Method and device for locating gas leaks, and computer-readable storage medium

Abstract

The present application relates to the field of gas safety detection technology, and discloses a method and device for gas leak location, and a computer-readable storage medium, the method comprising: obtaining real-time manhole gas diffusion trend data monitored by a gas sensor in a manhole; obtaining a predicted leak point location based on the real-time manhole gas diffusion trend data and a trained LSTM network; wherein the trained LSTM network is generated by training the LSTM network using the gas diffusion trend data of different locations around the same leak point in the data set as input and the leak point location as output; the data set is obtained by mixing simulated data and real data; the simulated data is obtained by performing a three-dimensional CFD simulation of the diffusion of gas in the soil based on the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of gas in the soil after a gas pipeline leak. The method timely and accurately predicts the location of the leak point, thereby eliminating safety hazards in a timely manner.

Description

Technical Field

[0001] The present application relates to the technical field of gas safety detection, for example, to a method and device for locating gas leaks, and a computer-readable storage medium. Background Art

[0002] At present, with the acceleration of my country's energy structure adjustment process, the construction of urban gas pipeline network is also developing rapidly. Due to the flammable and explosive characteristics of gas, the safety of pipelines as the main means of gas transportation is particularly important. Among various production safety accidents, gas pipeline leakage undoubtedly poses a huge threat to people's life and property safety. While trying to avoid such accidents, it is also necessary to locate the leakage point as soon as possible and carry out relevant treatment.

[0003] The related technology discloses a drone-type industrial hazardous gas leak detection system with freely adjustable angles. The system can realize thermal imaging detection in multiple directions and accident point detection in different directions without adjusting the posture of the drone. The operation is simple and convenient, and the use is flexible. It can well realize the detection of the conditions of different accident points by directly adjusting the direction of the imaging device, thereby achieving the purpose of quickly and conveniently observing and detecting hazardous gas leakage accident points.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] The accuracy of determining the location of the leak through unmanned vehicle and drone inspections depends on the frequency of inspections. If the frequency is low, the location of the leak will be discovered untimely and inaccurately, resulting in untimely elimination of hidden dangers and affecting gas safety.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The embodiments of the present disclosure provide a method and device for locating gas leaks, and a computer-readable storage medium, so as to timely and accurately predict the location of the leak point, thereby eliminating safety hazards in a timely manner.

[0009] In some embodiments, the method includes: obtaining real-time manhole gas diffusion trend data monitored by a gas sensor in the manhole; performing a three-dimensional CFD simulation of the gas in the soil according to the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of gas in the soil after a gas pipeline leak, to obtain simulation data; using the gas diffusion trend data at different positions around the same leakage point in the data set as input and the leakage point position as output to train an LSTM (Long Short-Term Memory) network; obtaining a predicted leakage point position according to the real-time manhole gas diffusion trend data and the trained LSTM network; wherein the trained LSTM (Long Short-Term Memory) network is generated by training the LSTM network with the gas diffusion trend data at different positions around the same leakage point in the data set as input and the leakage point position as output; the data set is obtained by mixing simulation data and real data; the simulation data is obtained according to the CFD (Computational Fluid Dynamics, computational fluid dynamics) manhole soil simulation parameters and the physical model of gas diffusion in the soil after gas pipeline leakage are obtained by three-dimensional CFD simulation of gas diffusion in the soil.

[0010] Optionally, based on the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of gas in the soil after a gas pipeline leak, a three-dimensional CFD simulation of the gas in the soil is performed to obtain simulation data, including: gridding the physical model of the diffusion of gas in the soil after a gas pipeline leak to obtain a grid model; setting boundary conditions for the grid model using the CFD manhole soil parameters of the target area; simulating the diffusion of gas in the soil using the grid model with boundary conditions to obtain simulation results; and preprocessing the simulation results to obtain simulation data.

