Gas leakage monitoring method and equipment
By establishing a gas leak simulation model and infrared spectral video imaging, the problem of low accuracy in existing gas leak detection models has been solved, achieving efficient and low-cost gas leak detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NORTH CHINA INSTITUTE OF SCIENCE & TECHNOLOGY (NATIONAL SAFETY TRAINING CENTER OF COAL MINES)
- Filing Date
- 2025-12-23
- Publication Date
- 2026-04-10
AI Technical Summary
Existing gas leak detection technology models based on infrared spectral imaging have low accuracy, requiring a large amount of experimental data, resulting in high time and economic costs, and making it difficult to meet the needs of model training.
By establishing a gas leakage simulation model, gas leakage simulations are performed under different simulation parameters to obtain gas concentration values and spatial characteristics. A gas leakage detection model is then established, and gas leakage detection is achieved using infrared spectral video imaging, reducing the need for experimental data.
It reduces the time and economic cost of model training, improves the accuracy and efficiency of gas leak detection, and meets the needs of model training.
Smart Images
Figure CN121834603A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of gas leak detection technology, and more specifically to a gas leak monitoring method and equipment. Background Technology
[0002] Hazardous gases, if leaked during production, transportation, and storage, can cause fires and explosions, posing serious threats to human health, production safety, and the ecological environment. Statistics show that 60% of gas leak accidents are caused by delayed warnings; therefore, timely detection and early warning of gas leaks are a core requirement for industrial safety.
[0003] Existing gas leak detection technologies are mainly based on electrochemical sensing and optical detection. Electrochemical sensing has significant limitations due to the need for a large number of sensors and its poor detection performance. Optical detection, on the other hand, has become the mainstream detection technology due to its advantages of imaging capabilities, fast response speed, and long detection distance. Infrared spectral video imaging, as an optical detection technology, has been widely used due to its ability to detect a wide variety of gases and its low susceptibility to temperature changes.
[0004] However, existing models for gas leak detection based on infrared spectral imaging have low accuracy. To improve accuracy, a large amount of experimental data is required, resulting in high time and economic costs, which makes it difficult to meet the needs of model training. Summary of the Invention
[0005] The purpose of this invention is to provide a gas leak monitoring method and device to reduce the time and economic cost of model training.
[0006] To achieve the above objectives, in a first aspect, embodiments of the present invention provide a gas leak monitoring method, the method comprising: performing gas leak simulations under different simulation parameters based on a pre-established gas leak simulation model to obtain gas concentration values corresponding to different simulation parameters; obtaining spatial characteristics of the gas corresponding to each simulation parameter based on the gas concentration values; obtaining a first spatial characteristic curve corresponding to each simulation parameter based on the spatial characteristics; and establishing a gas leak detection model based on the first spatial characteristic curve for monitoring gas leaks.
[0007] Optionally, the gas leakage simulation model is built based on ANSYS Fluent. The gas leakage simulation model includes a first leakage pipe and a cubic container. The first leakage pipe is used to release liquefied petroleum gas into the cubic container based on simulation parameters.
[0008] Optionally, based on a pre-established gas leakage simulation model, gas leakage simulation is performed under different simulation parameters to obtain the gas concentration values corresponding to different simulation parameters, including: establishing a coordinate system in the cube container, with the XY plane perpendicular to the first leakage pipe; setting a node at preset distances along the X, Y, and Z axes in the cube container, dividing the entire cube container into a spatial field composed of multiple grids, with each grid corresponding to a node; and for each simulation parameter, releasing liquefied petroleum gas into the cube container within a preset time, and obtaining the molar concentration of liquefied petroleum gas at each node based on a preset frequency during the release process.
[0009] Optionally, based on the gas concentration value, the spatial characteristics of the gas corresponding to each simulation parameter are obtained, including performing the following processing on the molar concentration of liquefied petroleum gas at each node obtained at each time point: for the same For each node, calculate the integral value of its molar concentration along the Z-axis using the following formula:
[0010] in, For the same The integral value corresponding to the node. For nodes molar concentration, The total number of nodes on the Z-axis is given; the highest integral value is selected as the highest concentration value of the gas cloud, and the maximum concentration value corresponding to the edge of the gas cloud is found in the four directions of the node corresponding to the highest integral value; and the slope between the highest integral value and the maximum concentration value corresponding to the four edges of the gas cloud is calculated respectively, and the slope is the spatial characteristic of the simulation parameter at the time point.
