An oil and gas pipeline leakage diagnosis method and system based on feature extraction

Abstract

The present invention discloses a method and system for diagnosing oil and gas pipeline leakage based on feature extraction, which relates to the technical field of oil and gas transportation. The present invention establishes a leakage diffusion model according to basic data, classifies and numbers each oil and gas pipeline according to the basic data, and obtains the real-time operation data of the oil and gas pipeline through a sensor group arranged on the monitoring node. By extracting features from the real-time operation data, the operation evaluation coefficient is further calculated, and the operation evaluation coefficient is judged according to a preset operation evaluation threshold to generate a leakage search signal. According to the leakage search signal, the coordinates of the monitoring node where the leakage is detected are obtained, and then the corresponding leakage diffusion model is searched. The real-time updated data at the target node is obtained to optimize the leakage diffusion model, and the leakage site is located according to the optimized leakage diffusion model. A visual reminder signal is generated and marked on the pipeline three-dimensional model, and the oil and gas diffusion effect is visually generated at the leakage site according to the leakage diffusion model.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas transportation, and particularly to an oil and gas pipeline leakage diagnosis method and system based on feature extraction. Background Art

[0002] Since the buried depth of oil and gas pipelines is usually about 1 - 2 meters, they are vulnerable to natural disasters such as landslides, earthquakes, floods, or human factors such as construction activities and deliberate sabotage, resulting in pipeline damage or even oil and gas leakage. Oil and gas leakage not only directly causes huge property losses but also has a serious impact on the environment, such as soil and water pollution, ecosystem damage, etc., and there is also a risk of ignition and explosion, seriously threatening life and property safety. Oil and gas pipeline leakage detection technology can quickly identify leakage problems, accurately locate the leakage location, and provide timely response and treatment measures, which is of great significance for ensuring the safe operation of pipelines.

[0003] Currently, the mainstream oil and gas pipeline leakage detection technologies mainly include manual line patrol method, acoustic wave detection method, stress wave detection method, distributed optical fiber sensor detection method, etc. Although these oil and gas pipeline leakage detection technologies are widely used, they still have some disadvantages: 1) Poor continuity and real - time performance: Due to the long laying distance, wide coverage, and complex working environment of oil and gas pipelines, some detection technologies such as manual line patrol method and acoustic wave detection method can only partially cover the pipeline and cannot achieve real - time monitoring of the entire pipeline; 2) Poor positioning ability: Limited by the sensitivity and resolution of sensors, the complexity of pipelines, the characteristics of leaks, and environmental conditions, the existing leakage detection technologies have low positioning accuracy for leakage points. For example, the positioning accuracy of the acoustic wave detection method is only about 100 meters.

[0004] In view of the above - mentioned technical defects, a solution is proposed. Summary of the Invention

[0005] The purpose of the present invention is to: locate the leakage site according to the optimized leakage diffusion model, generate a visual reminder signal for marking on the 3D pipeline model, and visually generate the oil and gas diffusion effect at the leakage site according to the leakage diffusion model.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions: An oil and gas pipeline leakage diagnosis method and system based on feature extraction, including the following steps:

[0007] Step 1: Obtain and process the basic data of the oil and gas pipeline, establish a leakage diffusion model according to the basic data, classify and number each oil and gas pipeline according to the basic data, and store the corresponding leakage diffusion model according to the number.

[0008] Step 2: Establish a 3D pipeline model based on the basic data of the oil and gas pipeline, demarcate several monitoring nodes on the 3D pipeline model, and assign classification number tags to the monitoring nodes according to their positions on the oil and gas pipeline. Obtain the real-time operation data of the oil and gas pipeline through the sensor group set on the monitoring nodes;

[0009] Step 3: Obtain and process the real-time operation data, extract the features of the real-time operation data, and then calculate the operation evaluation coefficient. Judge the operation evaluation coefficient according to the preset operation evaluation threshold to generate a leakage search signal;

[0010] Step 4: Obtain and process the leakage search signal, obtain the coordinates of the monitoring node where the leakage is detected according to the leakage search signal, and mark it as the target node. Search for the corresponding leakage diffusion model according to the number of the target node, obtain the real-time updated data at the target node to optimize the leakage diffusion model, and locate the leakage site according to the optimized leakage diffusion model, and send the coordinates of the leakage site to the trajectory output unit;

[0011] Step 5: Obtain the coordinates of the leakage site, generate a visual reminder signal and mark it on the 3D pipeline model, and visually generate the oil and gas diffusion effect at the leakage site according to the leakage diffusion model.

