Pipeline inspection abnormal hidden danger intelligent identification system based on unmanned aerial vehicle

Abstract

The invention relates to the technical field of intelligent inspection, in particular to a pipeline inspection abnormal hidden danger intelligent identification system based on an unmanned aerial vehicle. According to the invention, the three-dimensional grid construction is carried out on the data collected by the unmanned aerial vehicle in the inspection process, so that the space division of the inspection area is realized, and the detection of the gas pipeline has higher precision. In combination with hyperspectral data analysis, measurement of methane concentration can be accurately mapped to space grid points, interference of environmental factors is reduced, and preliminary recognition accuracy of a leakage area is improved. On the basis of local concentration gradient calculation, through a data smoothing and diffusion optimization method, the boundary of a leakage area is clearer, interference of environmental noise is eliminated, meanwhile, the concentration value is dynamically adjusted, and the adaptive capacity to the change trend of leakage points is enhanced. By means of the construction of the virtual diffusion field and in combination with the space occupation condition of terrain obstacles, the analysis of the gas flow path is more accurate, and the problem of misjudgment caused by terrain complexity is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent inspection, and particularly to an intelligent identification system for pipeline inspection anomalies and potential hazards based on unmanned aerial vehicles (UAVs). Background Art

[0002] An intelligent identification system for pipeline inspection anomalies and potential hazards based on UAVs refers to a system that uses UAVs equipped with high-precision sensing devices to inspect gas pipelines and intelligently identify abnormal situations. The system aims at problems such as gas leakage, pipeline appearance damage, and geological disaster impacts during pipeline inspection. It uses UAVs equipped with laser methane telemetry devices, high-definition optical imaging devices, infrared thermal imagers and other detection tools to obtain high-resolution data of the inspection area, and combines computer vision algorithms to analyze the spectral characteristics of the gas leakage area, perform morphological matching on the structural changes on the pipeline surface, and perform differential calculations on the temperature gradient of the surrounding environment to achieve the identification of pipeline anomalies and potential hazards.

[0003] Existing inspection methods are limited by the coverage range of sensors during data collection, and the inspection accuracy depends on single-point or small-scale data collection methods, resulting in data breakpoints during the inspection process, making it difficult to accurately capture the leakage situation in some areas. Data processing relies on a judgment method based on a single concentration value and is easily interfered by environmental factors, resulting in a high false alarm rate. Especially in an environment with large wind speed changes, the gas diffusion pattern is complex, and it is difficult to form an accurate judgment simply relying on the measured concentration value. The consideration of terrain obstacles is lacking during the inspection process, resulting in limited gas flow but unable to be correctly analyzed in complex terrain areas, increasing the possibility of missed inspections. The prediction of gas diffusion trends mostly relies on empirical judgment and lacks intelligent analysis based on historical data, resulting in insufficient early warning capabilities, making it difficult to predict potential hazard points in advance, causing the inspection response to lag, and affecting the accuracy and timeliness of pipeline maintenance work. Summary of the Invention

[0004] The purpose of the present invention is to solve the deficiencies existing in the prior art and propose an intelligent identification system for pipeline inspection anomalies and potential hazards based on UAVs.

[0005] To achieve the above purpose, the present invention adopts the following technical solution: An intelligent identification system for pipeline inspection anomalies and potential hazards based on UAVs includes:

[0006] The methane concentration detection module collects UAV flight data to construct a first grid in a three-dimensional space, evenly divides the first grid into multiple first grid points, and maps the methane concentration value of each first grid point according to the measured laser absorption spectrum data to generate a methane concentration heat map;

[0007] The concentration data smoothing module reads all methane concentration values in the methane concentration heat map, calculates the local methane concentration gradient of each first grid point, marks the potential leakage areas according to the magnitude of the local methane concentration gradient, sets the diffusion coefficient of the corresponding first grid point to update the methane concentration value, and generates a methane concentration heat map after diffusion optimization;

[0008] The virtual diffusion field reconstruction module constructs second grid points occupied by terrain obstacles on the methane concentration heat map after diffusion optimization, sets the methane concentration attenuation coefficient of the second grid points occupied by the obstacle space, analyzes the methane concentration values from the first grid points corresponding to the potential leakage areas to the second grid points occupied by the terrain obstacle space according to the methane concentration attenuation coefficient, and generates a methane concentration distribution map after terrain analysis;

[0009] The leakage trend prediction module predicts the change trend of methane around the potential leakage areas in the methane concentration distribution map after terrain analysis, and generates a diffusion trend prediction result;

[0010] The leakage risk assessment module identifies the change trend of methane in the diffusion trend prediction result and visually displays it on the methane concentration distribution map after terrain analysis, and generates a leakage hazard identification result for the gas pipeline.