[0011] Optionally, based on the spatial characteristics, the first spatial characteristic curve corresponding to each simulation parameter is obtained by performing the following processing for each simulation parameter: based on the spatial characteristics at each time point in each direction, a slope-time curve is established in each direction to obtain four slope-time curves, which are the first spatial characteristic curves corresponding to the simulation parameter.
[0012] Optionally, the simulation parameters include leakage rate, leak size, gas type, ambient wind field, obstacle arrangement and / or leak location, and different values of the simulation parameters correspond to gas leak tags or false alarm interference tags.
[0013] Optionally, establishing a gas leak detection model based on the first spatial feature curve includes: establishing a training set based on the first spatial feature curves obtained under all simulation parameters, wherein the labels of the first spatial feature curves are gas leak or false alarm interference; extracting curve features corresponding to each of the first spatial feature curves, wherein the curve features include the curve mean, standard deviation and / or curve area; and training a classification model based on the curve features to obtain the gas leak detection model.
[0014] Optionally, the method further includes: constructing an experimental platform, the experimental platform including a second leakage pipe and a blank background; releasing liquefied petroleum gas into the blank background through the second leakage pipe within a preset time to simulate the gas leakage process under different simulation parameters; during the release process, capturing images of the leakage location using an infrared spectral camera at a fixed position to obtain first video data corresponding to different simulation parameters; obtaining second spatial feature curves corresponding to each simulation parameter based on the first video data; and comparing and analyzing the first spatial feature curves and the second spatial feature curves under the same simulation parameters to obtain a consistency comparison result.
[0015] Optionally, monitoring gas leaks based on the gas leak detection model includes: acquiring second video data in real time using an infrared spectral camera; obtaining a third spatial feature curve based on the second video data; and inputting the third spatial feature curve into the gas leak simulation model to obtain the monitoring results of the gas leak, wherein the monitoring results include gas leaks or false alarm interference.
[0016] On the other hand, embodiments of the present invention provide a device for gas leak monitoring, the device including a memory and a processor, the processor being used to run a program, wherein the program, when run, is used to execute any of the methods described above.
[0017] The technical solution proposed in this invention is based on the correspondence between image pixels and gas cloud concentration, and the premise that the changing trends of different concentrations are consistent with the changing trends of different pixels. When establishing the gas leak detection model, only simulation data is used. However, in actual gas leak monitoring, infrared spectral video imaging is used to detect gas leaks. In this way, when building the dataset, it is not necessary to conduct extensive experiments to obtain data. Only a gas leak simulation model needs to be established, and the simulation parameters adjusted. A large amount of simulation data can be quickly obtained under different simulation parameters, greatly reducing the time and economic costs and better meeting the needs of model training.
[0018] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description
[0019] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic flowchart of the gas leak monitoring method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of the device provided in an embodiment of the present invention; Figure 3 This is a schematic flowchart of another gas leak monitoring method provided in an embodiment of the present invention.
[0020] Explanation of reference numerals in the attached figures 101 Processor 102 Memory 103 bus 10 devices Detailed Implementation The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.
[0021] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.
[0022] Figure 1 This is a schematic flowchart of the gas leak monitoring method provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes the following steps S1 to S4.
[0023] Step S1: Based on the pre-established gas leakage simulation model, perform gas leakage simulation under different simulation parameters to obtain the gas concentration values corresponding to different simulation parameters.
[0024] Step S2: Based on the concentration value of the gas, obtain the spatial characteristics of the gas corresponding to each simulation parameter.
[0025] Step S3: Based on the spatial features, obtain the first spatial feature curves corresponding to each simulation parameter.
[0026] Step S4: Based on the first spatial characteristic curve, establish a gas leak detection model for monitoring gas leaks.
