A pipeline natural gas leakage concentration field reconstruction method and system

Abstract

The present application provides a method and system for reconstructing the concentration field of pipeline natural gas leakage. Based on the concentration-grayscale mapping relationship, the method converts the two-dimensional grayscale image of the pipeline natural gas leakage area into a two-dimensional concentration projection image, calculates the leakage concentration value of the two-dimensional grid obtained by segmenting the two-dimensional concentration projection image, and then constructs the leakage concentration equation of the leakage area, and generates the three-dimensional gas concentration field of the leakage area based on the algebraic iteration algorithm. In this way, the three-dimensional gas concentration field of the leakage area is reconstructed by obtaining the image of the leakage area, effectively avoiding the shortage of personnel entering the leakage site for detection, improving the efficiency and safety of emergency rescue work after a pipeline leak occurs, greatly improving the safety management after a pipeline natural gas leak incident, and providing technical support for the rapid and effective implementation of emergency rescue after a pipeline natural gas leak.

Description

Technical Field

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

[0002] With the rapid development of social economy, natural gas is increasingly becoming one of the most important energy sources to promote industrial development. However, the distribution of natural gas resources is extremely uneven. Some regions have rich energy reserves, while other regions are relatively scarce.

[0003] Due to the uneven distribution of natural resources, pipeline transportation plays a key role in maintaining the energy supply chain. This is primarily reflected in the construction of a large pipeline network to transport natural gas from resource-rich areas to resource-scarce areas, ensuring a stable energy supply and meeting the energy needs of different regions.

[0004] With the rapid development of society, fossil fuels such as oil and natural gas are having an increasingly greater impact on promoting industrial and economic development. The number and capacity of gas pipelines have increased significantly. However, natural gas is flammable and explosive. With the increase in high-pressure, large-diameter pipelines, its dangers are also increasing. If a gas pipeline leak occurs and is not quickly and effectively addressed, it is very likely to cause harm and damage to personnel, pipelines, the environment, and buildings. Summary of the Invention

[0005] The purpose of this application is to provide a pipeline natural gas leakage concentration field reconstruction method and system to solve or alleviate the problems existing in the above-mentioned prior art.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] The present application provides a method for reconstructing a pipeline natural gas leakage concentration field, comprising: step S101, based on a pre-calibrated concentration-grayscale mapping relationship, converting an acquired two-dimensional grayscale image of a pipeline natural gas leakage area into a two-dimensional concentration projection image, and calculating leakage concentration values ​​of two-dimensional grids obtained by segmenting the two-dimensional concentration projection image; step S102, constructing a leakage concentration equation for the leakage area based on the leakage concentration values, and generating a three-dimensional gas concentration field in the leakage area based on an algebraic iterative algorithm.

[0008] Preferably, in step S101, the two-dimensional grayscale image obtained by synchronously scanning the leakage area from two different preset directions based on the mid-infrared camera is converted into the two-dimensional concentration projection image, and the two-dimensional concentration projection image is two-dimensionally segmented along the light propagation direction perpendicular to the mid-infrared camera, and the average concentration value in each two-dimensional grid obtained by segmentation is calculated.

[0009] Preferably, the converting of the two-dimensional grayscale image obtained by synchronously scanning the leakage area from two different preset directions with a mid-infrared camera into the two-dimensional concentration projection image includes: calibrating the concentration-grayscale mapping relationship between the grayscale of the image captured by the mid-infrared camera and the concentration of natural gas; performing feature extraction on the two-dimensional grayscale image based on Swin Transformer to separate the leakage gas cloud in the leakage area from the two-dimensional grayscale image; and converting the two-dimensional grayscale image into the two-dimensional concentration projection image based on the concentration-grayscale mapping relationship according to the grayscale value of the leakage gas cloud.