[0012] Furthermore, the specific process of establishing the leakage diffusion model based on the basic data is as follows:

[0013] S101: Obtain the basic data of the oil and gas pipeline, and the basic data includes the pipe diameter data of the oil and gas pipeline, the thickness data of the oil and gas pipeline, and the concentration data of the transportation medium in the oil and gas pipeline;

[0014] S102: Based on the basic data of the oil and gas pipeline, set the physical constraint conditions of the initial network model based on the fully connected neural network architecture, define the loss function of the initial network model, and embed the non-steady convective diffusion equation and its residual gradient of the oil and gas pipeline leakage diffusion into the loss function of the initial network model to obtain the leakage diffusion model of the oil and gas pipeline leakage;

[0015] S103: Detect the leaked oil and gas in the leakage area during the leakage diffusion of the oil and gas pipeline through mid-infrared light waves, and take the concentration grayscale map of the leakage area during the leakage diffusion of the oil and gas pipeline. Integrate multiple groups of concentration grayscale maps into a data set as training samples;

[0016] S104: Divide the generated training samples into a training set and a test set according to the ratio of 8:2;

[0017] S105: Download the weight file and load it onto the corresponding network to initialize the transfer network parameters, and determine the number of hidden layer nodes of the BP neural network model according to the number of normal images in the training set;

[0018] S106. Modify the last fully connected layer of the network, keep the input unchanged, set the output to the maximum diameter of the leakage area, initialize the weights of the last layer, use the gradient descent algorithm for learning, and adopt fixed-step decay to optimize the training parameters. Retrain the entire network to obtain an anomaly recognition model;

[0019] S305. During the training process, randomly and without repetition extract small batches of normal images from the training set. After extracting all the normal images in the training set, it is regarded as one training cycle. Iterate for a certain number of cycles to complete the training, and then use the test set to evaluate the effect of the leakage diffusion model.

[0020] Furthermore, the sensor group includes a pressure sensor and a flow sensor arranged on the inner wall of the oil and gas pipeline, and a temperature sensor and an acoustic wave sensor arranged on the outer wall of the oil and gas pipeline.

[0021] Furthermore, the specific process of generating the leakage search signal is as follows:

[0022] S201. Obtain real-time operation data, where the real-time operation data includes real-time pressure data Fi, real-time flow data Qi, real-time temperature data Ti, and real-time acoustic wave data;

[0023] S202. Extract features from the real-time acoustic wave data to obtain the time-domain feature values of the acoustic wave data, including amplitude A, zero-crossing rate η, and signal energy E. Calculate the acoustic wave feature coefficient Ui of the oil and gas pipeline according to the following formula: , where e1, e2, and e3 are preset weight coefficients, and the acoustic wave feature coefficient is used to reflect the comprehensive performance of each time-domain feature value in the real-time acoustic wave data;

[0024] S203. Then calculate the operation evaluation coefficient Wi according to the following formula: , where α, β, and γ are preset proportionality coefficients, is the standard pressure value under the normal state of the oil and gas pipeline, is the standard flow value under the normal state of the oil and gas pipeline, is the standard temperature value under the normal state of the oil and gas pipeline, is the normal state characteristic coefficient value of the acoustic wave data under the normal state of the oil and gas pipeline. The operation evaluation coefficient is used to reflect the actual operation state of the oil and gas pipeline. The smaller the operation evaluation coefficient, the more the operation state of the oil and gas pipeline tends to be in the normal state. On the contrary, the larger the operation evaluation coefficient, the more the operation state of the oil and gas pipeline tends to be in the abnormal state;

[0025] S204. Obtain a preset operation evaluation threshold. If the operation evaluation coefficient is greater than or equal to the operation evaluation threshold, find the corresponding monitoring node according to the source of the real-time operation data, and generate a leakage search signal in combination with the coordinates of the monitoring node.