[0011] Optionally, the CFD manhole soil simulation parameters of the target area include: leakage point location, and / or soil porosity, and / or average particle diameter, and / or viscous resistance coefficient, and / or inertial resistance coefficient, and / or leakage flow, and / or boundary of soil layer; wherein, viscous resistance and inertial resistance are determined by soil porosity and average particle diameter; leakage flow is determined by pipeline operating pressure, leakage hole diameter, ambient temperature and ambient pressure.

[0012] Optionally, determine the viscous drag coefficient based on soil porosity and average particle diameter, including: Calculate ;in, α is the viscous drag coefficient, D p is the soil porosity, is the average particle diameter.

[0013] Optionally, in case the soil type is loam, D p The value of can be 0.43, The value can be 0.05 mm.

[0014] Optionally, the inertial drag coefficient is determined based on the soil porosity and average particle diameter, including: calculation ;in, C 2 is the inertial drag coefficient, D p is the soil porosity, is the average particle diameter.

[0015] Optionally, the leakage flow rate is determined based on the pipeline operating pressure, the leakage hole diameter, the ambient temperature and the ambient pressure, including: calculating Q m = C d × A × P L ×√{[2× k / ( k -1)]×[ M × k / ( R × T L )]×[( P E / P L ) 2 / k -( P E / P L ) (k+1) / k ]};in, Q m is the leakage flow, k is the gas adiabatic coefficient, T L is the ambient temperature before the gas leak, R is the gas constant, P L For environmental pressure, C d is the leakage hole coefficient, M is the molar mass of the gas, A is the leakage hole area, P E The operating pressure of the pipeline.

[0016] Optionally, Q m The unit is kilograms per second. kThe value of can be 1.334. R The value of can be 8.314. P L The value of can be one atmosphere of pressure. C d It is determined according to the shape of the leakage hole. M The unit is kg / mole. A The unit can be square meters. P E The unit can be Pa or MPa.

[0017] Specifically, the leakage hole shape is determined C d , including: in the case where the leakage hole is circular, C d = C d1 In the case of a triangular leak hole, C d = C d2 In the case of a rectangular leak hole, C d = C d3 .in, C d1 > C d2 > C d3 More specifically, C d1 The value of can be 1.00, C d2 The value of can be 0.95, C d3 The value of can be 0.90.

[0018] Optionally, the simulation results are preprocessed to obtain simulation data, including: extracting gas diffusion data at different locations around the same leakage point from the simulation results to form diffusion trend graph data; cleaning the diffusion trend graph data to remove outliers and noise to obtain clean data; normalizing or standardizing the clean data to obtain simulation data.

[0019] Optionally, the gas diffusion data includes: gas mole fraction and diffusion velocity.

[0020] Optionally, obtaining a data set by mixing simulated data and real data includes: mixing simulated data and real data to obtain a data set; dividing the data set into a training set, a test set, and a validation set, so that the training set, the test set, and the validation set all contain simulated data and real data.

[0021] Optionally, the predicted leakage point location is obtained based on the real-time gas diffusion trend data and the trained LSTM network, including: inputting multiple real-time manhole gas diffusion trend data into the trained LSTM network to obtain predicted leakage data; and using the GIS system to present the predicted leakage data as a leakage point map.

[0022] In some embodiments, the device includes: a data acquisition module, configured to obtain real-time manhole gas diffusion trend data monitored by a gas sensor in the manhole; a prediction module, configured to obtain a predicted leakage point location based on the real-time gas diffusion trend data and a trained LSTM network; wherein the trained LSTM network is generated by training the LSTM network with the gas diffusion trend data at different locations around the same leakage point in the data set as input and the leakage point location as output; the data set is obtained by mixing simulated data and real data; the simulated data is obtained by performing a three-dimensional CFD simulation of the diffusion of gas in the soil based on the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of gas in the soil after a gas pipeline leak.

[0023] In some embodiments, the device includes a processor and a memory storing program instructions, and the processor is configured to execute the method for locating a gas leak when running the program instructions.

[0024] In some embodiments, the server includes: a server body; and the device for locating gas leaks is installed on the server body.

