Natural gas pipeline leakage detection method and system

Abstract

The invention relates to the technical field of natural gas leakage detection, and discloses a natural gas pipeline leakage detection method and system, and the method comprises the steps: carrying out the analysis of a surface vibration signal and an in-pipe air pressure signal correspondingly obtained at each node in a topological structure of a pipeline network, and obtaining an analysis result; when the analysis result is that the frequency of the surface vibration signal is greater than the frequency threshold value and the in-pipe air pressure signal is represented as negative pressure, marking the node as a pipeline leakage node; serial numbers corresponding to the pipeline leakage nodes are obtained, and pipeline leakage sections are marked in the topological structure according to the serial numbers; acquiring the flow velocity of natural gas in the pipeline corresponding to the pipeline leakage section, acquiring the time of the surface vibration signal and the in-pipe air pressure signal from the leakage point to the node, and calculating the time difference of the acquired quantity signals; and according to the propagation rate of the surface vibration signal, the propagation rate of the in-pipe air pressure signal, the flow velocity of the natural gas and the time difference, calculating to obtain a leakage point location. The accurate position of the leakage point of the natural gas pipeline can be accurately obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of natural gas leakage detection, and in particular to a natural gas pipeline leakage detection method and system. Background Art

[0002] Pipeline transportation is widely used to transport large quantities of natural gas, and the transportation process is isolated from the outside world. However, due to natural corrosion, external construction and other factors, leakage occurs during the transportation process, which not only wastes resources but also pollutes the environment. In order to avoid natural gas leakage incidents, it is extremely important to detect the leakage location in a timely and accurate manner. With the development of science and technology, pipeline leakage detection technology is also constantly improving, and currently mainly includes hardware-based detection methods and software-based detection methods.

[0003] Hardware-based detection methods include: distributed optical fiber detection method, magnetic flux leakage detection method, gas infrared imaging detection method, pipeline robot detection method, etc. For example, the invention patent application with publication number CN112347919A discloses a remote sensing detection method for underground natural gas micro-leakage points, including: obtaining hyperspectral images of vegetation areas and control areas under natural gas micro-leakage stress; extracting spectral features and color features from the hyperspectral images to obtain spectral and color feature images; segmenting the spectral and color feature images to obtain segmented images, including preliminary natural gas micro-leakage heavy and light stressed vegetation areas; using the segmented images, constructing a circle-like recognition model to identify the location of natural gas micro-leakage points and natural gas micro-leakage stressed vegetation areas; and constructing a natural gas micro-leakage point recognition model based on spectral-spatial feature fusion of spatial relationship features, and fusing the spectral and color feature recognition results through a circle-like ring discrimination model and a linear weighted fusion model to obtain the final natural gas micro-leakage point detection result, so as to achieve non-destructive, rapid, and large-area detection of micro-leakage points in buried long-distance natural gas pipelines or underground gas storage reservoirs in vegetation-covered areas.

[0004] Software-based detection methods include: support vector machine detection method, transient model method, neural network detection method, etc. For example, the invention patent with publication number CN111022941B provides a natural gas pipeline leakage detection method based on LSTM recurrent neural network, including the following steps: Step 1: Collect pipeline leakage audio data; Step 2: Use the improved Mel frequency cepstral coefficient MFCC method to extract features from the audio data; Step 3: Construct a natural gas pipeline leakage detection model based on long short-term memory LSTM recurrent neural network; Step 4: Train and optimize the parameters of the pipeline micro-leakage detection model, and verify the robustness of the model. In the process of optimizing the parameters of the pipeline leakage detection model, the natural gas pipeline leakage detection method based on LSTM recurrent neural network can detect the pipeline status, improve the accuracy of pipeline leakage detection, provide sufficient response time, and reduce the possibility of safety accidents.

[0005] The above method only realizes the rapid and accurate detection of whether a natural gas pipeline is leaking, but cannot accurately obtain the exact location of the natural gas pipeline leak point.

[0006] In view of this, this application is hereby filed. Summary of the invention

[0007] The purpose of the present invention is to provide a natural gas pipeline leakage detection method and system to solve the problem that the existing pipeline leakage detection method cannot accurately obtain the exact location of the natural gas pipeline leakage point.

