiple equal intervals within multiple historical detection cycles through a road vibration sensor. The acoustic wave signal detection data acquisition unit is used to collect acoustic wave signal detection data of multiple equidistant detection points along the gas PE pipeline at multiple equal intervals within multiple historical detection cycles through an acoustic wave detector.
[0033] Compared with the prior art, the present invention has the following advantages and beneficial effects:
[0034] The present invention includes a data acquisition module, a vibration data analysis module, an acoustic signal data analysis module, a gas PE pipeline leakage risk prediction module, a leakage risk warning module and a control module, wherein the vibration data analysis module is used to analyze the gas PE pipeline vibration according to the vibration detection data, the acoustic signal data analysis module is used to analyze the gas PE pipeline acoustic signal according to the acoustic signal detection data, the gas PE pipeline leakage risk prediction module is used to predict the gas leakage risk of the gas PE pipeline in the next detection cycle according to the gas PE pipeline vibration analysis result and the gas PE pipeline acoustic signal analysis result, and the leakage risk warning module is used to give a leakage risk warning according to the prediction result. Thus, real-time monitoring of the gas PE pipeline is realized, the accuracy and timeliness of monitoring are improved, and the occurrence of leakage accidents is avoided. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:
[0036] Figure 1 It is a structural schematic diagram of a gas pipeline detection system based on acoustic analysis of the present invention;
[0037] Figure 2 A basic flow chart of a recurrent neural network model in a gas pipeline detection system based on acoustic analysis of the present invention;
[0038] Figure 3 It is a structural schematic diagram of a data acquisition module in a gas pipeline detection system based on acoustic analysis of the present invention. DETAILED DESCRIPTION
[0039] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.
[0040] Example 1
[0041] like Figure 1 As shown, this embodiment provides a gas pipeline detection system based on acoustic analysis, which specifically includes a data acquisition module, a vibration data analysis module, an acoustic signal data analysis module, a gas PE pipeline leakage risk prediction module, a leakage risk warning module and a control module, wherein the data acquisition module is used to collect vibration detection data and acoustic signal detection data within multiple historical detection cycles, the vibration data analysis module is used to analyze the vibration of the gas PE pipeline according to the vibration detection data, the acoustic signal data analysis module is used to analyze the acoustic signal of the gas PE pipeline according to the acoustic signal detection data, the gas PE pipeline leakage risk prediction module is used to predict the gas leakage risk of the gas PE pipeline in the next detection cycle according to the gas PE pipeline vibration analysis results and the gas PE pipeline acoustic signal analysis results, the leakage risk warning module is used to issue a leakage risk warning according to the gas leakage risk prediction result of the gas PE pipeline in the next detection cycle, and the control module is used to control the operation of the data acquisition module, the vibration data analysis module, the acoustic signal data analysis module, the gas PE pipeline leakage risk prediction module, and the leakage risk warning module.
[0042] In this embodiment, a vibration data analysis strategy is executed in the vibration data analysis module, and the vibration data analysis strategy includes the following specific steps:
[0043] S11, extracting vibration detection data collected by the data acquisition module;
[0044] S12. Substituting the vibration detection data into the vibration risk coefficient calculation formula to calculate the vibration risk coefficient. The vibration risk coefficient calculation formula is:
[0045] ;
[0046] In the formula It represents the vibration risk coefficient of the ith equidistant detection point along the gas PE pipeline in a certain historical detection period, , They represent the average amplitude and average frequency of the vibration detection data of the ith equidistant detection point along the gas PE pipeline collected within the jth equal interval time within a certain historical detection period, , They represent the elastic modulus and yield strength of the gas PE pipeline respectively, n is the number of equal intervals in a certain historical detection cycle, MAX() and MIN() respectively represent the average amplitude and average frequency of the vibration detection data of all equidistant detection points along the gas PE pipeline collected in all equal intervals in a certain historical detection cycle. The maximum and minimum values of the calculation results obtained by calculation;
[0047] In this embodiment, the vibration data analysis strategy also includes the following specific steps:
[0048] S13, extracting the calculated vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in all historical detection periods, constructing the vibration time series of the i-th equidistant detection point in chronological order according to the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in all historical detection periods, and training the i-th risk prediction model for predicting the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in the next detection period based on the vibration time series of the i-th equidistant detection point;
[0049] S14, preset the sliding step length to be 1 and the sliding window length to be W; use the sliding window method to convert the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in all historical detection periods in the vibration time series of the i-th equidistant detection point into multiple training samples, wherein each training sample is composed of a vibration risk coefficient sequence in the sliding window, and the training sample is used as the input of the i-th risk prediction model, and the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline with a preset sliding step length of 1 is used as the output, and the prediction accuracy is used as the training target to train the i-th risk prediction model; generate a vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in accordance with all historical detection periods; The vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline within a period is predicted by the i-th risk prediction model of the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in the next detection period; wherein the i-th risk prediction model is a recurrent neural network model; wherein the sliding window length W is set by technical personnel in this field according to the length of the vibration time series of the i-th equidistant detection point and actual needs; of course, in the specific implementation process, technical personnel in this field can also reset the sliding step size to predict the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in more detection periods in the future.