[0026] Further, the specific process of obtaining the coordinates of the leakage site is as follows:

[0027] S301. Search for the corresponding leakage diffusion model in the model storage unit according to the number of the target node;

[0028] S302. Obtain the real-time updated data at the target node. The real-time updated data includes the real-time data of the oil and gas pipeline where the target node is located and the concentration data of the transportation medium in the updated oil and gas pipeline. Reconstruct the oil and gas concentration field during the leakage diffusion of the oil and gas pipeline based on the concentration data of the transportation medium in the updated oil and gas pipeline to obtain a simulated diagram of the oil and gas concentration field;

[0029] S304. Obtain the real-time data of the oil and gas pipeline. Based on the leakage diffusion model, obtain the oil and gas concentration field during the diffusion of the oil and gas pipeline. After visualizing the oil and gas concentration field during the diffusion of the oil and gas pipeline, intercept several groups of predicted diagrams of the oil and gas concentration field one by one along the distribution position of the oil and gas pipeline;

[0030] S305. Compare the simulated diagram of the oil and gas concentration field with several groups of predicted diagrams of the oil and gas concentration field to obtain a predicted diagram of the oil and gas concentration field that is consistent with the simulated diagram of the oil and gas concentration field. Then, the position where the predicted diagram of the oil and gas concentration field is located is the leakage site, and the coordinates of the leakage site are obtained.

[0031] The present invention also provides an oil and gas pipeline leakage diagnosis system based on feature extraction, including a model storage unit, a data monitoring unit, a data analysis unit, a leakage diagnosis unit, and a trajectory output unit;

[0032] The model storage unit is used to obtain and process the basic data of the oil and gas pipeline, establish a leakage diffusion model according to the basic data, classify and number each oil and gas pipeline according to the basic data, and store the corresponding leakage diffusion model according to the number;

[0033] The data monitoring unit is used to establish a three-dimensional pipeline model according to the basic data of the oil and gas pipeline, delimit several monitoring nodes on the three-dimensional pipeline model, assign classification number marks to the monitoring nodes according to the positions of the monitoring nodes on the oil and gas pipeline, obtain the real-time operation data of the oil and gas pipeline through the sensor group arranged on the monitoring nodes, and send the real-time operation data to the data analysis unit;

[0034] The data analysis unit is used to obtain and process real-time operation data, extract features from the real-time operation data, and then calculate an operation evaluation coefficient. It judges the operation evaluation coefficient according to a preset operation evaluation threshold to generate a leakage search signal and send it to the leakage diagnosis unit;

[0035] The leakage diagnosis unit is used to obtain and process the leakage search signal. According to the leakage search signal, it obtains the monitoring node coordinates where the detected leakage occurs and marks them as target nodes. It searches for the corresponding leakage diffusion model from the model storage unit according to the numbers of the target nodes, obtains the real-time updated data at the target nodes to optimize the leakage diffusion model, and locates the leakage site according to the optimized leakage diffusion model, and sends the coordinates of the leakage site to the trajectory output unit;

[0036] The trajectory output unit is used to obtain the coordinates of the leakage site, generate a visual reminder signal to mark it on the pipeline three-dimensional model, and visually generate an oil and gas diffusion effect at the leakage site according to the leakage diffusion model.