[0025] In some embodiments, the computer-readable storage medium stores program instructions, and when the program instructions are executed, the computer executes the method for locating a gas leak.

[0026] The method and device for gas leak location and computer-readable storage medium provided in the embodiments of the present disclosure can achieve the following technical effects:

[0027] Through the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of gas in the soil after the gas pipeline leaks, a three-dimensional CFD simulation is carried out, which is conducive to obtaining more sufficient and higher-quality simulation data of gas leakage. Then the simulated data and real data are mixed to obtain a data set, which is conducive to improving the generalization ability of the LSTM network and making it accurate in the simulated environment and the real environment. Using the gas diffusion trend data at different locations around the same leak point as input and the leak point location as output to train the LSTM network is conducive to capturing the long-term dependencies in the time series, so as to more accurately process the manhole gas diffusion trend data. The real-time manhole gas diffusion trend data is detected by the gas sensor in the manhole, and the detection frequency is higher than that of drones or unmanned vehicles, which is conducive to obtaining real-time manhole gas diffusion trend data in a more timely manner. Inputting the manhole gas diffusion trend data into the LSTM network is conducive to timely and accurate prediction of the leak point location. In this way, it is conducive to improving the accuracy and timeliness of gas leak point positioning and timely eliminating the safety hazards of gas leakage.

[0028] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0030] Figure 1 is a schematic diagram of a method for locating a gas leak provided by an embodiment of the present disclosure;

[0031] Figure 2 A set of gas diffusion trend diagrams at different positions under two working conditions provided by an embodiment of the present disclosure;

[0032] Figure 3 A set of gas diffusion trend diagrams under different porosity conditions at different positions provided by an embodiment of the present disclosure;

[0033] Figure 4 is a schematic diagram of another method for locating a gas leak provided by an embodiment of the present disclosure;

[0034] Figure 5 is a schematic diagram of a device for locating a gas leak provided by an embodiment of the present disclosure;

[0035] Figure 6 is a schematic diagram of another device for locating gas leaks provided by an embodiment of the present disclosure;

[0036] Figure 7It is a schematic diagram of a server provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0037] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0038] The terms "first", "second", etc. in the description of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so as to describe the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0039] Unless otherwise stated, the term "plurality" means two or more.

[0040] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0041] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0042] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0043] The embodiment of the present disclosure provides a server, and the server and the gas sensor in the manhole can communicate with each other. The gas sensor is used to detect the real-time manhole gas diffusion trend data in the manhole.

[0044] Combination Figure 1 As shown, the embodiment of the present disclosure provides a method for locating a gas leak, comprising:

[0045] S101, the server obtains real-time manhole gas diffusion trend data monitored by the gas sensor in the manhole.

[0046] S102, the server obtains the predicted leakage point location based on the real-time manhole gas diffusion trend data and the trained LSTM network.

[0047] Among them, the trained LSTM network is generated by training the gas diffusion trend data of different locations around the same leakage point in the data set as input and the leakage point location as output; the data set is obtained by mixing simulated data and real data; the simulated data is obtained by three-dimensional CFD simulation of gas diffusion in soil based on the CFD manhole soil simulation parameters of the target area and the physical model of gas diffusion in soil after gas pipeline leakage.

[0048] By adopting the method for gas leak location provided by the embodiment of the present disclosure, a three-dimensional CFD simulation is performed through the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of gas in the soil after the gas pipeline leaks, which is conducive to obtaining more sufficient and higher quality simulation data of gas leaks. Then the simulated data and the real data are mixed to obtain a data set, which is conducive to improving the generalization ability of the LSTM network and making it accurately predict in the simulated environment and the real environment. Using the gas diffusion trend data of different positions around the same leakage point as input and the leakage point position as output, the LSTM network is trained, which is conducive to capturing the long-term dependency in the time series, so as to more accurately process the manhole gas diffusion trend data. The real-time manhole gas diffusion trend data is detected by the gas sensor in the manhole, and the detection frequency is higher than that of the drone or unmanned vehicle, which is conducive to more timely acquisition of real-time manhole gas diffusion trend data. The manhole gas diffusion trend data is input into the LSTM network, which is conducive to timely and accurate prediction of the leakage point location. In this way, it is conducive to improving the accuracy and timeliness of gas leakage point location and timely eliminating the safety hazards of gas leakage.