[0010] Preferably, in step S102, the propagation trajectory of the detection light emitted by the mid-infrared camera is simulated in the established three-dimensional spatial model of the pipeline natural gas, and the optical path length of each detection light passing through each three-dimensional grid cell is calculated based on the spatial coordinates of the three-dimensional grid cells obtained by discretizing the leakage area in the three-dimensional spatial model; wherein the planar projection of the three-dimensional grid cell is the two-dimensional grid obtained by segmenting the two-dimensional concentration projection image;

[0011] Based on the total leakage concentration on the optical path of each detection light and the optical path length in the corresponding three-dimensional grid unit, a leakage concentration equation of the three-dimensional space model is established, and all the leakage concentration equations are solved based on an algebraic iterative algorithm to generate a three-dimensional gas concentration field in the leakage area; wherein the total leakage concentration on the optical path of the i-th detection light emitted by the mid-infrared camera is the leakage concentration value of the corresponding two-dimensional grid, and i is a positive integer.

[0012] Preferably, the calculating of the optical path length of each detection light through each three-dimensional grid unit includes: simulating the propagation trajectory of the detection light emitted by the mid-infrared camera in the three-dimensional space model based on the two different preset orientations, and calculating the entry grid intersection and exit grid intersection of each detection light with each three-dimensional grid unit according to the spatial coordinates of the three-dimensional grid unit to obtain the corresponding optical path length of the detection light through each three-dimensional grid unit.

[0013] Preferably, according to the formula:

[0014]

[0015] Calculating the leakage concentration value in each three-dimensional grid unit of the three-dimensional space model to generate a three-dimensional gas concentration field in the leakage area; wherein, is the leakage concentration value in the j-th three-dimensional grid cell obtained in the k-th iteration; is the leakage concentration value in the jth three-dimensional grid unit obtained in the k+1th iteration; A is the matrix of the optical path lengths corresponding to all the three-dimensional grid units; A i is a matrix of optical path lengths corresponding to the three-dimensional grid cells that the i-th detection light passes through; i represents the total leakage concentration on the optical path of the detection light described in the i-th item; λ is the convergence factor, and j is a positive integer.

[0016] The present application also provides a pipeline natural gas leakage concentration field reconstruction system, including:

[0017] a data acquisition unit configured to convert the acquired two-dimensional grayscale image of the leakage area of ​​the pipeline natural gas into a two-dimensional concentration projection image based on a pre-calibrated concentration-grayscale mapping relationship, and calculate the leakage concentration value of the two-dimensional grid obtained by segmenting the two-dimensional concentration projection image;

[0018] The concentration reconstruction unit is configured to construct a leakage concentration equation of the leakage area according to the leakage concentration value, and generate a three-dimensional gas concentration field of the leakage area based on an algebraic iteration algorithm.

[0019] An embodiment of the present application also provides an electronic device, comprising: a memory, a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor performs the above pipeline natural gas leakage concentration field reconstruction method.

[0020] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the above pipeline natural gas leakage concentration field reconstruction method.

[0021] An embodiment of the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the above pipeline natural gas leakage concentration field reconstruction method.

[0022] Beneficial effects:

[0023] In a pipeline natural gas leakage concentration field reconstruction method and system provided in an embodiment of the present application, a two-dimensional grayscale image of a pipeline natural gas leakage area is converted into a two-dimensional concentration projection image based on a pre-calibrated concentration-grayscale mapping relationship. The leakage concentration values ​​of the two-dimensional grids obtained by segmenting the two-dimensional concentration projection image are calculated. A leakage concentration equation for the leakage area is then constructed, and a three-dimensional gas concentration field in the leakage area is generated based on an algebraic iteration algorithm. Thus, the three-dimensional gas concentration field in the leakage area is reconstructed using the acquired image of the leakage area, effectively avoiding the need for personnel to enter the leakage site for inspection, improving the efficiency and safety of emergency rescue work after a high-pressure, large-diameter pipeline leak, significantly enhancing safety management after a pipeline natural gas leak incident, and providing technical support for rapid and effective emergency rescue after a pipeline natural gas leak. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings and descriptions that constitute part of this application are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. Among them:

[0025] Figure 1 A schematic flow chart of a pipeline natural gas leakage concentration field reconstruction method provided in an embodiment of the present application;