[0037] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present invention are:

[0038] The oil and gas pipeline leakage diagnosis method and system based on feature extraction establish a leakage diffusion model according to basic data, classify and number each oil and gas pipeline according to the basic data, and obtain the real-time operation data of the oil and gas pipeline through the sensor group set on the monitoring nodes. By extracting features from the real-time operation data, then calculating an operation evaluation coefficient, judging the operation evaluation coefficient according to a preset operation evaluation threshold to generate a leakage search signal, obtaining the monitoring node coordinates where the detected leakage occurs according to the leakage search signal, then searching for the corresponding leakage diffusion model, obtaining the real-time updated data at the target nodes to optimize the leakage diffusion model, locating the leakage site according to the optimized leakage diffusion model, generating a visual reminder signal to mark it on the pipeline three-dimensional model, and visually generating an oil and gas diffusion effect at the leakage site according to the leakage diffusion model. Brief Description of the Drawings

[0039] Figure 1 Shows the schematic flow chart of the method of the present invention;

[0040] Figure 2 Shows the schematic structural diagram of the system of the present invention. Detailed Embodiments

[0041] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0042] Embodiment 1:

[0043] As Figure 1 shown, a method for diagnosing oil and gas pipeline leakage based on feature extraction includes the following steps:

[0044] Step 1: Obtain and process the basic data of the oil and gas pipeline, establish a leakage diffusion model according to the basic data, classify and number each oil and gas pipeline according to the basic data, and store the corresponding leakage diffusion model according to the number;

[0045] The specific process of establishing a leakage diffusion model according to the basic data is as follows:

[0046] S101: Obtain the basic data of the oil and gas pipeline. The basic data includes the pipe diameter data of the oil and gas pipeline, the pipe thickness data of the oil and gas pipeline, and the concentration data of the transportation medium in the oil and gas pipeline;

[0047] S102: Based on the basic data of the oil and gas pipeline, set the physical constraint conditions of the initial network model based on the fully connected neural network architecture, define the loss function of the initial network model, and embed the non-steady convective diffusion equation and its residual gradient of the oil and gas pipeline leakage diffusion into the loss function of the initial network model to obtain the leakage diffusion model of the oil and gas pipeline leakage;

[0048] S103: Detect the leaked oil and gas in the leakage area during the leakage diffusion of the oil and gas pipeline through mid-infrared light waves, take the concentration grayscale image of the leakage area during the leakage diffusion of the oil and gas pipeline, and integrate multiple groups of concentration grayscale images into a data set as training samples;

[0049] S104: Divide the generated training samples into a training set and a test set according to the ratio of 8:2;

[0050] S105: Download the weight file and load it onto the corresponding network to initialize the transfer network parameters, and determine the number of hidden layer nodes of the BP neural network model according to the number of normal images in the training set;

[0051] S106: Modify the last fully connected layer of the network, keep the input unchanged, set the output to the maximum diameter of the leakage area, initialize the weights of the last layer, use the gradient descent algorithm for learning, and use fixed-step decay to optimize the training parameters, and retrain the entire network to obtain an anomaly recognition model;

[0052] S305. During the training process, randomly and without repetition, small batches of normal images are drawn from the training set. After all the normal images in the training set are drawn, it is regarded as one training cycle. Iterate for a certain number of cycles to complete the training, and then use the test set to evaluate the effect of the leakage diffusion model.

[0053] Step 2. Establish a 3D pipeline model based on the basic data of the oil and gas pipeline, and demarcate several monitoring nodes on the 3D pipeline model. According to the positions of the monitoring nodes on the oil and gas pipeline, the monitoring nodes are also given classification number marks. The real-time operation data of the oil and gas pipeline is obtained through the sensor group set on the monitoring nodes.

[0054] The sensor group includes a pressure sensor and a flow sensor set on the inner wall of the oil and gas pipeline, and a temperature sensor and a sound wave sensor set on the outer wall of the oil and gas pipeline.

[0055] Step 3. Obtain and process the real-time operation data, extract features from the real-time operation data, and then calculate the operation evaluation coefficient. Judge the operation evaluation coefficient according to the preset operation evaluation threshold to generate a leakage search signal.

[0056] The specific process of generating the leakage search signal is as follows:

[0057] S201. Obtain the real-time operation data, and the real-time operation data includes real-time pressure data Fi, real-time flow data Qi, real-time temperature data Ti, and real-time sound wave data.