[0049] It should be noted that the target area refers to the geographical area where the gas sensor that can communicate with the server is located, and can also refer to the area where the user wants to locate the gas leak. The physical model of the gas diffusion in the soil after the gas pipeline leaks is obtained by modeling with Fusion 360 and CAD software.

[0050] Optionally, the server performs a three-dimensional CFD simulation of the gas in the soil according to the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of the gas in the soil after the gas pipeline leaks, and obtains simulation data, including: the server grids the physical model of the diffusion of the gas in the soil after the gas pipeline leaks to obtain a grid model. The server sets boundary conditions for the grid model using the CFD manhole soil parameters of the target area. The server simulates the diffusion of the gas in the soil using the grid model with boundary conditions to obtain simulation results. The server preprocesses the simulation results to obtain simulation data.

[0051] In this way, the grid model decomposes the complex physical model of gas diffusion in soil after gas pipeline leakage into multiple small units, each of which has specific physical properties and boundary conditions. This division improves the accuracy and controllability of the simulation process and provides a basis for the accuracy of the simulation results. The boundary conditions define the external environment of the simulation area that has a direct impact on the diffusion speed and direction of the gas, improving the reality and reliability of the simulation. Preprocessing is conducive to converting the original simulation results into a format suitable for further analysis and LSTM network training of gas pipeline diffusion in soil after leakage, improving the accuracy and efficiency of the LSTM network.

[0052] Optionally, the CFD manhole soil simulation parameters of the target area include: leakage point location, and / or soil porosity, and / or average particle diameter, and / or viscous resistance coefficient, and / or inertial resistance coefficient, and / or leakage flow, and / or soil layer boundary. Among them, viscous resistance and inertial resistance are determined by soil porosity and average particle diameter. The leakage flow is determined by pipeline operating pressure, leakage hole diameter, ambient temperature and ambient pressure.

[0053] In this way, soil porosity affects the diffusion speed and path of gas in the soil, which is conducive to more accurate prediction of gas diffusion behavior. The average particle diameter determines the permeability of the soil and affects the flow and diffusion of gas. The viscosity resistance coefficient is determined by the soil porosity and the average particle diameter, which affects the flow resistance of gas in the soil, which is conducive to predicting the diffusion speed of gas under different soil conditions. The inertial resistance coefficient is determined by the soil porosity and the average particle diameter, which affects the inertia of gas movement in the soil, which is conducive to simulating the behavior of gas under fast flow conditions. The leakage flow is determined by the pipeline operating pressure, the diameter of the leakage hole, the ambient temperature and the ambient pressure, which is conducive to accurately simulating the initial intensity and diffusion range of gas diffusion. The boundary conditions of the soil layer define the external environment of the simulation area, such as soil type and groundwater level, which is conducive to simulating the limiting effect of the soil layer on gas diffusion. In this way, it is conducive to building a comprehensive soil simulation environment, making the simulation results closer to the actual situation.

[0054] Optionally, the server determines a viscous resistance coefficient based on the soil porosity and the average particle diameter, including: the server calculates ;in, α is the viscous drag coefficient, D p is the soil porosity, is the average particle diameter.

[0055] Specifically, in the case where the soil type is loam, D p The value of can be 0.43, The value can be 0.05 mm.

[0056] In this way, determining the viscous resistance coefficient based on soil porosity and average particle diameter is helpful in reflecting the flow resistance of gas in the soil and in predicting the diffusion rate of gas under different soil conditions.

[0057] Optionally, the server determines the inertial drag coefficient based on the soil porosity and the average particle diameter, including: the server calculates ;in, C 2 is the inertial drag coefficient, D p is the soil porosity, is the average particle diameter.