[0026] Figure 2 A logical diagram of a pipeline natural gas leakage concentration field reconstruction method provided in an embodiment of the present application;

[0027] Figure 3 Schematic diagram of segmentation of a two-dimensional concentration projection image corresponding to a two-dimensional grayscale image taken by a mid-infrared camera 20 meters above the leak center and extraction of leakage concentration values ​​according to an embodiment of the present application;

[0028] Figure 4 Schematic diagram of segmentation of a two-dimensional concentration projection image corresponding to a two-dimensional grayscale image of the leakage area captured by a mid-infrared camera at a height of 10 m and 10 m in front of the leakage center during a pipeline natural gas leak provided in an embodiment of the present application, and extraction of leakage concentration values;

[0029] Figure 5 A schematic diagram of ray tracing within a three-dimensional space model provided in an embodiment of the present application;

[0030] Figure 6 A two-dimensional grayscale image of the leakage area captured by a mid-infrared camera from 20 meters above the center of the leakage during a pipeline natural gas leak provided in an embodiment of the present application;

[0031] Figure 7A two-dimensional grayscale image of the leakage area captured by a mid-infrared camera from a height of 10 m and 10 m in front of the leakage center during a natural gas pipeline leakage according to an embodiment of the present application;

[0032] Figure 8 for Figure 6 The three-dimensional gas concentration field in the leakage area generated by reconstructing the pipeline natural gas leakage is shown;

[0033] Figure 9 This is a structural schematic diagram of a pipeline natural gas leakage concentration field reconstruction system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. Each example is provided by way of explanation of the present application and does not limit the present application. In fact, it will be clear to those skilled in the art that modifications and variations can be made in the present application without departing from the scope or spirit of the present application. For example, a feature shown or described as part of one embodiment can be used in another embodiment to produce yet another embodiment. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention should fall within the scope of protection of the embodiments of the present invention.

[0035] In high-pressure natural gas pipelines, it is extremely important to quickly and effectively handle leaks and quickly and accurately determine the concentration of the leaked gas. Traditional detection methods require personnel to carry detection equipment into the leak area and conduct on-site detection, which is not only extremely dangerous but also has low detection efficiency.

[0036] Based on this, this application proposes a method for reconstructing the concentration field of pipeline natural gas leakage, using a drone carrying a mid-infrared camera to scan the leakage area, and using a new three-dimensional concentration field reconstruction algorithm to overcome the problems of low algorithm accuracy and slow calculation speed in traditional reconstruction algorithms. Figure 1 A flow chart of a pipeline natural gas leakage concentration field reconstruction method provided in an embodiment of the present application; Figure 2 This is a logical diagram of the pipeline natural gas leakage concentration field reconstruction method provided in the embodiment of the present application, as shown in FIG. Figure 1 and Figure 2 As shown in FIG, the pipeline natural gas leakage concentration field reconstruction method includes:

[0037] Step S101: Based on a pre-calibrated concentration-grayscale mapping relationship, a two-dimensional grayscale image of a natural gas pipeline leakage area is converted into a two-dimensional concentration projection image, and leakage concentration values ​​of two-dimensional grids obtained by segmenting the two-dimensional concentration projection image are calculated.