[0058] S202. Extract features from the real-time sound wave data to obtain the time-domain feature values of the sound wave data, including amplitude A, zero-crossing rate η, and signal energy E. Calculate the sound wave feature coefficient Ui of the oil and gas pipeline according to the following formula: , where e1, e2, and e3 are preset weight coefficients, and the sound wave feature coefficient is used to reflect the comprehensive performance of each time-domain feature value in the real-time sound wave data.

[0059] S203. Then calculate the operation evaluation coefficient Wi according to the following formula: , where α, β, and γ are preset proportionality coefficients, is the standard pressure value under the normal state of the oil and gas pipeline, is the standard flow value under the normal state of the oil and gas pipeline, is the standard temperature value under the normal state of the oil and gas pipeline, is the normal characteristic coefficient value of the sound wave data under the normal state of the oil and gas pipeline. The operation evaluation coefficient is used to reflect the actual operation state of the oil and gas pipeline. The smaller the operation evaluation coefficient, the more the operation state of the oil and gas pipeline tends to be in the normal state. On the contrary, the larger the operation evaluation coefficient, the more the operation state of the oil and gas pipeline tends to be in the abnormal state.

[0060] S204. Obtain a preset operation evaluation threshold. If the operation evaluation coefficient is greater than or equal to the operation evaluation threshold, find the corresponding monitoring node according to the source of the real-time operation data, and generate a leakage search signal in combination with the coordinates of the monitoring node.

[0061] Step 4. Obtain and process the leakage search signal. According to the leakage search signal, obtain the coordinates of the monitoring node where the leakage is detected and mark it as the target node. Find the corresponding leakage diffusion model according to the number of the target node, obtain the real-time updated data at the target node to optimize the leakage diffusion model, and locate the leakage site according to the optimized leakage diffusion model, and send the coordinates of the leakage site to the trajectory output unit.

[0062] The specific process of obtaining the coordinates of the leakage site is as follows:

[0063] S301. Find the corresponding leakage diffusion model from the model storage unit according to the number of the target node.

[0064] S302. Obtain the real-time updated data at the target node. The real-time updated data includes the real-time data of the oil and gas pipeline where the target node is located and the concentration data of the transported medium in the updated oil and gas pipeline. Reconstruct the oil and gas concentration field during the leakage diffusion of the oil and gas pipeline based on the updated concentration data of the transported medium in the oil and gas pipeline to obtain an oil and gas concentration field simulation diagram.

[0065] S304. Obtain the real-time data of the oil and gas pipeline, obtain the oil and gas concentration field during the diffusion of the oil and gas pipeline based on the leakage diffusion model, and after visualizing the oil and gas concentration field during the diffusion of the oil and gas pipeline, intercept several groups of oil and gas concentration field prediction diagrams one by one along the distribution position of the oil and gas pipeline.

[0066] S305. Compare the oil and gas concentration field simulation diagram with several groups of oil and gas concentration field prediction diagrams, and obtain the oil and gas concentration field prediction diagram that is consistent with the oil and gas concentration field simulation diagram. Then the position where the oil and gas concentration field prediction diagram is located is the leakage site, and the coordinates of the leakage site are obtained.

[0067] Step 5. Obtain the coordinates of the leakage site, generate a visual reminder signal and mark it on the pipeline 3D model, and visually generate the oil and gas diffusion effect at the leakage site according to the leakage diffusion model.

[0068] The present invention establishes a leakage diffusion model based on basic data, classifies and numbers each oil and gas pipeline according to the basic data, obtains the real-time operation data of the oil and gas pipeline through a sensor group arranged on the monitoring node, extracts features from the real-time operation data, and then calculates an operation evaluation coefficient. The operation evaluation coefficient is judged according to a preset operation evaluation threshold to generate a leakage search signal. The coordinates of the monitoring node where the leakage is detected are obtained according to the leakage search signal, and then the corresponding leakage diffusion model is searched. The real-time updated data at the target node is obtained to optimize the leakage diffusion model, and the leakage location is located according to the optimized leakage diffusion model. A visual reminder signal is generated and marked on the pipeline three-dimensional model, and the oil and gas diffusion effect is visually generated at the leakage location according to the leakage diffusion model.