[0058] In this way, determining the inertial resistance coefficient based on the soil porosity and the average particle diameter is helpful in reflecting the movement inertia of the gas in the soil and simulating the behavior of the gas under fast flow conditions.

[0059] Optionally, the server determines the leakage flow rate according to the pipeline operating pressure, the leakage hole diameter, the ambient temperature and the ambient pressure, including: the server calculates Q m = C d × A × P L ×√{[2× k / ( k -1)]×[ M × k / ( R × T L )]×[( P E / P L ) 2 / k -( P E / P L ) (k+1) / k ]};in, Q m is the leakage flow, k is the gas adiabatic coefficient, T L is the ambient temperature before the gas leak, R is the gas constant, P L For environmental pressure, C d is the leakage hole coefficient, M is the molar mass of the gas, A is the leakage hole area, P EThe operating pressure of the pipeline.

[0060] Specifically, Q m The unit is kilograms per second. k The value of can be 1.334. R The value of can be 8.314. P L The value of can be one atmosphere of pressure. C d It is determined according to the shape of the leakage hole. M The unit is kg / mole. A The unit can be square meters. P E The unit can be Pa or MPa.

[0061] Taking the first working condition ( P E is 0.152 MPa, the diameter of the leak hole is 20 mm) and the second working condition ( P E For example, the first leakage flow rate calculated under the first working condition is 3.71, and the second leakage flow rate calculated under the second working condition is 3.74. The gas diffusion trend diagram (horizontally time, vertically gas molar mass) at different positions (0.5m, 1.0m, 1.5m, 2.0m, 2.5m, 3.0m, 3.5m and 4.0m from the leakage point) under the two working conditions is as follows: Figure 2 As shown, it can be seen that even if the pipeline operating pressure and the leakage hole diameter are different, if the leakage flow rate is the same, their diffusion trends are similar.

[0062] In this way, the leakage flow rate is jointly determined according to the pipeline operating pressure, leakage hole diameter, ambient temperature and ambient pressure, which is conducive to accurate simulation for predicting the initial intensity and diffusion range of gas diffusion.

[0063] Specifically, the server determines the leakage hole shape according to C d , including: in the case where the leakage hole is circular, C d = C d1 In the case of a triangular leak hole, C d = C d2 In the case of a rectangular leak hole, C d = C d3 .in, C d1 >C d2 > C d3 More specifically, C d1 The value of can be 1.00, C d2 The value of can be 0.95, C d3 The value of can be 0.90.

[0064] In this way, since the flow characteristics of a circular leakage hole are higher and the resistance is usually smaller, the corresponding hole leakage coefficient is larger. The flow characteristics of a triangular leakage hole are between those of a circle and a rectangle, so the resistance is between the resistances corresponding to the circle and the rectangle, and the corresponding hole leakage coefficient is also between the leakage coefficients of the circle and the rectangle. The rectangular leakage hole has the largest flow resistance due to the existence of its corners, so the corresponding hole leakage coefficient is the smallest. This is conducive to more accurate determination of the leakage flow, thereby accurately simulating the initial intensity and diffusion range for predicting gas diffusion.

[0065] Optionally, the server preprocesses the simulation results to obtain simulation data, including: the server extracts gas diffusion data at different locations around the same leakage point from the simulation results to form diffusion trend map data. The server cleans the diffusion trend map data to remove outliers and noise to obtain clean data. The server normalizes or standardizes the clean data to obtain simulation data. Specifically, the server extracts gas diffusion data at different locations around the same leakage point from the simulation results to form diffusion trend map data, which can use ParaView software.

[0066] Among them, the diffusion trend graph data can form a diffusion trend graph, such as Figure 3 As shown, the embodiment disclosed in the present application provides a gas diffusion trend diagram (the horizontal axis is time, and the vertical axis is gas molar mass) under different porosity conditions (the porosity is 0.25, 0.43 and 0.6) at different positions (0.5 m, 1.0 m, 1.5 m, 2.0 m, 2.5 m, 3.0 m, 3.5 m and 4.0 m away from the leakage point).