[0050] like Figure 2 As shown in the figure, by extracting the historical vibration risk coefficients of the i-th equidistant detection point along the gas PE pipeline, and constructing a vibration time series based on these historical data, a model for predicting the vibration risk coefficient in the next detection cycle is trained. The recurrent neural network (RNN) model is selected to capture the time dependency in the data and the correlation between the sequences. In the prediction of the vibration risk coefficient of the gas PE pipeline, the current risk coefficient is likely to be affected by the risk coefficients of multiple previous time points. The RNN saves this historical information through its internal state, thereby effectively modeling this time series characteristic. Moreover, compared with traditional feedforward neural networks, such as multi-layer perceptrons MLP, the recurrent neural network model can retain previous input information when processing sequences. This "memory" ability enables the RNN to learn long-term dependencies in the sequence. In the prediction of the vibration risk coefficient, this long-term dependency is crucial for predicting future risk changes. Since the recurrent neural network model can receive new input data in real time and update its internal state, it can realize real-time prediction of the vibration risk coefficient. This is of great significance for timely monitoring and early warning of potential failures of gas PE pipelines.
[0051] In this embodiment, the acoustic wave signal data analysis strategy is executed in the acoustic wave signal data analysis module, and the acoustic wave signal data analysis strategy includes the following specific steps:
[0052] S21, acquiring the acoustic signal detection data collected by the data acquisition module;
[0053] S22, substituting the acoustic signal detection data into the acoustic signal risk coefficient calculation formula to calculate the acoustic signal risk coefficient, the acoustic signal risk coefficient calculation formula is:
[0054] ;
[0055] In the formula It represents the acoustic signal risk coefficient of the ith equidistant detection point along the gas PE pipeline in a certain historical detection period, It represents the average sound wave frequency in the sound wave signal detection data of the i-th equidistant detection point along the gas PE pipeline collected within the j-th equal interval time within a certain historical detection period;
[0056] S23. The calculated acoustic wave signal risk coefficient of the ith equidistant detection point along the gas PE pipeline in each detection cycle is used as the gas leakage risk coefficient of the ith equidistant detection point along the gas PE pipeline in each detection cycle.
[0057] In this embodiment, a leakage risk analysis strategy is run in the gas PE pipeline leakage risk prediction module, and the leakage risk analysis strategy includes the following specific steps:
[0058] S33, storing the calculated vibration risk coefficient and gas leakage risk coefficient of the ith equidistant detection point along the gas PE pipeline in all historical detection cycles into a historical detection data set, the historical detection data set is used to train the gas leakage risk prediction model of the ith equidistant detection point, and the historical detection data set is divided into a 70% historical detection data training set and a 30% historical detection data test set;
[0059] S34, constructing a regression network model, taking the vibration risk coefficient in the historical detection data training set as the input of the regression network model, taking the gas leakage risk coefficient in the historical detection data training set as the output of the regression network model, and training the regression network model to obtain an initial regression network model;
[0060] S35, testing the initial regression network model through the historical detection data test set, and outputting the initial regression network model that meets the preset model accuracy as the gas leakage risk prediction model for the i-th equidistant detection point. The model accuracy is set by those skilled in the art according to the actual situation and specific needs.