[0069] Embodiment 2:

[0070] As Figure 2 shown, the present invention also provides an oil and gas pipeline leakage diagnosis system based on feature extraction, including a model storage unit, a data monitoring unit, a data analysis unit, a leakage diagnosis unit, and a trajectory output unit;

[0071] The model storage unit is used to obtain and process the basic data of the oil and gas pipeline, establish a leakage diffusion model according to the basic data, classify and number each oil and gas pipeline according to the basic data, and store the corresponding leakage diffusion model according to the number;

[0072] The data monitoring unit is used to establish a pipeline three-dimensional model according to the basic data of the oil and gas pipeline, delimit a number of monitoring nodes on the pipeline three-dimensional model, assign the same classification number mark to the monitoring nodes according to the positions of the monitoring nodes in the oil and gas pipeline, obtain the real-time operation data of the oil and gas pipeline through a sensor group arranged on the monitoring nodes, and send the real-time operation data to the data analysis unit;

[0073] The data analysis unit is used to obtain and process the real-time operation data, extract features from the real-time operation data, and then calculate an operation evaluation coefficient. The operation evaluation coefficient is judged according to a preset operation evaluation threshold to generate a leakage search signal and send it to the leakage diagnosis unit;

[0074] The leakage diagnosis unit is used to obtain and process the leakage search signal, obtain the coordinates of the monitoring node where the leakage is detected according to the leakage search signal, and mark it as the target node. According to the number of the target node, the corresponding leakage diffusion model is searched from the model storage unit. The real-time updated data at the target node is obtained to optimize the leakage diffusion model, and the leakage location is located according to the optimized leakage diffusion model. The coordinates of the leakage location are sent to the trajectory output unit;

[0075] The trajectory output unit is used to obtain the coordinates of the leakage site, generate a visual reminder signal for marking on the 3D pipeline model, and visually generate the oil and gas diffusion effect at the leakage site according to the leakage diffusion model.

[0076] The setting of the threshold size is for the convenience of comparison. Regarding the threshold size, it depends on the amount of sample data and the base quantity set by those skilled in the art for each group of sample data; as long as the proportional relationship between the parameter and the quantified value is not affected.

[0077] The above formulas are all dimensionless and take their numerical calculations. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0078] In the two embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways; for example, the division of the modules is only for logical function division, and there can be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed; another point, the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the modules can be in an electrical or other form.

[0079] The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A method for diagnosing oil and gas pipeline leakage based on feature extraction, characterized in that, It includes the following steps: Step 1: Obtain and process the basic data of the oil and gas pipeline, establish a leakage diffusion model based on the basic data, classify and number each oil and gas pipeline according to the basic data, and store the corresponding leakage diffusion model according to the number; Step 2: Establish a three-dimensional pipeline model based on the basic data of the oil and gas pipeline, delimit several monitoring nodes on the three-dimensional pipeline model, assign classification number marks to the monitoring nodes according to the positions of the monitoring nodes on the oil and gas pipeline, and obtain the real-time operation data of the oil and gas pipeline through the sensor group arranged on the monitoring nodes; Step 3: Obtain and process the real-time operation data, extract the features of the real-time operation data, and then calculate the operation evaluation coefficient, and judge the operation evaluation coefficient according to the preset operation evaluation threshold to generate a leakage search signal; The specific process of generating the leakage search signal is as follows: S201: Obtain the real-time operation data, and the real-time operation data includes real-time pressure data Fi, real-time flow data Qi, real-time temperature data Ti, and real-time acoustic wave data; S202. Extract features from the real-time acoustic wave data to obtain the time-domain feature values of the acoustic wave data, including the amplitude A, the zero-crossing rate η, and the signal energy E. Calculate the acoustic wave characteristic coefficient Ui of the oil and gas pipeline according to the following formula: , where e1, e2, and e3 are preset weight coefficients, and the acoustic wave characteristic coefficient is used to reflect the comprehensive performance of each time-domain feature value in the real-time acoustic wave data; S203. Furthermore, calculate the operation evaluation coefficient Wi according to the following formula: , where α, β, and γ are preset proportionality coefficients, is the standard pressure value under the normal state of the oil and gas pipeline, is the standard flow value under the normal state of the oil and gas pipeline, is the standard temperature value under the normal state of the oil and gas pipeline, is the normal characteristic coefficient value of the acoustic wave data under the normal state of the oil and gas pipeline; S204: Obtain the preset operation evaluation threshold. If the operation evaluation coefficient is greater than or equal to the operation evaluation threshold, find the corresponding monitoring node according to the source of the real-time operation data, and generate a leakage search signal in combination with the coordinates of the monitoring node; Step 4: Obtain and process the leakage search signal, obtain the coordinates of the monitoring node where the leakage is detected according to the leakage search signal and mark it as the target node, find the corresponding leakage diffusion model according to the number of the target node, obtain the real-time updated data at the target node to optimize the leakage diffusion model, and locate the leakage site according to the optimized leakage diffusion model, and send the coordinates of the leakage site to the trajectory output unit; Step 5: Obtain the coordinates of the leakage site, generate a visual reminder signal and mark it on the three-dimensional pipeline model, and visually generate the oil and gas diffusion effect at the leakage site according to the leakage diffusion model.