[0067] In this way, by extracting the gas diffusion data, a diffusion trend graph showing the changes in gas concentration over time and space can be formed, providing an intuitive view for further analysis of the gas diffusion pattern.

[0068] Optionally, the gas diffusion data includes: gas mole fraction and diffusion velocity.

[0069] This will help to form a more accurate gas diffusion trend diagram.

[0070] Optionally, the server obtains the data set by mixing the simulated data and the real data, including: the server mixes the simulated data and the real data to obtain the data set. The server divides the data set into a training set, a test set, and a validation set, so that the training set, the test set, and the validation set all contain the simulated data and the real data.

[0071] In this way, the division of data sets allows the LSTM network to use different data sets for training, tuning, and evaluation, and the training set, test set, and validation set all contain simulated data and real data, ensuring that the LSTM network learns the transition from simulation to actual application and improves the adaptability of the LSTM network to real data. This is conducive to improving the generalization ability and robustness of the LSTM network.

[0072] Optionally, the server obtains the predicted leakage point location according to the real-time gas diffusion trend data and the trained LSTM network, including: the server inputs a plurality of real-time manhole gas diffusion trend data into the trained LSTM network to obtain the predicted leakage data. The server uses the GIS system to present the predicted leakage data as a leakage point map.

[0073] In this way, inputting the manhole gas diffusion trend data into the LSTM network is conducive to timely and accurate prediction of the location of the leak point. The prediction results are visualized in the form of a map in a timely manner, allowing relevant personnel to quickly understand the geographical location and diffusion of the leak point, greatly shortening the time from detection to response and improving the speed of emergency response.

[0074] Combination Figure 4 As shown, the embodiment of the present disclosure provides another method for locating a gas leak, comprising:

[0075] S401, the server meshes the physical model of the diffusion of the gas pipeline in the soil to obtain a meshed model.

[0076] S402, the server sets boundary conditions for the grid model using the CFD manhole soil parameters of the target area.

[0077] S403, the server simulates the diffusion of gas in the soil using a grid model with boundary conditions to obtain a simulation result.

[0078] S404, the server preprocesses the simulation results to obtain simulation data.

[0079] S405, the server obtains a data set by mixing the simulated data and the real data.

[0080] S406, the server uses the gas diffusion trend data at different locations around the same leakage point in the data set as input and the leakage point location as output to train the LSTM network.

[0081] S407, the server obtains the predicted leakage point location based on the real-time manhole gas diffusion trend data and the trained LSTM network.

[0082] Among them, the real-time manhole gas diffusion trend data is obtained by the gas sensor in the manhole.

[0083] Using the method for gas leak location provided by the embodiment of the present disclosure, the grid model decomposes the physical model of the diffusion of gas in the soil after the complex gas pipeline leaks into multiple small units, each unit has specific physical properties and boundary conditions, and such division improves the accuracy and controllability of the simulation process, providing a basis for the accuracy of the simulation results. The boundary conditions define the external environment of the simulation area that has a direct impact on the diffusion speed and direction of the gas, improving the reality and reliability of the simulation. Preprocessing is conducive to converting the original simulation results into a format suitable for further analysis and LSTM network training of the diffusion in the soil after the gas pipeline leaks, improving the accuracy and efficiency of LSTM network training. Then, the simulated data and the real data are mixed to obtain a data set, which is conducive to improving the generalization ability of the LSTM network and making it accurately predict in the simulated environment and the real environment. Using the gas diffusion trend data at different locations around the same leak point as input and the leak point location as output, the LSTM network is trained, which is conducive to capturing the long-term dependencies in the time series, thereby more accurately processing the gas diffusion trend data of the manhole. The gas sensor in the manhole detects the real-time manhole gas diffusion trend data, and the detection frequency is higher than that of drones or unmanned vehicles, which is conducive to obtaining real-time manhole gas diffusion trend data in a more timely manner. Inputting the manhole gas diffusion trend data into the LSTM network is conducive to timely and accurate prediction of the leakage point location. This is conducive to improving the accuracy and timeliness of gas leakage point positioning and timely eliminating the safety hazards of gas leakage.