[0008] The present invention is achieved through the following technical solutions:

[0009] In one aspect, a natural gas pipeline leakage detection method is provided, comprising the following steps:

[0010] A topological structure is established with the pipeline intersection of the natural gas pipeline network as a node, and multiple nodes of the topological structure are numbered sequentially;

[0011] A vibration detection device and an air pressure detection device are arranged at each node of the topological structure; at each node position, the surface vibration signal of the pipeline between the current node and the next node is collected by the vibration detection device, and the air pressure signal in the pipeline between the current node and the next node is collected by the air pressure detection device;

[0012] For each node, execute S1 to S5:

[0013] S1: Analyze the surface vibration signal and the air pressure signal in the pipe to obtain the analysis result;

[0014] S2: When the analysis result shows that the frequency of the surface vibration signal is greater than the frequency threshold and the air pressure signal in the pipe is characterized by negative pressure, the node is marked as a pipeline leakage node;

[0015] S3: Obtain the number corresponding to the pipeline leakage node, and mark the pipeline leakage section in the topology structure according to the number;

[0016] S4: Obtain the flow velocity of natural gas in the pipeline corresponding to the pipeline leakage section, obtain the time t1 when the surface vibration signal reaches the node from the leakage point, obtain the time t2 when the gas pressure signal in the pipe reaches the node from the leakage point, and calculate the time difference between t1 and t2;

[0017] S5: The leakage point is calculated based on the propagation rate of the surface vibration signal, the propagation rate of the gas pressure signal in the pipe, the flow rate of the natural gas and the time difference.

[0018] Among them, S5 includes

[0019] S51: Establish a leakage point calculation model. The expression of the leakage point calculation model is: Wherein, L represents the distance from the leak point to the node, v1 represents the propagation speed of the air pressure signal in the corresponding pipeline, v2 represents the propagation speed of the surface vibration signal on the wall of the corresponding pipeline, v represents the flow rate of natural gas, t1 represents the time for the air pressure signal in the pipeline to propagate from the leak point to the node, t2 represents the time for the surface vibration signal to propagate from the leak point to the node, and t represents the time difference between t1 and t2;

[0020] S52: Calculate the leakage point according to the leakage point calculation model.

[0021] Furthermore, the propagation speed of the air pressure signal in the corresponding pipeline is The propagation speed of the surface vibration signal on the wall of the corresponding pipe Among them, K represents the volume elastic coefficient of natural gas in the pipeline, ρ represents the density of natural gas in the pipeline, E represents the elastic modulus of the pipe, D represents the diameter of the pipeline, e represents the thickness of the pipe wall, and C represents the correction coefficient related to the pipeline constraint conditions.

[0022] Furthermore, calculating the time difference between t1 and t2 includes the following steps:

[0023] Perform noise reduction processing on the surface vibration signal and the air pressure signal in the pipe respectively;

[0024] The surface vibration signal after noise reduction and the air pressure signal in the tube after noise reduction are cross-correlated and the time difference between the two signals is obtained.

[0025] Further, performing noise reduction processing on the surface vibration signal and the air pressure signal in the pipe respectively comprises the following steps:

[0026] Performing filtering and noise reduction processing on the surface vibration signal to obtain a noise-reduced surface vibration signal;

[0027] The cross-spectrum analysis of the air pressure signal inside the tube is performed to obtain the noise-reduced air pressure signal inside the tube.

[0028] Further, filtering and denoising the surface vibration signal includes the following steps:

[0029] Performing collective empirical mode decomposition on the surface vibration signal to obtain signal components after empirical mode decomposition;

[0030] Obtaining the mutual correlation coefficient between the signal component and the surface vibration signal;

[0031] Divide the signal components whose mutual correlation coefficient is greater than the threshold value to obtain the dominant component;

[0032] The dominant components are superimposed and reconstructed to obtain the denoised surface vibration signal.