2. The oil and gas pipeline leakage diagnosis method based on feature extraction according to claim 1, wherein The specific process of establishing the leakage diffusion model based on the basic data is as follows: S101: Obtain the basic data of the oil and gas pipeline, and the basic data includes the pipe diameter data of the oil and gas pipeline, the thickness data of the oil and gas pipeline, and the concentration data of the transportation medium in the oil and gas pipeline; S102: Based on the basic data of the oil and gas pipeline, set the physical constraint conditions of the initial network model based on the fully connected neural network architecture, define the loss function of the initial network model, and embed the non-steady convective diffusion equation and its residual gradient of the oil and gas pipeline leakage diffusion into the loss function of the initial network model to obtain the leakage diffusion model of the oil and gas pipeline leakage; S103: Detect the leaked oil and gas in the leakage area during the leakage diffusion of the oil and gas pipeline through mid-infrared light waves, and use the concentration grayscale map of the leakage area during the leakage diffusion of the oil and gas pipeline, and integrate multiple groups of concentration grayscale maps into a data set as training samples; S104: Divide the generated training samples into a training set and a test set according to the ratio of 8:2; S105: Download the weight file and load it onto the corresponding network to initialize the transfer network parameters, and determine the number of hidden layer nodes of the BP neural network model according to the number of normal images in the training set; S106. Modify the last fully connected layer of the network. Keep the input unchanged, set the output to the maximum diameter of the leakage area, initialize the weights of the last layer, use the gradient descent algorithm for learning, and adopt fixed-step decay to optimize the training parameters. Retrain the entire network to obtain an anomaly recognition model; S305. During the training process, randomly and without repetition extract small batches of normal images from the training set. Completing one draw of all the normal images in the training set is considered one training cycle. Iterate for a certain number of cycles to complete the training, and then use the test set to evaluate the effect of the leakage diffusion model.

3. A method for diagnosing oil and gas pipeline leakage based on feature extraction according to claim 1, characterized in that The sensor group includes a pressure sensor and a flow sensor arranged on the inner wall of the oil and gas pipeline, and a temperature sensor and an acoustic wave sensor arranged on the outer wall of the oil and gas pipeline.