[0038] In this application, a mid-infrared camera mounted on a drone is used to synchronously scan the leak area of ​​the natural gas pipeline from two different perspectives to capture infrared images of the leak area. Specifically, the two-dimensional concentration image obtained by synchronously scanning the leak area from two different preset directions with the mid-infrared camera is converted into a two-dimensional concentration projection image. For example, with the leak point of the natural gas pipeline as the center of the reference system, two drones equipped with mid-infrared cameras are used to synchronously scan the leak area from 20 meters directly above the leak center, 10 meters directly in front of the leak center, and 10 meters at a height, respectively, to obtain two-dimensional grayscale images of the leaked gas cloud in the above two directions. Figure 6 A two-dimensional grayscale image of the leakage area captured by a mid-infrared camera from 20 meters above the center of the leakage during a pipeline natural gas leak provided in an embodiment of the present application; Figure 7 The embodiment of the present application provides a two-dimensional grayscale image of the leakage area captured by a mid-infrared camera from 10m in front of the leakage center and 10m in height during a pipeline natural gas leak. Then, after performing pre-processing operations such as noise removal, boundary extraction, and quality enhancement on the acquired two-dimensional grayscale image, the two-dimensional grayscale image is segmented to separate leakage features such as the boundary and shape of the gas leakage area. Specifically, feature extraction is performed on the two-dimensional grayscale image based on SwinTransformer to separate the leakage gas cloud in the leakage area from the two-dimensional grayscale image, that is, semantic segmentation is performed on the two-dimensional grayscale image through Swin Transformer to extract the gas area from the complex background of the two-dimensional grayscale image to obtain a two-dimensional grayscale image containing only the leakage gas cloud; then, through the mapping relationship between the grayscale of the image captured by the laboratory-calibrated mid-infrared camera and the natural gas concentration, the grayscale value of the leakage gas cloud is converted into the corresponding concentration value to convert the two-dimensional grayscale image into a two-dimensional concentration projection image. Figure 3 Schematic diagram of segmentation of a two-dimensional concentration projection image corresponding to a two-dimensional grayscale image taken by a mid-infrared camera 20 m above the leakage center and extraction of leakage concentration values ​​provided in an embodiment of the present application. Figure 4 This is a schematic diagram of segmenting a two-dimensional concentration projection image corresponding to a two-dimensional grayscale image of the leakage area captured by a mid-infrared camera at 10 m in front of the leakage center and at a height of 10 m during a pipeline natural gas leak provided in this embodiment, and extracting a leakage concentration value.

[0039] Specifically, first, in the laboratory, the grayscale of the image captured by the mid-infrared camera and the natural gas concentration are calibrated to obtain the concentration-grayscale mapping relationship between the grayscale value of the image captured by the mid-infrared camera and the natural gas concentration value; then, based on the concentration-grayscale mapping relationship between the grayscale value of the image captured and the natural gas concentration value, the grayscale value of the leakage gas cloud in the leakage area separated from the two-dimensional grayscale image is converted into the corresponding concentration value, thereby realizing the conversion of the two-dimensional grayscale image into a two-dimensional concentration projection image.

[0040] Next, the 2D density projection image is segmented along a direction perpendicular to the light propagation direction of the mid-infrared camera, and the average concentration value within each segmented 2D grid is calculated. By segmenting the 2D density projection image, the 2D density projection image is divided into multiple 2D grids. Here, the concentration within each 2D grid is defined as uniformly distributed. Furthermore, the average concentration value within each 2D grid is calculated, i.e., the leakage concentration value within each 2D grid.

[0041] When calculating the average concentration value for each 2D grid, a grayscale extraction algorithm is used to extract the average grayscale value of each grid in the 2D grayscale image. Then, based on the concentration-grayscale mapping relationship between the grayscale values ​​of the mid-infrared camera image and the natural gas concentration, the average grayscale value of each 2D grid is converted into an average concentration value. The average concentration value within each 2D grid represents the total concentration value of the corresponding detection light in subsequent ray tracing, laying the foundation for reconstructing the concentration field in the leakage area.

[0042] Step S102: constructing a leakage concentration equation of the leakage area according to the leakage concentration value, and generating a three-dimensional gas concentration field of the leakage area based on an algebraic iteration algorithm.

[0043] In this application, Figure 5 Schematic diagram of ray tracing within a three-dimensional spatial model provided for an embodiment of the present application. Ray tracing is used to simulate the propagation of detection light emitted by a mid-infrared camera within the leakage area, and the propagation trajectory of the detection light emitted by the mid-infrared camera is simulated within a three-dimensional spatial model of pipeline natural gas. Based on the ray tracing, the corresponding portion of the leakage area within the three-dimensional spatial model is spatially discretized to determine the optical path length of each detection light in the discrete three-dimensional grid unit. At the same time, combined with the total concentration of each detection light (the average concentration value of each two-dimensional grid), a leakage concentration equation for the detection light is established. Based on the leakage concentration equation, an algebraic iterative algorithm is used to iteratively solve the gas concentration value within each three-dimensional grid unit, thereby reconstructing the leakage concentration field of the leakage area.