[0033] Further, performing collective empirical mode decomposition on the surface vibration signal includes the following steps:

[0034] Set the average number of signal processing times;

[0035] Multiple random white noises are superimposed on the signal to obtain multiple signals superimposed with random white noises;

[0036] Repeating the empirical mode decomposition process on multiple signals superimposed with random white noise until the average number of processing times is reached, thereby obtaining multiple signal components after the empirical mode decomposition process;

[0037] The average value of multiple signal components processed by the empirical mode decomposition is obtained to obtain the signal component of the collective empirical mode decomposition.

[0038] Furthermore, the calculation formula of the mutual correlation coefficient is The threshold value of the cross-correlation coefficient is Where R(i) represents the mutual correlation coefficient, ρ i (t) represents the i-th signal component, x(t) represents the surface vibration signal, and ε represents the threshold of the cross-correlation coefficient.

[0039] Furthermore, performing cross-spectrum analysis on the air pressure signal in the tube includes the following steps:

[0040] Obtaining a cross-spectrum phase difference spectrum between the surface vibration signal and the pressure signal in the pipe;

[0041] Obtaining the square coherence function of the amplitude of the surface vibration signal and the pressure signal in the pipe;

[0042] The characteristic frequency band of the in-tube pressure signal is extracted according to the cross-spectral phase difference spectrum and the amplitude square coherence function, and the in-tube pressure signal after noise reduction is obtained according to the characteristic frequency band.

[0043] In another aspect, a natural gas pipeline leakage detection system is provided, comprising:

[0044] The pipeline network topology module is used to establish a topological structure with the pipeline intersection points of the natural gas pipeline network as nodes, and to sequentially number multiple nodes of the topological structure;

[0045] A signal receiving module, used to receive a surface vibration signal sent by a vibration detection device and an in-pipe air pressure signal sent by an air pressure detection device, wherein the vibration detection device and the air pressure detection device are installed at each node of the topological structure, the vibration detection device is used to collect surface vibration signals of pipes between adjacent nodes, and the air pressure detection device is used to collect in-pipe air pressure signals of pipes between adjacent nodes;

[0046] A signal analysis module is used to analyze the surface vibration signal and the air pressure signal in the pipe to obtain the analysis result;

[0047] A node marking module, used for marking the node as a pipeline leakage node when the analysis result shows that the frequency of the surface vibration signal is greater than the frequency threshold and the air pressure signal in the pipe is characterized by negative pressure;

[0048] The leakage section marking module is used to obtain the number corresponding to the pipeline leakage node and mark the pipeline leakage section in the topology structure according to the number;

[0049] The parameter acquisition module is used to obtain the flow velocity of natural gas in the pipeline corresponding to the pipeline leakage section, obtain the time t1 when the surface vibration signal reaches the node from the leakage point, obtain the time t2 when the gas pressure signal in the pipe reaches the node from the leakage point, and calculate the time difference between t1 and t2;

[0050] The leakage point calculation module is used to calculate the leakage point according to the propagation rate of the surface vibration signal, the propagation rate of the air pressure signal in the pipe, the flow rate of the natural gas and the time difference.

[0051] Compared with the prior art, the present invention has the following advantages and beneficial effects: based on the characteristics that the natural gas leakage at the pipeline rupture point rubs against the pipeline wall to generate a surface vibration signal of the pipeline, and the natural gas leakage causes the internal air pressure of the pipeline to change to generate an internal air pressure signal, and based on the principle that the signal propagates at different speeds in different media and arrives at the same signal detection point at different times to form a time difference, the relationship between the distance, speed and time is finally used to calculate the exact position of the leakage point, thereby making up for the defect that the traditional pipeline leakage detection method cannot accurately obtain the exact position of the natural gas pipeline leakage point. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A schematic diagram of the principle of locating a pipeline leakage point provided by an embodiment of the present invention;

[0054] Figure 2 A flow chart of a natural gas pipeline leakage detection method provided by an embodiment of the present invention;

[0055] Figure 3 A schematic diagram of the topological structure of a natural gas pipeline network provided in an embodiment of the present invention;

[0056] Figure 4 A schematic diagram of a topological structure with nodes and leakage sections marked provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0058] Example 1

[0059] When a pipeline in the natural gas network is damaged and leaks, the natural gas will rub against the pipe wall at the leak point to produce sound wave oscillations. At the same time, the loss of natural gas causes the pressure in the pipeline to change and produce negative pressure waves. Negative pressure waves propagate through the natural gas in the pipeline, while infrasound waves propagate along the pipeline wall. Since the two signals propagate at different speeds in different media, the location of the pipeline leak can be determined by the time difference between the two signals received by the sensor at the first station. The principle of locating pipeline leak points is as follows: Figure 1 shown.