[0027] Infrared spectral video imaging exhibits selective absorption of characteristic gases in the infrared band. When a leaking gas enters the field of view, it attenuates the background infrared radiation, causing changes in the image brightness. Therefore, the brightness differences among pixels in the image contain information about the spatial distribution of the gas cloud. To describe this spatial distribution characteristic, the concept of a "concentration field" is introduced to characterize the relative concentration distribution of the gas cloud within the imaging area. It is evident that there is a correspondence between image pixels and gas cloud concentration; the trends of different concentrations are consistent with the trends of different pixels. Based on this consistent trend, the method proposed in this invention uses only simulation data when establishing the gas leak detection model. In actual gas leak monitoring, however, detection can be achieved through infrared spectral video imaging. This approach eliminates the need for extensive experiments to acquire data when building the dataset. By establishing a gas leak simulation model and adjusting the simulation parameters, a large amount of simulation data can be quickly obtained under different simulation parameters, significantly reducing time and economic costs and better meeting the needs of model training.
[0028] Furthermore, the gas leakage simulation model is built based on ANSYS Fluent. The model includes a first leakage pipe and a cubic container. The first leakage pipe is used to release liquefied petroleum gas into the cubic container based on simulation parameters. When building the gas leakage simulation model using ANSYS Fluent, geometric modeling, mesh generation, physical property parameter settings, and boundary condition definitions are set according to actual working conditions. Specific settings will not be elaborated upon in this invention.
[0029] Furthermore, based on a pre-established gas leakage simulation model, gas leakage simulations are performed under different simulation parameters to obtain the gas concentration values corresponding to different simulation parameters, including: establishing a coordinate system in the cube container, with the XY plane perpendicular to the first leakage pipe; setting a node at preset distances along the X, Y, and Z axes in the cube container, dividing the entire cube container into a spatial field composed of multiple grids, with each grid corresponding to a node; and for each simulation parameter, releasing liquefied petroleum gas into the cube container within a preset time, and obtaining the molar concentration of liquefied petroleum gas at each node based on a preset frequency during the release process.
[0030] As an example, by setting nodes along the X, Y, and Z axes, the entire container is divided into a 40×40×40 spatial field. When the simulation parameters are adjusted to change the gas flow rate, multiple simulation parameters correspond to gas flow rates of 0.2 L / min, 0.4 L / min, 0.6 L / min…3 L / min, respectively. For each flow rate, liquefied petroleum gas (LPG) is continuously released into the cubic container for a preset time, such as 5 seconds. During this process, based on a preset frequency, such as every 0.2 seconds, the molar concentration of LPG at each node is obtained, thereby obtaining the simulation data corresponding to each flow rate.
[0031] Furthermore, based on the gas concentration values, the spatial characteristics of the gas corresponding to each simulation parameter are obtained, including performing the following processing on the molar concentration of liquefied petroleum gas at each node obtained at each time point: for the same For each node, calculate the integral value of its molar concentration along the Z-axis using the following formula:
[0032] in, For the same The integral value corresponding to the node. For nodes molar concentration, The total number of nodes on the Z-axis is given; the highest integral value is selected as the highest concentration value of the gas cloud, and the maximum concentration value corresponding to the edge of the gas cloud is found in the four directions of the node corresponding to the highest integral value; and the slope between the highest integral value and the maximum concentration value corresponding to the four edges of the gas cloud is calculated respectively, and the slope is the spatial characteristic of the simulation parameter at the time point.
[0033] As an example, when a cube container is divided into a 40×40×40 spatial field, the total number of nodes on the Z-axis is... The value is 40. When each identical [item] is calculated... When integrating the node values, the maximum value is selected as the highest concentration value of the gas cloud. Using the node corresponding to this highest concentration value as the center, the edge of the gas cloud is searched in four directions along the X and Y axes. For example, when searching for the edge of the gas cloud along the positive X-axis, if the edge is found... Discovered If all integral values on the corresponding Y-axis are 0, then The previous value The corresponding node represents the edge of the gas cloud in that direction. After finding the edge of the gas cloud, the maximum concentration value is located at that edge, and based on the difference between the maximum concentration value and the highest concentration value corresponding to that edge, along with the distance, the slope of the concentration change is calculated, thus obtaining the spatial characteristics.