4. A method for diagnosing oil and gas pipeline leakage based on feature extraction according to claim 1, characterized in that, The specific process of obtaining the coordinates of the leakage site is as follows: S301. Search for the corresponding leakage diffusion model in the model storage unit according to the number of the target node; S302. Obtain the real-time updated data at the target node. The real-time updated data includes the real-time data of the oil and gas pipeline where the target node is located and the updated concentration data of the transportation medium in the oil and gas pipeline. Based on the updated concentration data of the transportation medium in the oil and gas pipeline, reconstruct the oil and gas concentration field during the leakage diffusion of the oil and gas pipeline to obtain a simulated diagram of the oil and gas concentration field; S304. Obtain the real-time data of the oil and gas pipeline. Based on the leakage diffusion model, obtain the oil and gas concentration field during the diffusion of the oil and gas pipeline. After visualizing the oil and gas concentration field during the diffusion of the oil and gas pipeline, intercept several groups of predicted diagrams of the oil and gas concentration field one by one along the distribution position of the oil and gas pipeline; S305. Compare the simulated diagram of the oil and gas concentration field with several groups of predicted diagrams of the oil and gas concentration field. The position of the predicted diagram of the oil and gas concentration field that is consistent with the simulated diagram of the oil and gas concentration field is the leakage site, and the coordinates of the leakage site are obtained.

5. An oil and gas pipeline leakage diagnosis system based on feature extraction, characterized in that, A model storage unit, a data monitoring unit, a data analysis unit, a leakage diagnosis unit, and a trajectory output unit; The model storage unit is used to obtain and process the basic data of the oil and gas pipeline, establish a leakage diffusion model according to the basic data, classify and number each oil and gas pipeline according to the basic data, and store the corresponding leakage diffusion model according to the number; The data monitoring unit is used to establish a three-dimensional model of the pipeline according to the basic data of the oil and gas pipeline, delimit several monitoring nodes on the three-dimensional model of the pipeline, and also assign classification number marks to the monitoring nodes according to the positions of the monitoring nodes on the oil and gas pipeline. Obtain the real-time operation data of the oil and gas pipeline through the sensor group arranged on the monitoring nodes, and send the real-time operation data to the data analysis unit; The data analysis unit is used to obtain and process the real-time operation data, extract features from the real-time operation data, and then calculate the operation evaluation coefficient. Judge the operation evaluation coefficient according to the preset operation evaluation threshold to generate a leakage search signal and send it to the leakage diagnosis unit; The specific process of generating the leakage search signal is as follows: S201. Obtain the real-time operation data. The real-time operation data includes real-time pressure data Fi, real-time flow data Qi, real-time temperature data Ti, and real-time acoustic wave data; S202. Extract features from the real-time acoustic wave data to obtain the time-domain feature values of the acoustic wave data, including the amplitude A, the zero-crossing rate η, and the signal energy E. Calculate the acoustic wave feature coefficient Ui of the oil and gas pipeline according to the following formula: where e1, e2, and e3 are preset weight coefficients, and the acoustic wave feature coefficient is used to reflect the comprehensive performance of each time-domain feature value in the real-time acoustic wave data; S203. Further, calculate the operation evaluation coefficient Wi according to the following formula: , where α, β, and γ are preset proportionality coefficients, is the standard pressure value under the normal state of the oil and gas pipeline, is the standard flow value under the normal state of the oil and gas pipeline, is the standard temperature value under the normal state of the oil and gas pipeline, is the normal characteristic coefficient value of the acoustic wave data under the normal state of the oil and gas pipeline; S204. Obtain a preset operation evaluation threshold. If the operation evaluation coefficient is greater than or equal to the operation evaluation threshold, find the corresponding monitoring node according to the source of the real-time operation data, and generate a leakage search signal in combination with the coordinates of the monitoring node; The leakage diagnosis unit is used to obtain and process the leakage search signal, obtain the coordinates of the monitoring node where the leakage is detected according to the leakage search signal, and mark it as the target node. Find the corresponding leakage diffusion model from the model storage unit according to the number of the target node, obtain the real-time updated data at the target node to optimize the leakage diffusion model, and locate the leakage site according to the optimized leakage diffusion model, and send the coordinates of the leakage site to the trajectory output unit; The trajectory output unit is used to obtain the coordinates of the leakage site, generate a visual reminder signal and mark it on the pipeline 3D model, and visually generate an oil and gas diffusion effect at the leakage site according to the leakage diffusion model.

Images