[0061] Since the gas leakage risk prediction model is trained based on historical data of road vibration caused by the passage of vehicles, it can more accurately capture the impact of vibration risk caused by road vibration on leakage risk. This helps to reduce the interference of other irrelevant factors on the prediction results, thereby improving the accuracy of the prediction. In the specific implementation process, when the road vibration caused by vehicles is detected, technicians in this field can quickly predict the potential gas leakage risk based on the current vibration risk coefficient using the gas leakage risk model. This real-time response capability is essential for taking preventive measures in a timely manner and ensuring pipeline safety. In addition, technicians in this field can also more accurately determine which detection points are more susceptible to vibration and leakage through accurate prediction of the vibration risk caused by vehicles. It helps to optimize maintenance strategies, concentrate limited resources on high-risk areas, and improve the efficiency and effectiveness of maintenance. For example, in busy sections of roads, traffic flow can be adjusted, pipeline monitoring can be strengthened, or other measures can be taken to reduce the impact of vibration on pipelines based on the prediction results, thereby ensuring the safe operation of pipelines.
[0062] In this embodiment, the leakage risk warning module runs a leakage risk warning execution strategy, which includes the following specific steps:
[0063] S41, obtaining the gas leakage risk coefficient of the i-th equidistant detection point in the next detection cycle predicted by the gas PE pipeline leakage risk prediction module;
[0064] S42, preset a gas leakage risk threshold, when the predicted gas leakage risk coefficient of the ith equidistant detection point in the next detection cycle is greater than the gas leakage risk threshold, execute the first warning operation, the first warning operation is to issue a gas leakage risk warning of the ith equidistant detection point along the gas PE pipeline to the maintenance personnel; when the predicted gas leakage risk coefficient of the ith equidistant detection point in the next detection cycle is less than or equal to the gas leakage risk threshold, the first warning operation is not executed. Among them, the gas leakage risk threshold is set by those skilled in the art according to actual conditions.
[0065] In this embodiment, the leakage risk warning execution strategy also includes the following contents:
[0066] S43, obtaining the gas leakage risk coefficients of all equally-distanced detection points in the next detection period predicted by the gas PE pipeline leakage risk prediction module, adding up the gas leakage risk coefficients of all equally-distanced detection points and calculating the average value, so as to obtain the gas PE pipeline leakage risk coefficient for the next detection period;
[0067] S44. Preset a gas PE pipeline leakage risk threshold. When the gas PE pipeline leakage risk coefficient in the next detection cycle is greater than the gas PE pipeline leakage risk threshold, execute the second warning operation, and the second warning operation is to issue a gas PE pipeline leakage risk warning to the maintenance personnel; when the gas PE pipeline leakage risk coefficient in the next detection cycle is less than or equal to the gas PE pipeline leakage risk threshold, the second warning operation is not executed, wherein the gas PE pipeline leakage risk threshold is set by technical personnel in this field according to actual conditions.
[0068] In this embodiment, the data acquisition module includes a vibration detection data acquisition unit and an acoustic wave signal detection data acquisition unit. The vibration detection data acquisition unit is used to collect vibration detection data of multiple equidistant detection points along the gas PE pipeline at multiple equal intervals within multiple historical detection cycles through a road vibration sensor. The acoustic wave signal detection data acquisition unit is used to collect acoustic wave signal detection data of multiple equidistant detection points along the gas PE pipeline at multiple equal intervals within multiple historical detection cycles through an acoustic wave detector.
[0069] Example 2
[0070] An electronic device according to an embodiment of the present invention comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-mentioned data acquisition module, vibration data analysis module, acoustic signal data analysis module, gas PE pipeline leakage risk prediction module, leakage risk warning module and control module by calling the computer program stored in the memory. It should be noted that: all computer programs of the gas pipeline detection system based on acoustic analysis are implemented in C language, wherein the data acquisition module, vibration data analysis module, acoustic signal data analysis module, gas PE pipeline leakage risk prediction module, leakage risk warning module and control module are all controlled by a remote server.