[0034] Furthermore, based on the spatial characteristics, the first spatial characteristic curve corresponding to each simulation parameter is obtained. This includes performing the following processing for each simulation parameter: based on the spatial characteristics at each time point in each direction, establishing a slope-time curve in each direction, resulting in four slope-time curves, which are the first spatial characteristic curves corresponding to the simulation parameter. To comprehensively reflect the dynamic behavior of gas leakage, a fusion analysis of spatial and temporal characteristics is required. By combining the slope of each simulation parameter in each direction with the acquisition time of the simulation data corresponding to that slope, a slope-time curve in each direction can be obtained.
[0035] Furthermore, the simulation parameters include leakage rate, leak size, gas type, ambient wind field, obstacle arrangement and / or leak location, and different values of the simulation parameters correspond to gas leak tags or false alarm interference tags.
[0036] The leakage rate is used to control the gas flow rate, and the arrangement of obstacles can simulate common disturbances such as people walking and leaves swaying. When the gas flow rate is 0 and common disturbances are present, the acquired data is labeled as false alarm interference. Therefore, Fluent can be used to simulate and generate large-scale, multi-scenario gas leakage concentration field datasets for training and optimizing gas leakage detection models. By systematically changing parameters such as leakage rate, leak size, gas type, ambient wind field, obstacle arrangement, and leak location in Fluent, first-space feature curves of the concentration field containing more scenarios can be quickly generated, thus obtaining large-scale, multi-scenario datasets to meet the training requirements of the model.
[0037] Furthermore, based on the first spatial feature curve, establishing a gas leak detection model includes: establishing a training set based on the first spatial feature curve obtained under all simulation parameters, wherein the label of the first spatial feature curve is gas leak or false alarm interference; extracting curve features corresponding to each of the first spatial feature curves, wherein the curve features include curve mean, standard deviation and / or curve area; and training a classification model based on the curve features to obtain the gas leak detection model.
[0038] In practical implementation, traditional machine learning methods can be used for model training. By constructing gas leak samples under different scenarios and extracting features such as curve mean, standard deviation, and area under the curve, the model learns the diffusion trend of these data concentration field distributions over time, resulting in a classification model used to distinguish between gas leaks and false alarm interference. In some embodiments of the present invention, other curve features can also be extracted, such as fitting features like linear fitting and quadratic polynomial fitting, shape features like the number of inflection points and Gaussian distribution R², and time-series features like DTW and FFT.
[0039] To verify the effectiveness of the method proposed in this invention, a gas leakage experiment was also conducted. Correlation analysis was performed on the simulation data and experimental data to verify the consistency between concentration gradient changes and pixel gradient trends. The verification steps included: constructing an experimental platform comprising a second leakage pipe and a blank background; releasing liquefied petroleum gas into the blank background through the second leakage pipe within a preset time to simulate the gas leakage process under different simulation parameters; during the release process, capturing images of the leakage location using an infrared spectral camera at a fixed position to obtain first video data corresponding to different simulation parameters; obtaining second spatial feature curves corresponding to each simulation parameter based on the first video data; and comparing and analyzing the first spatial feature curves and second spatial feature curves under the same simulation parameters to obtain consistency comparison results.
[0040] To ensure consistency, the gas leakage process on the experimental platform must be simulated under the same conditions as the simulation. Taking varying gas flow rates as an example, the simulation on the experimental platform uses the same flow rates of 0.2 L / min, 0.4 L / min, 0.6 L / min…3 L / min, with each flow rate lasting for 5 seconds. When releasing liquefied petroleum gas into the blank background through a second leakage pipe, the experimental environment must be windless. After capturing the leakage location with an infrared spectral camera at a fixed position and obtaining the first video data, a frame is extracted every 0.2 seconds to construct the same dataset as the simulation.