[0044] First, the propagation trajectory of the detection light emitted by the mid-infrared camera is simulated within the established 3D spatial model of the natural gas pipeline. Based on the spatial coordinates of the 3D grid cells obtained by discretizing the leak area in the 3D spatial model, the optical path length of each detection light beam through each 3D grid cell is calculated. It should be noted that the planar projection of the 3D grid cell is the 2D grid obtained by segmenting the 2D concentration projection image.

[0045] When calculating the optical path length within each three-dimensional grid cell, the intersection points of each detection light ray entering and exiting each three-dimensional grid cell are calculated based on the propagation trajectory of the simulated detection light emitted by two mid-infrared cameras at different preset orientations within the three-dimensional space model and the spatial coordinates of the three-dimensional grid cells, thereby obtaining the optical path length of the corresponding detection light ray passing through each three-dimensional grid cell. In other words, the spatial coordinates of the three-dimensional grid cells are used to determine the coordinates of the intersection points where the detection light ray enters and exits the three-dimensional grid cell along the light propagation path. Furthermore, the distance between the coordinates of the intersection points where the detection light ray enters and exits the three-dimensional grid cell is calculated, which is the optical path length of the detection light ray within the corresponding three-dimensional grid cell.

[0046] Then, the average concentration value calculated within each two-dimensional grid is used as the leakage concentration within the optical path (the entire optical path) of the detection light in the corresponding three-dimensional grid cell. Combined with the optical path length within the corresponding three-dimensional grid cell, the leakage concentration equation for the three-dimensional grid cell within the entire optical path of the detection light is established. That is, based on the total leakage concentration along the optical path of each detection light and the optical path length in the corresponding three-dimensional grid cell, the leakage concentration equation for the three-dimensional spatial model is established as follows:

[0047] O i =∑L i , j *X j

[0048] Where, O i is the total leakage concentration on the optical path of the i-th detection light emitted by the mid-infrared camera, that is, the leakage concentration value of the corresponding two-dimensional grid, L i , j is the optical path length of the i-th detection light passing through the j-th three-dimensional grid unit, X j is the leakage concentration value in the jth three-dimensional grid unit.

[0049] Then, all leakage concentration equations are solved based on the algebraic iteration algorithm to generate the three-dimensional gas concentration field in the leakage area.

[0050]

[0051] Calculate the leakage concentration value within each 3D grid cell of the 3D space model to generate the 3D gas concentration field in the leakage area. is the leakage concentration value in the j-th three-dimensional grid cell obtained in the k-th iteration; is the leakage concentration value in the jth three-dimensional grid unit obtained in the k+1th iteration; A is the matrix of optical path lengths corresponding to all three-dimensional grid units; A iis the matrix of the optical path lengths corresponding to the three-dimensional grid cells that the i-th detection light passes through; i It represents the total leakage concentration on the optical path of the i-th detection light; λ is the convergence factor, and j is a positive integer.

[0052] Therefore, based on ray tracing and algebraic iteration algorithm, the three-dimensional concentration field in the entire leakage area is reconstructed, which effectively solves the problem that traditional methods can only reconstruct two-dimensional concentration fields or segment the three-dimensional space and then reconstruct the concentration fields in the segmented areas one by one and then superimpose them to form a three-dimensional concentration field in the leakage area. Not only is the boundary of the leaking gas cloud accurately portrayed and the concentration field reconstruction error small, but the calculation speed is also fast and the algorithm structure is simple.