[0060] Based on the above principle, this embodiment provides a natural gas pipeline leakage detection method. The main implementation process of the method is as follows: Figure 2 As shown, the following steps are included:

[0061] Step 1: Establish a topological structure with the intersection of pipelines in the natural gas pipeline network as nodes, and number multiple nodes in the topological structure in sequence. The topological structure of the natural gas pipeline network with numbers is as follows: Figure 3 shown.

[0062] Step 2: A vibration detection device and an air pressure detection device are set at each node of the topological structure; at each node position, the surface vibration signal of the pipeline between the current node and the next node is collected by the vibration detection device, and the in-pipe air pressure signal of the pipeline between the current node and the next node is collected by the air pressure detection device.

[0063] This embodiment uses the YSV8008S 8-channel quasi-dynamic strain gauge to collect the surface vibration signal of the pipeline wall. The YSV8008S quasi-dynamic strain gauge has the input function of measuring strain and vibration signals simultaneously, with a total of 16 channels, 24-bit AD, each channel is independent, and the sampling frequency is 1-8000Hz. At the same time, it adopts the internationally advanced network communication method for connection, and is suitable for various desktop and notebook computers for data collection, monitoring, and control. It can be used independently by a single unit or cascaded by multiple units. The HPM180 gas pressure sensor is selected to obtain the changes in the air pressure in the pipe and generate the air pressure signal in the pipe at the same time.

[0064] Step 3: For each node, execute steps 3.1 to 3.5:

[0065] Step 3.1: Analyze the surface vibration signal and the air pressure signal in the tube to obtain the analysis result. When analyzing the signal, the frequency of the surface vibration signal is mainly compared with the preset frequency threshold, and whether the air pressure signal in the tube transmitted by the gas pressure sensor is a negative pressure wave signal is judged.

[0066] Step 3.2: When the analysis result shows that the frequency of the surface vibration signal is greater than the frequency threshold and the air pressure signal in the pipe is characterized by negative pressure, the node is marked as a pipeline leakage node.

[0067] Step 3.3: Obtain the number corresponding to the pipeline leakage node, and mark the pipeline leakage section in the topology structure according to the number.

[0068] After pipeline leakage node marking and pipeline leakage section marking, the topological structure is as follows Figure 4 shown.

[0069] Step 3.4: Obtain the flow velocity of natural gas in the pipeline corresponding to the pipeline leakage section, obtain the time t1 when the surface vibration signal reaches the node from the leakage point, obtain the time t2 when the gas pressure signal in the pipe reaches the node from the leakage point, and calculate the time difference between t1 and t2.

[0070] Step 3.5: Establish a leakage point calculation model. The expression of the leakage point calculation model is: Where L represents the distance from the leakage point to the node, v1 represents the propagation speed of the air pressure signal in the corresponding pipeline, v2 represents the propagation speed of the surface vibration signal on the wall of the corresponding pipeline, v represents the flow rate of natural gas, t1 represents the time it takes for the air pressure signal in the pipeline to propagate from the leakage point to the node, t2 represents the time it takes for the surface vibration signal to propagate from the leakage point to the node, and t represents the time difference between t1 and t2.

[0071] It should be noted that the propagation speed of the negative pressure wave in the pipeline is affected by many factors, such as the density of the medium in the pipeline and the material, thickness, diameter, etc. of the pipeline. Therefore, the speed of the negative pressure wave cannot be simply regarded as a constant value. The propagation speed of the air pressure signal in the corresponding pipeline is The propagation speed of the surface vibration signal on the wall of the corresponding pipe Among them, K represents the volume elastic coefficient of natural gas in the pipeline, ρ represents the density of natural gas in the pipeline, E represents the elastic modulus of the pipe, D represents the diameter of the pipeline, e represents the thickness of the pipe wall, and C represents the correction coefficient related to the pipeline constraint conditions.