[0084] Combination Figure 5 As shown, an embodiment of the present disclosure provides a device 200 for locating gas leaks, including a data acquisition module 501 and a prediction module 502. The data acquisition module 501 is configured to obtain real-time manhole gas diffusion trend data monitored by a gas sensor in the manhole; the prediction module 502 is configured to obtain a predicted leakage point location based on the real-time gas diffusion trend data and the trained LSTM network. Among them, the trained LSTM network is generated by training the LSTM network with the gas diffusion trend data of different positions around the same leakage point in the data set as input and the leakage point position as output; the data set is obtained by mixing simulated data and real data; the simulated data is obtained by performing a three-dimensional CFD simulation of the diffusion of gas in the soil based on the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of gas in the soil after the gas pipeline leaks.

[0085] By using the device 200 for gas leak location provided by the embodiment of the present disclosure, a three-dimensional CFD simulation is performed through the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of gas in the soil after the gas pipeline leaks, which is conducive to obtaining more sufficient and higher quality simulation data of gas leaks. Then the simulated data and the real data are mixed to obtain a data set, which is conducive to improving the generalization ability of the LSTM network and enabling it to accurately predict in the simulated environment and the real environment. Using the gas diffusion trend data of different positions around the same leakage point as input and the leakage point position as output to train the LSTM network is conducive to capturing the long-term dependency in the time series, so as to more accurately process the manhole gas diffusion trend data. The real-time manhole gas diffusion trend data is detected by the gas sensor in the manhole, and the detection frequency is higher than that of the drone or unmanned vehicle, which is conducive to more timely acquisition of real-time manhole gas diffusion trend data. The manhole gas diffusion trend data is input into the LSTM network, which is conducive to timely and accurate prediction of the leakage point location. In this way, it is conducive to improving the accuracy and timeliness of gas leakage point location and timely eliminating the safety hazards of gas leakage.

[0086] Combination Figure 6 As shown, the embodiment of the present disclosure provides a device 70 for gas leak location, including a processor 700 and a memory 701. Optionally, the device 70 may also include a communication interface 702 and a bus 703. The processor 700, the communication interface 702, and the memory 701 may communicate with each other through the bus 703. The communication interface 702 may be used for information transmission. The processor 700 may call the logic instructions in the memory 701 to execute the method for gas leak location of the above embodiment.

[0087] In addition, the logic instructions in the memory 701 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0088] The memory 701 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 700 executes functional applications and data processing by running the program instructions / modules stored in the memory 701, that is, implementing the method for gas leak locating in the above embodiment.

[0089] The memory 701 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 701 may include a high-speed random access memory and may also include a non-volatile memory.

[0090] Combination Figure 7 As shown, an embodiment of the present disclosure provides a server 100, comprising: a server body, and the above-mentioned device 200 (70) for locating a gas leak. The device 200 (70) for locating a gas leak is installed on the server body. The installation relationship described here is not limited to placement inside the server body, but also includes installation connections with other components of the server 100, including but not limited to physical connections, electrical connections or signal transmission connections. It can be understood by those skilled in the art that the device 200 (70) for locating a gas leak can be adapted to a feasible server body, thereby realizing other feasible embodiments.

[0091] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned method for locating a gas leak.