[0071] Example 3
[0072] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;
[0073] When the computer program runs on a computer device, the computer device executes the above-mentioned data acquisition module, vibration data analysis module, acoustic signal data analysis module, gas PE pipeline leakage risk prediction module, leakage risk warning module and control module.
[0074] Each embodiment of the present invention is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0075] The system and medium provided in the embodiments of the present invention correspond one-to-one to the method, and therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.
[0076] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0077] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device are used to implement the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0079] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0080] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
[0081] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer readable instructions, data structures, program modules or other data. Computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0082] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0083] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims
1. Gas pipeline detection system based on acoustic analysis, characterized by: It includes a data acquisition module, a vibration data analysis module, an acoustic signal data analysis module, a gas PE pipeline leakage risk prediction module, a leakage risk warning module and a control module, wherein the data acquisition module is used to collect vibration detection data and acoustic signal detection data within multiple historical detection cycles, the vibration data analysis module is used to analyze the vibration of the gas PE pipeline according to the vibration detection data, the acoustic signal data analysis module is used to analyze the acoustic signal of the gas PE pipeline according to the acoustic signal detection data, the gas PE pipeline leakage risk prediction module is used to predict the gas leakage risk of the gas PE pipeline in the next detection cycle according to the gas PE pipeline vibration analysis results and the gas PE pipeline acoustic signal analysis results, the leakage risk warning module is used to issue a leakage risk warning according to the gas leakage risk prediction result of the gas PE pipeline in the next detection cycle, and the control module is used to control the operation of the data acquisition module, the vibration data analysis module, the acoustic signal data analysis module, the gas PE pipeline leakage risk prediction module and the leakage risk warning module; The vibration data analysis module runs a vibration data analysis strategy, which includes the following specific steps: S11, extracting vibration detection data collected by the data acquisition module; S12. Substituting the vibration detection data into a vibration risk coefficient calculation formula to calculate the vibration risk coefficient, the vibration risk coefficient calculation formula is: ; In the formula It represents the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in a certain historical detection period, 、 They represent the average amplitude and average frequency of the vibration detection data of the i-th equidistant detection point along the gas PE pipeline collected within the j-th equal interval time within a certain historical detection period, 、 They represent the elastic modulus and yield strength of the gas PE pipeline respectively, n is the number of equal intervals in a certain historical detection period, MAX() and MIN() respectively represent the average amplitude and average frequency of the vibration detection data of all equidistant detection points along the gas PE pipeline collected in all equal intervals in a certain historical detection period. The maximum and minimum values of the calculation results obtained by calculation; The vibration data analysis strategy also includes the following specific steps: S13. Extract the calculated vibration risk coefficients of the i-th equidistant detection points along the gas PE pipeline in all historical detection periods, construct a vibration time series of the i-th equidistant detection points according to the time sequence of the vibration risk coefficients of the i-th equidistant detection points along the gas PE pipeline in all historical detection periods, and train an i-th risk prediction model for predicting the vibration risk coefficients of the i-th equidistant detection points along the gas PE pipeline in the next detection period based on the vibration time series of the i-th equidistant detection points; S14. The preset sliding step size is 1 and the sliding window length is W; the sliding window method is used to convert the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in all historical detection periods within the vibration time series of the i-th equidistant detection point into multiple training samples, wherein each training sample is composed of a vibration risk coefficient sequence within the sliding window, and the training sample is used as the input of the i-th risk prediction model, and the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline after the preset sliding step size is 1 is used as the output, and the i-th risk prediction model is trained with the prediction accuracy as the training target; an i-th risk prediction model is generated for predicting the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in the next detection period based on the vibration risk coefficient of the i-th equidistant detection point along the gas PE pipeline in all historical detection periods; wherein the i-th risk prediction model is a recurrent neural network model.