[0072] Furthermore, the method for calculating the time difference between t1 and t2 is:

[0073] Firstly, the surface vibration signal and the air pressure signal in the pipe are subjected to noise reduction processing respectively.

[0074] Then, the surface vibration signal after noise reduction and the air pressure signal in the tube after noise reduction are cross-correlated and the time difference between the two signals is obtained.

[0075] Specifically, on the one hand, the surface vibration signal is subjected to collective empirical mode decomposition to obtain the signal components after empirical mode decomposition; the mutual correlation coefficient between the signal component and the surface vibration signal is obtained; the signal component with a mutual correlation coefficient greater than a threshold is divided to obtain the dominant component; the dominant component is superimposed and reconstructed to obtain the surface vibration signal after noise reduction. On the other hand, the cross-spectral phase difference spectrum between the surface vibration signal and the pressure signal in the pipe is obtained; the amplitude square coherence function of the surface vibration signal and the pressure signal in the pipe is obtained; the characteristic frequency band of the pressure signal in the pipe is extracted according to the cross-spectral phase difference spectrum and the amplitude square coherence function, and the pressure signal in the pipe after noise reduction is obtained according to the characteristic frequency band.

[0076] Among them, the method for performing collective empirical mode decomposition on surface vibration signals is: setting the average number of signal processing times; superimposing multiple random white noises on the signal to obtain multiple signals superimposed with random white noises; repeatedly performing empirical mode decomposition processing on multiple signals superimposed with random white noises until the average number of processing times is reached to obtain multiple signal components after empirical mode decomposition processing; obtaining the average value of the multiple signal components after empirical mode decomposition processing to obtain the signal component of collective empirical mode decomposition.

[0077] The pipeline leakage signal is abrupt at the leakage position (time domain) and is a non-stationary signal. Empirical mode analysis is often used to process non-stationary signals. However, there is an intermittent effect in the empirical mode analysis signal, and the use of empirical mode analysis is prone to modal aliasing. There is also an endpoint effect, which reduces the accuracy of modal decomposition and affects the analysis results of the signal. In order to overcome the modal aliasing phenomenon caused by empirical mode analysis, this embodiment uses the above-mentioned collective empirical mode analysis to perform noise reduction on the surface vibration signal.

[0078] Furthermore, in the above-mentioned ensemble empirical mode analysis method, the calculation formula of the mutual correlation coefficient is:

[0079] The threshold value of the cross-correlation coefficient is Where R(i) represents the mutual correlation coefficient, ρ i (t) represents the i-th signal component, x(t) represents the surface vibration signal, and ε represents the threshold of the cross-correlation coefficient.

[0080] Furthermore, the method for performing cross-spectral analysis on the air pressure signal in the pipe is: obtaining the cross-spectral phase difference spectrum between the surface vibration signal and the pressure signal in the pipe; obtaining the amplitude-squared coherence function of the surface vibration signal and the pressure signal in the pipe; extracting the characteristic frequency band of the pressure signal in the pipe according to the cross-spectral phase difference spectrum and the amplitude-squared coherence function, and obtaining the noise-reduced pressure signal in the pipe according to the characteristic frequency band.

[0081] Step 3.6: Substitute the time difference into the leakage point calculation model to calculate the leakage point.