[0041] After constructing the dataset, the images in the dataset can be preprocessed, including denoising, background subtraction, and normalization, to improve image quality. Then, the grayscale value of each pixel in the processed image is output to a table, obtaining data corresponding to the XY plane in the simulation. For each table, the same processing as in the simulation is performed: the highest grayscale value is selected, and the maximum grayscale value corresponding to the edge of the gas cloud is found in the four directions corresponding to the maximum grayscale value; and the slope between the highest grayscale value and the maximum grayscale value corresponding to the edge of the four gas clouds is calculated respectively. After obtaining the slope, a slope-time curve is established based on the same steps as in the simulation, thus obtaining the second spatial feature curve.
[0042] After obtaining the first spatial characteristic curve of the simulation and the second spatial characteristic curve of the experimental data under the same simulation parameters, a correlation analysis can be performed between the two to establish a concentration-pixel mapping relationship. For example, by placing simulation data and leakage data with the same flow rate together and observing their curves, it can be found that high concentration areas correspond to high pixel value areas, the concentration gradient change is consistent with the pixel gradient trend, and the upward trend over time is also consistent. Therefore, using simulation data instead of experimental data for model training is effective. Furthermore, the curves also show that gas leakage has a fixed diffusion trend; the shape of the gas leak changes over time, and this change follows a certain regularity. Common disturbances such as people walking or leaves swaying do not exhibit this diffusion trend. Therefore, this diffusion trend can be used to distinguish between gas leakage and disturbances.
[0043] Furthermore, monitoring gas leaks based on the gas leak detection model includes: acquiring second video data in real time using an infrared spectral camera; obtaining a third spatial feature curve based on the second video data; and inputting the third spatial feature curve into the gas leak simulation model to obtain the monitoring result of the gas leak, wherein the monitoring result includes gas leaks or false alarm interference. It should be noted that after acquiring the second video data, a frame should be extracted at a preset frequency, for example, every 0.2 seconds, and the extracted image should be preprocessed before obtaining the third spatial feature curve based on the processed image. The method for obtaining the third spatial feature curve is the same as that for the second spatial feature curve, and will not be described again in this invention.
[0044] Example 1: Figure 3 This is a schematic flowchart of another gas leak monitoring method provided in an embodiment of the present invention. Figure 3 For example, this embodiment includes the following steps S201 to S206.
[0045] Step S201: Perform gas leakage simulation using ANSYS Fluent, and analyze the concentration field distribution based on the spatial characteristics obtained from the simulation.
[0046] Step S202: Simulate a gas leakage experiment using an experimental platform, and analyze the pixel value distribution based on the spatial features obtained from the experiment.
[0047] Step S203: The spatial features obtained from simulation and the spatial features obtained from experiment are fused and analyzed with the temporal features to obtain the spatial feature curves corresponding to the simulation and the experimental respectively. The spatial feature curves corresponding to the simulation are used to describe the concentration field distribution, and the spatial feature curves corresponding to the experiment are used to describe the pixel value distribution.
[0048] Step S204: Perform correlation analysis and consistency verification on the two types of feature curves obtained in step S203 to obtain verification results showing that the concentration gradient change is consistent with the pixel gradient trend.
[0049] Step S205: Perform extensive gas leakage simulations using ANSYS Fluent to create a gas leakage concentration field dataset.
[0050] Step S206: Construct a gas leak detection model based on the created gas leak concentration field dataset for monitoring gas leaks.
[0051] This invention also provides a device for gas leak monitoring, such as... Figure 2 As shown, the device includes a memory and a processor, the processor being used to run a program, wherein the program is run to perform the method described.
[0052] The processor contains a kernel, which retrieves the corresponding program unit from memory. One or more kernels can be configured, and gas leak detection can be achieved by adjusting kernel parameters.
[0053] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0054] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of a gas leak monitoring method.
[0055] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0056] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0057] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0058] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0059] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0060] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0061] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0062] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0063] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A method for monitoring gas leaks, characterized in that, The method includes: Based on a pre-established gas leakage simulation model, gas leakage simulations were performed under different simulation parameters to obtain the gas concentration values corresponding to different simulation parameters. Based on the gas concentration value, the spatial characteristics of the gas corresponding to each simulation parameter are obtained; Based on the aforementioned spatial characteristics, the first spatial characteristic curves corresponding to each simulation parameter are obtained; and Based on the first spatial characteristic curve, a gas leak detection model is established for monitoring gas leaks.