2. The gas pipeline detection system based on acoustic analysis according to claim 1, characterized in that: The acoustic signal data analysis module runs an acoustic signal data analysis strategy, which includes the following specific steps: S21, obtaining the acoustic signal detection data collected by the data acquisition module; S22, substituting the acoustic signal detection data into an acoustic signal risk coefficient calculation formula to calculate the acoustic signal risk coefficient, wherein the acoustic signal risk coefficient calculation formula is: ; In the formula It represents the acoustic signal risk coefficient of the i-th equidistant detection point along the gas PE pipeline within a certain historical detection period. It represents the average acoustic frequency in the acoustic signal detection data of the i-th equidistant detection point along the gas PE pipeline collected during the j-th equally spaced time period in a certain historical detection period; S23. The calculated acoustic signal risk coefficient of the i-th equidistant detection point along the gas PE pipeline in each detection period is used as the gas leakage risk coefficient of the i-th equidistant detection point along the gas PE pipeline in each detection period.
3. The gas pipeline detection system based on acoustic analysis according to claim 2, characterized in that: The gas PE pipeline leakage risk prediction module runs a leakage risk analysis strategy, which includes the following specific steps: S33, storing the calculated vibration risk coefficient and gas leakage risk coefficient of the i-th equidistant detection point along the gas PE pipeline in all historical detection cycles into a historical detection data set, wherein the historical detection data set is used to train a gas leakage risk prediction model for the i-th equidistant detection point, and the historical detection data set is divided into a 70% historical detection data training set and a 30% historical detection data test set; S34, constructing a regression network model, using the vibration risk coefficient in the historical detection data training set as the input of the regression network model, using the gas leakage risk coefficient in the historical detection data training set as the output of the regression network model, and training the regression network model to obtain an initial regression network model; S35. Test the initial regression network model using a historical detection data test set, and output an initial regression network model that meets the preset model accuracy as the gas leakage risk prediction model for the i-th equidistant detection point.
4. The gas pipeline detection system based on acoustic analysis according to claim 3, characterized in that: The leakage risk warning module runs a leakage risk warning execution strategy, which includes the following specific steps: S41, obtaining the gas leakage risk coefficient of the i-th equidistant detection point in the next detection cycle predicted by the gas PE pipeline leakage risk prediction module; S42: Preset a gas leakage risk threshold. When the predicted gas leakage risk coefficient of the i-th equidistant detection point in the next detection cycle is greater than the gas leakage risk threshold, execute a first warning operation, which is to issue a gas leakage risk warning of the i-th equidistant detection point along the gas PE pipeline to maintenance personnel; When the predicted gas leakage risk coefficient of the i-th equidistant detection point in the next detection cycle is less than or equal to the gas leakage risk threshold, the first warning operation is not performed.
5. The gas pipeline detection system based on acoustic analysis according to claim 4, characterized in that: The leakage risk warning implementation strategy also includes the following: S43. Obtain the gas leakage risk coefficients of all equally-distanced detection points in the next detection period predicted by the gas PE pipeline leakage risk prediction module, and add and average the gas leakage risk coefficients of all equally-distanced detection points to obtain the gas PE pipeline leakage risk coefficient for the next detection period; S44: Preset a gas PE pipeline leakage risk threshold. When the gas PE pipeline leakage risk coefficient in the next detection cycle is greater than the gas PE pipeline leakage risk threshold, execute a second warning operation, which is to issue a gas PE pipeline leakage risk warning to maintenance personnel; When the gas PE pipeline leakage risk coefficient in the next detection cycle is less than or equal to the gas PE pipeline leakage risk threshold, the second warning operation is not performed.
6. The gas pipeline detection system based on acoustic analysis according to claim 5, characterized in that: The data acquisition module includes a vibration detection data acquisition unit and an acoustic wave signal detection data acquisition unit. The vibration detection data acquisition unit is used to collect vibration detection data of multiple equidistant detection points along the gas PE pipeline at multiple equal intervals within multiple historical detection cycles through a road vibration sensor. The acoustic wave signal detection data acquisition unit is used to collect acoustic wave signal detection data of multiple equidistant detection points along the gas PE pipeline at multiple equal intervals within multiple historical detection cycles through an acoustic wave detector.