[0082] Example 2

[0083] Corresponding to Example 1, this embodiment provides a natural gas pipeline leakage detection system, comprising:

[0084] The pipeline network topology module is used to establish a topological structure with the pipeline intersection points of the natural gas pipeline network as nodes, and to sequentially number multiple nodes of the topological structure;

[0085] A signal receiving module, used to receive a surface vibration signal sent by a vibration detection device and an in-pipe air pressure signal sent by an air pressure detection device, wherein the vibration detection device and the air pressure detection device are installed at each node of the topological structure, the vibration detection device is used to collect surface vibration signals of pipes between adjacent nodes, and the air pressure detection device is used to collect in-pipe air pressure signals of pipes between adjacent nodes;

[0086] A signal analysis module is used to analyze the surface vibration signal and the air pressure signal in the pipe to obtain the analysis result;

[0087] A node marking module, used for marking the node as a pipeline leakage node when the analysis result shows that the frequency of the surface vibration signal is greater than the frequency threshold and the air pressure signal in the pipe is characterized by negative pressure;

[0088] The leakage section marking module is used to obtain the number corresponding to the pipeline leakage node and mark the pipeline leakage section in the topology structure according to the number;

[0089] The parameter acquisition module is used to obtain the flow velocity of natural gas in the pipeline corresponding to the pipeline leakage section, obtain the time t1 when the surface vibration signal reaches the node from the leakage point, obtain the time t2 when the gas pressure signal in the pipe reaches the node from the leakage point, and calculate the time difference between t1 and t2;

[0090] The leakage point calculation module is used to calculate the leakage point according to the propagation rate of the surface vibration signal, the propagation rate of the air pressure signal in the pipe, the flow rate of the natural gas and the time difference.

[0091] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A natural gas pipeline leakage detection method, characterized in that: The following steps are involved: A topological structure is established with the pipeline intersection of the natural gas pipeline network as a node, and multiple nodes of the topological structure are numbered sequentially; A vibration detection device and an air pressure detection device are arranged at each node of the topological structure; at each node position, the surface vibration signal of the pipeline between the current node and the next node is collected by the vibration detection device, and the air pressure signal in the pipeline between the current node and the next node is collected by the air pressure detection device; For each node, execute S1 to S5: S1: Analyze the surface vibration signal and the air pressure signal in the pipe to obtain the analysis result; S2: When the analysis result shows that the frequency of the surface vibration signal is greater than the frequency threshold and the air pressure signal in the pipe is characterized by negative pressure, the node is marked as a pipeline leakage node; S3: Obtain the number corresponding to the pipeline leakage node, and mark the pipeline leakage section in the topology structure according to the number; S4: Obtain the flow velocity of natural gas in the pipeline corresponding to the pipeline leakage section, obtain the time t1 when the surface vibration signal reaches the node from the leakage point, obtain the time t2 when the gas pressure signal in the pipe reaches the node from the leakage point, and calculate the time difference between t1 and t2; S5: The leakage point is calculated based on the propagation rate of the surface vibration signal, the propagation rate of the gas pressure signal in the pipe, the flow rate of the natural gas and the time difference.

2. A natural gas pipeline leakage detection method according to claim 1, characterized in that: S5 includes S51: Establish a leakage point calculation model. The expression of the leakage point calculation model is: Wherein, L represents the distance from the leak point to the node, v1 represents the propagation speed of the air pressure signal in the corresponding pipeline, v2 represents the propagation speed of the surface vibration signal on the wall of the corresponding pipeline, v represents the flow rate of natural gas, t1 represents the time for the air pressure signal in the pipeline to propagate from the leak point to the node, t2 represents the time for the surface vibration signal to propagate from the leak point to the node, and t represents the time difference between t1 and t2; S52: Calculate the leakage point according to the leakage point calculation model.

3. A natural gas pipeline leakage detection method according to claim 2, characterized in that: The propagation speed of the air pressure signal in the corresponding pipeline The propagation speed of the surface vibration signal on the wall of the corresponding pipe Among them, K represents the volume elastic coefficient of natural gas in the pipeline, ρ represents the density of natural gas in the pipeline, E represents the elastic modulus of the pipe, D represents the diameter of the pipeline, e represents the thickness of the pipe wall, and C represents the correction coefficient related to the pipeline constraint conditions.

4. A natural gas pipeline leakage detection method according to any one of claims 1 to 3, characterized in that: Calculating the time difference between t1 and t2 includes the following steps: The surface vibration signal and the air pressure signal in the pipe are subjected to noise reduction processing respectively; The surface vibration signal after noise reduction and the air pressure signal in the tube after noise reduction are cross-correlated and the time difference between the two signals is obtained.