[0053] At the same time, the leakage area is scanned by a mid-infrared camera equipped with a drone to obtain images of the leakage area and reconstruct the three-dimensional concentration field of the gas in the leakage area. Figure 8 The three-dimensional gas concentration field of the leakage area reconstructed and generated in the embodiment of the present application during a pipeline natural gas leak effectively avoids the inadequacy of personnel entering the leakage site for detection. This not only improves the efficiency and safety of emergency rescue work after a high-pressure, large-diameter pipeline leak, but also greatly enhances safety management after a pipeline natural gas leak, providing technical support for rapid and effective emergency rescue after a pipeline natural gas leak. Furthermore, this method is transferable and can be applied to the reconstruction of various gas leakage concentration fields, enabling unmanned detection with high safety, providing an effective reference for emergency rescue work in gas pipeline leaks.

[0054] Figure 9 The embodiment of the present application provides a pipeline natural gas leakage concentration field reconstruction system, such as Figure 9 As shown, the system includes:

[0055] The data acquisition unit 901 is configured to acquire a two-dimensional concentration projection image of a natural gas pipeline leakage area and calculate leakage concentration values ​​of two-dimensional grids obtained by segmenting the two-dimensional concentration projection image;

[0056] The concentration reconstruction unit 902 is configured to construct a leakage concentration equation of the leakage area according to the leakage concentration value, and generate a three-dimensional gas concentration field of the leakage area based on an algebraic iteration algorithm.

[0057] The pipeline natural gas leakage concentration field reconstruction system provided in the embodiment of the present application can implement the steps and processes of the pipeline natural gas leakage concentration field reconstruction method of any of the above embodiments and achieve the same technical effects, which will not be described in detail here.

[0058] An electronic device provided in an embodiment of the present application includes: at least one processor and a memory. Optionally, the electronic device also includes a communication component. The processor, memory, and communication component are connected via a bus. In a specific implementation process, at least one processor executes computer-executable instructions stored in the memory, causing the at least one processor to perform the above-mentioned method. The specific implementation process of the processor can be found in the above-mentioned method embodiment. The implementation principles and technical effects are similar and will not be repeated here in this embodiment.

[0059] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0060] An embodiment of the present application further provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above-mentioned method is implemented.

[0061] In the description of the present invention, the terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any appropriate manner in any one or more embodiments or examples.

[0062] The foregoing description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are readily apparent to those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A pipeline natural gas leakage concentration field reconstruction method, characterized in that: include: Step S101: based on a pre-calibrated concentration-grayscale mapping relationship, convert the acquired two-dimensional grayscale image of the leakage area of ​​the pipeline natural gas into a two-dimensional concentration projection image, and calculate the leakage concentration value of the two-dimensional grid obtained by segmenting the two-dimensional concentration projection image; Step S102: simulating the propagation trajectory of the detection light emitted by the mid-infrared camera within the established three-dimensional spatial model of the pipeline natural gas, and calculating the optical path length of each detection light passing through each three-dimensional grid cell based on the spatial coordinates of the three-dimensional grid cells obtained by discretizing the leakage area in the three-dimensional spatial model; wherein the planar projection of the three-dimensional grid cell is the two-dimensional grid obtained by segmenting the two-dimensional concentration projection image; establishing a leakage concentration equation for the three-dimensional spatial model based on the total leakage concentration on the optical path of each detection light and the optical path length in the corresponding three-dimensional grid cell, and solving all the leakage concentration equations based on an algebraic iterative algorithm to generate a three-dimensional gas concentration field in the leakage area; wherein the total leakage concentration on the optical path of the i-th detection light emitted by the mid-infrared camera is the leakage concentration value of the corresponding two-dimensional grid, where i is a positive integer; According to the formula: Calculating the leakage concentration value in each three-dimensional grid unit of the three-dimensional space model to generate a three-dimensional gas concentration field in the leakage area; wherein, For the The first iteration The leakage concentration value within each of the three-dimensional grid cells; For the The first iteration The leakage concentration value within each of the three-dimensional grid cells; A matrix of the optical path lengths corresponding to all the three-dimensional grid cells; For the a matrix of optical path lengths corresponding to the three-dimensional grid cells through which the detection light rays pass; Indicates the The total leakage concentration on the optical path of the detection light; is the convergence factor, Is a positive integer.