2. The method according to claim 1, characterized in that, The gas leakage simulation model is based on ANSYS Fluent and includes a first leakage pipe and a cubic container. The first leakage pipe is used to release liquefied petroleum gas into the cubic container based on simulation parameters.
3. The method according to claim 2, characterized in that, Based on a pre-established gas leakage simulation model, gas leakage simulations were performed under different simulation parameters, and the gas concentration values corresponding to different simulation parameters were obtained, including: Establish a coordinate system within the cube-shaped container, with the XY plane perpendicular to the first leaking pipe; Within the cube-shaped container, nodes are positioned at predetermined intervals along the X, Y, and Z axes, dividing the entire cube-shaped container into a spatial field composed of multiple grids, with each grid corresponding to one node; and For each simulation parameter, liquefied petroleum gas is released into the cube container within a preset time, and during the release process, the molar concentration of liquefied petroleum gas at each node is obtained based on a preset frequency.
4. The method according to claim 3, characterized in that, Based on the gas concentration values, the spatial characteristics of the gas corresponding to each simulation parameter are obtained, including performing the following processing on the molar concentration of liquefied petroleum gas at each node obtained at each time point: For the same For each node, calculate the integral value of its molar concentration along the Z-axis using the following formula: in, For the same The integral value corresponding to the node. For nodes molar concentration, This represents the total number of nodes on the Z-axis. The highest integral value is selected as the highest concentration value of the gas cloud, and the maximum concentration value corresponding to the edge of the gas cloud is found in four directions of the node corresponding to the highest integral value; and Calculate the slope between the highest integral value and the maximum concentration value corresponding to the edges of the four gas clouds, respectively. The slope is the spatial characteristic of the simulation parameter at the time point.
5. The method according to claim 4, characterized in that, Based on the spatial characteristics, the first spatial characteristic curve corresponding to each simulation parameter is obtained, including performing the following processing for each simulation parameter: Based on the spatial characteristics at each time point in each direction, a slope-time curve is established in each direction, resulting in four slope-time curves. These four slope-time curves are the first spatial characteristic curves corresponding to the simulation parameters.
6. The method according to claim 1, characterized in that, The simulation parameters include leakage rate, leak size, gas type, ambient wind field, obstacle arrangement and / or leak location. Different values of the simulation parameters correspond to gas leak tags or false alarm interference tags.
7. The method according to claim 6, characterized in that, Based on the first spatial characteristic curve, the gas leak detection model is established as follows: A training set is established based on the first spatial feature curve obtained under all simulation parameters, wherein the label of the first spatial feature curve is gas leak or false alarm interference. Extract curve features corresponding to each of the first spatial feature curves, wherein the curve features include the curve mean, standard deviation, and / or curve area; and The classification model is trained based on the curve features to obtain the gas leak detection model.
8. The method according to claim 1, characterized in that, The method further includes: An experimental platform was constructed, which included a second leaking pipe and a blank background. The second leaking pipe releases liquefied petroleum gas into the blank background within a preset time to simulate the gas leakage process under different simulation parameters. During the release process, an infrared spectral camera at a fixed position captures images of the leak location, obtaining first video data corresponding to different simulation parameters; Based on the first video data, the second spatial feature curves corresponding to each simulation parameter are obtained; and The first spatial characteristic curve and the second spatial characteristic curve under the same simulation parameters are compared and analyzed to obtain the consistency comparison results.
9. The method according to claim 1, characterized in that, Gas leak monitoring based on the aforementioned gas leak detection model includes: Second video data is acquired in real time using an infrared spectral camera; Based on the second video data, a third spatial feature curve is obtained; and The third spatial characteristic curve is input into the gas leakage simulation model to obtain the gas leakage monitoring results, which include gas leakage or false alarm interference.
10. A device for gas leak monitoring, the device comprising a memory and a processor, characterized in that, The processor is used to run a program, wherein the program is run to perform the method as described in any one of claims 1-9.