[0092] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0093] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method or device including the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0094] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0095] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0096] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for locating a gas leak, It is characterized in that include: Obtain real-time manhole gas diffusion trend data monitored by gas sensors in the manhole; According to the real-time manhole gas diffusion trend data and the trained LSTM network, the predicted leakage point location is obtained; The trained LSTM network is generated by taking the gas diffusion trend data at different locations around the same leakage point in the data set as input and the leakage point location as output; the data set is obtained by mixing simulated data and real data; the simulated data is obtained by performing three-dimensional CFD simulation of gas diffusion in soil based on the CFD manhole soil simulation parameters of the target area and the physical model of gas diffusion in soil after gas pipeline leakage; The method performs a three-dimensional CFD simulation of gas in the soil according to the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of gas in the soil after the gas pipeline leaks, and obtains simulation data, including: gridding the physical model of the diffusion of gas in the soil after the gas pipeline leaks to obtain a grid model; setting boundary conditions for the grid model using the CFD manhole soil parameters of the target area; simulating the diffusion of gas in the soil using the grid model with boundary conditions to obtain simulation results; and preprocessing the simulation results to obtain simulation data; The simulation results are preprocessed to obtain simulation data, including: extracting gas diffusion data at different positions around the same leakage point from the simulation results to form diffusion trend graph data; cleaning the diffusion trend graph data to remove outliers and noise to obtain clean data; normalizing or standardizing the clean data to obtain simulation data; wherein the diffusion trend graph data can form a diffusion trend graph; the gas diffusion data includes: gas mole fraction and diffusion velocity.

2. The method according to claim 1, It is characterized in that The CFD manhole soil simulation parameters of the target area include: leakage point location, and / or soil porosity, and / or average particle diameter, and / or viscous resistance coefficient, and / or inertial resistance coefficient, and / or leakage flow, and / or boundary of soil layer; wherein, viscous resistance and inertial resistance are determined by soil porosity and average particle diameter; leakage flow is determined by pipeline operating pressure, leakage hole diameter, ambient temperature and ambient pressure.

3. The method according to claim 1 or 2, It is characterized in that The data set is obtained by mixing simulated data and real data, including: Mix the simulated data and the real data to get the data set; The data set is divided into training set, test set, and validation set, so that the training set, test set, and validation set all contain simulated data and real data.

4. The method according to claim 1 or 2, It is characterized in that Based on the real-time gas diffusion trend data and the trained LSTM network, the predicted leakage point location is obtained, including: Input multiple real-time manhole gas diffusion trend data into the trained LSTM network to obtain predicted leakage data; The GIS system is used to present the predicted leakage data as a leakage point map.

5. A device for locating gas leaks, It is characterized in that include: A data acquisition module is configured to obtain real-time manhole gas diffusion trend data monitored by a gas sensor in the manhole; The prediction module is configured to obtain the predicted leakage point location based on the real-time gas diffusion trend data and the trained LSTM network; The trained LSTM network is generated by taking the gas diffusion trend data at different locations around the same leakage point in the data set as input and the leakage point location as output; the data set is obtained by mixing simulated data and real data; the simulated data is obtained by performing three-dimensional CFD simulation of gas diffusion in soil based on the CFD manhole soil simulation parameters of the target area and the physical model of gas diffusion in soil after gas pipeline leakage; The method performs a three-dimensional CFD simulation of gas in the soil according to the CFD manhole soil simulation parameters of the target area and the physical model of the diffusion of gas in the soil after the gas pipeline leaks, and obtains simulation data, including: gridding the physical model of the diffusion of gas in the soil after the gas pipeline leaks to obtain a grid model; setting boundary conditions for the grid model using the CFD manhole soil parameters of the target area; simulating the diffusion of gas in the soil using the grid model with boundary conditions to obtain simulation results; and preprocessing the simulation results to obtain simulation data; The simulation results are preprocessed to obtain simulation data, including: extracting gas diffusion data at different positions around the same leakage point from the simulation results to form diffusion trend graph data; cleaning the diffusion trend graph data to remove outliers and noise to obtain clean data; normalizing or standardizing the clean data to obtain simulation data; wherein the diffusion trend graph data can form a diffusion trend graph; the gas diffusion data includes: gas mole fraction and diffusion velocity.

6. A device for locating a gas leak, comprising a processor and a memory storing program instructions, It is characterized in that The processor is configured to execute the method for gas leak locating according to any one of claims 1 to 4 when running the program instructions.

7. A computer-readable storage medium storing program instructions, It is characterized in that When the program instructions are executed, the computer is used to execute the method for locating gas leaks according to any one of claims 1 to 4.

Images