5. A natural gas pipeline leakage detection method according to claim 4, characterized in that: The noise reduction processing of the surface vibration signal and the air pressure signal in the pipe includes the following steps: Performing filtering and noise reduction processing on the surface vibration signal to obtain a noise-reduced surface vibration signal; The cross-spectrum analysis of the air pressure signal in the tube is performed to obtain the noise-reduced air pressure signal in the tube.

6. A natural gas pipeline leakage detection method according to claim 5, characterized in that: The filtering and noise reduction process of the surface vibration signal includes the following steps: Performing collective empirical mode decomposition on the surface vibration signal to obtain signal components after empirical mode decomposition; Obtaining the mutual correlation coefficient between the signal component and the surface vibration signal; Divide the signal components whose mutual correlation coefficient is greater than the threshold value to obtain the dominant component; The dominant components are superimposed and reconstructed to obtain the denoised surface vibration signal.

7. A natural gas pipeline leakage detection method according to claim 6, characterized in that: The ensemble empirical mode decomposition of surface vibration signals includes the following steps: Set the average number of signal processing times; Multiple random white noises are superimposed on the signal to obtain multiple signals superimposed with random white noises; Repeating the empirical mode decomposition process on multiple signals superimposed with random white noise until the average number of processing times is reached, thereby obtaining multiple signal components after the empirical mode decomposition process; The average value of multiple signal components processed by the empirical mode decomposition is obtained to obtain the signal component of the collective empirical mode decomposition.

8. A natural gas pipeline leakage detection method according to claim 6, characterized in that: The calculation formula of the mutual correlation coefficient is The threshold value of the cross-correlation coefficient is Where R(i) represents the mutual correlation coefficient, ρ i (t) represents the i-th signal component, x(t) represents the surface vibration signal, and ε represents the threshold of the cross-correlation coefficient.

9. A natural gas pipeline leakage detection method according to any one of claims 5 to 8, characterized in that: The cross-spectrum analysis of the air pressure signal in the tube includes the following steps: Obtaining a cross-spectrum phase difference spectrum between the surface vibration signal and the pressure signal in the pipe; Obtaining the square coherence function of the amplitude of the surface vibration signal and the pressure signal in the pipe; The characteristic frequency band of the in-pipe pressure signal is extracted according to the cross-spectral phase difference spectrum and the amplitude square coherence function, and the in-pipe pressure signal after noise reduction is obtained according to the characteristic frequency band.

10. A natural gas pipeline leakage detection system, characterized in that: include The pipeline network topology module is used to establish a topological structure with the pipeline intersection points of the natural gas pipeline network as nodes, and to sequentially number multiple nodes of the topological structure; A signal receiving module, used to receive a surface vibration signal sent by a vibration detection device and an in-pipe air pressure signal sent by an air pressure detection device, wherein the vibration detection device and the air pressure detection device are installed at each node of the topological structure, the vibration detection device is used to collect surface vibration signals of pipes between adjacent nodes, and the air pressure detection device is used to collect in-pipe air pressure signals of pipes between adjacent nodes; A signal analysis module is used to analyze the surface vibration signal and the air pressure signal in the pipe to obtain the analysis result; A node marking module, used for marking the node as a pipeline leakage node when the analysis result shows that the frequency of the surface vibration signal is greater than the frequency threshold and the air pressure signal in the pipe is characterized by negative pressure; The leakage section marking module is used to obtain the number corresponding to the pipeline leakage node and mark the pipeline leakage section in the topology structure according to the number; The parameter acquisition module is used to obtain the flow velocity of natural gas in the pipeline corresponding to the pipeline leakage section, obtain the time t1 when the surface vibration signal reaches the node from the leakage point, obtain the time t2 when the gas pressure signal in the pipe reaches the node from the leakage point, and calculate the time difference between t1 and t2; The leakage point calculation module is used to calculate the leakage point according to the propagation rate of the surface vibration signal, the propagation rate of the air pressure signal in the pipe, the flow rate of the natural gas and the time difference.

Images