2. The pipeline natural gas leakage concentration field reconstruction method according to claim 1 is characterized in that: In step S101, The two-dimensional grayscale image obtained by synchronously scanning the leakage area from two different preset directions with a mid-infrared camera is converted into the two-dimensional concentration projection image, and the two-dimensional concentration projection image is two-dimensionally segmented along the light propagation direction perpendicular to the mid-infrared camera, and the leakage concentration value in each two-dimensional grid obtained by segmentation is calculated.

3. The pipeline natural gas leakage concentration field reconstruction method according to claim 2 is characterized in that: The step of converting the two-dimensional grayscale image obtained by synchronously scanning the leakage area from two different preset positions with a mid-infrared camera into the two-dimensional concentration projection image comprises: Calibrate the concentration-grayscale mapping relationship between the grayscale of the image captured by the mid-infrared camera and the natural gas concentration; performing feature extraction on the two-dimensional grayscale image based on Swin Transformer to separate the leakage gas cloud in the leakage area from the two-dimensional grayscale image; According to the grayscale value of the leaked gas cloud, the two-dimensional grayscale image is converted into the two-dimensional concentration projection image based on the concentration-grayscale mapping relationship.

4. The pipeline natural gas leakage concentration field reconstruction method according to claim 1 is characterized in that: Calculating the optical path length of each detection light beam passing through each three-dimensional grid unit includes: Based on two different preset orientations, the propagation trajectory of the detection light emitted by the mid-infrared camera is simulated in the three-dimensional space model, and according to the spatial coordinates of the three-dimensional grid cells, the entry grid intersection and the exit grid intersection of each detection light with each three-dimensional grid cell are calculated to obtain the corresponding optical path length of the detection light passing through each three-dimensional grid cell.

5. A pipeline natural gas leakage concentration field reconstruction system, characterized in that: include: a data acquisition unit configured to convert the acquired two-dimensional grayscale image of the leakage area of ​​the pipeline natural gas into a two-dimensional concentration projection image based on a pre-calibrated concentration-grayscale mapping relationship, and calculate the leakage concentration value of the two-dimensional grid obtained by segmenting the two-dimensional concentration projection image; A concentration reconstruction unit is configured to simulate the propagation trajectory of the detection light emitted by the mid-infrared camera within the established three-dimensional spatial model of the pipeline natural gas, and calculate the optical path length of each detection light passing through each three-dimensional grid cell based on the spatial coordinates of the three-dimensional grid cells obtained by discretizing the leakage area in the three-dimensional spatial model; wherein the plane projection of the three-dimensional grid cell is the two-dimensional grid obtained by segmenting the two-dimensional concentration projection image; based on the total leakage concentration on the optical path of each detection light and the optical path length in the corresponding three-dimensional grid cell, a leakage concentration equation of the three-dimensional spatial model is established, and all the leakage concentration equations are solved based on an algebraic iterative algorithm to generate a three-dimensional gas concentration field in the leakage area; wherein the total leakage concentration on the optical path of the i-th detection light emitted by the mid-infrared camera is the leakage concentration value of the corresponding two-dimensional grid, and i is a positive integer; according to the formula: Calculating the leakage concentration value in each three-dimensional grid unit of the three-dimensional space model to generate a three-dimensional gas concentration field in the leakage area; wherein, For the The first iteration The leakage concentration value within each of the three-dimensional grid cells; For the The first iteration The leakage concentration value within each of the three-dimensional grid cells; A matrix of the optical path lengths corresponding to all the three-dimensional grid cells; For the a matrix of optical path lengths corresponding to the three-dimensional grid cells through which the detection light rays pass; Indicates the The total leakage concentration on the optical path of the detection light; is the convergence factor, Is a positive integer.

6. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the pipeline natural gas leakage concentration field reconstruction method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 4 when executed by a processor.

8. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 4 when the computer program is executed by a processor.

Images