[0011] As a further solution of the present invention, the steps for obtaining the methane concentration heat map are specifically as follows:

[0012] Collect drone flight data, including drone position information and flight trajectory data along the gas pipeline area, determine the three-dimensional coordinates of all measurement points, integrate the three-dimensional coordinates of all measurement points to construct a first grid in three-dimensional space, evenly divide the first grid into multiple first grid points, and generate a first grid division result;

[0013] Obtain terrain height data, adjust the divided first grid points in the first grid division result to match the current terrain structure, collect the laser absorption spectrum data measured by the methane laser telemeter on the drone, analyze the methane concentration in the air according to the laser absorption spectrum data, and generate methane concentration values;

[0014] Fill the gaps of the methane concentration values between the measurement points by interpolation method and map them into each first grid point in three-dimensional space to generate a methane concentration heat map.

[0015] As a further solution of the present invention, the steps for obtaining the methane concentration heat map after diffusion optimization are specifically as follows:

[0016] Read all the methane concentration values in the methane concentration heat map, calculate the local methane concentration gradient of each first grid point, compare the local methane concentration gradient with a preset change threshold, mark the potential leakage areas where the local methane concentration gradient exceeds the change threshold, and generate a potential leakage area marking result;

[0017] Based on the magnitude of the local methane concentration gradient of each first grid point corresponding to a potential leakage area in the potential leakage area marking result, set the diffusion coefficient of the first grid point corresponding to the potential leakage area, and update the methane concentration value of the first grid point corresponding to the potential leakage area through the partial differential diffusion equation according to the diffusion coefficient, and generate a methane concentration heat map after diffusion optimization.

[0018] As a further solution of the present invention, the steps for obtaining the methane concentration distribution map after terrain analysis are specifically as follows:

[0019] Collect the three-dimensional terrain point cloud data scanned by the UAV LiDAR, construct the second grid points occupied by the terrain obstacles on the methane concentration heat map after diffusion optimization according to the three-dimensional terrain point cloud data, and discretize the methane diffusion path around the potential leakage area by using the finite volume method with reference to the position and distribution of the second grid points, and generate a methane diffusion path processing result;

[0020] Obtain the real-time wind speed, wind direction, temperature, and humidity data of the terrain obstacle area corresponding to the methane diffusion path processing result, analyze the total flow deviation of methane in the terrain obstacle area, and set the methane concentration attenuation coefficient of the second grid points occupied by the obstacles according to the total flow deviation;

[0021] Analyze the methane concentration value from the first grid point corresponding to the potential leakage area to the second grid points occupied by the terrain obstacles according to the methane concentration attenuation coefficient, and generate a methane concentration distribution map after terrain analysis.

[0022] As a further solution of the present invention, the steps for obtaining the diffusion trend prediction result are specifically as follows:

[0023] Identify the diffusion direction of methane around the potential leakage area in the methane concentration distribution map after terrain analysis, and generate a methane diffusion direction analysis result;

[0024] Based on the methane diffusion direction analysis result, obtain all the records of historical methane leakage, and combine the turbulent diffusion theory to predict the change trend of methane concentration in the future time, and generate a diffusion trend prediction result.

[0025] As a further solution of the present invention, the steps for obtaining the gas pipeline leakage hazard identification result are specifically as follows:

[0026] Visualize the methane concentration change trend in the future time in the predicted diffusion trend results on the methane concentration distribution map after the terrain analysis, identify the aggregation of methane concentration in different potential leakage areas, and obtain a methane concentration evolution display map;

[0027] Based on the methane concentration change trend in the methane concentration evolution display map, evaluate the risk level of the current potential leakage area, and generate an identification result of gas pipeline leakage hazards.

[0028] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0029] In the present invention, through the construction of a three-dimensional grid for the data collected by the drone during the inspection process, the spatial division of the inspection area is realized, so that the detection of the gas pipeline has higher accuracy. Combining the hyperspectral data analysis, the determination of the methane concentration can be accurately mapped to the spatial grid points, reducing the interference of environmental factors and improving the accuracy of the preliminary identification of the leakage area. Based on the calculation of the local concentration gradient, through the data smoothing and diffusion optimization methods, the boundary of the leakage area is made clearer, excluding the interference of environmental noise, and at the same time dynamically adjusting the concentration value to enhance the adaptability to the change trend of the leakage point. With the construction of the virtual diffusion field, combined with the spatial occupancy of the terrain obstacles, the analysis of the gas flow path is made more accurate, solving the misjudgment problem caused by the terrain complexity. Combining the real-time analysis of environmental parameters, according to the influence of wind speed, wind direction, temperature and humidity, dynamically adjust the calculation method of the diffusion path, so that the prediction of the methane concentration distribution trend is more in line with the actual situation. Combining the turbulent diffusion theory, conduct a correlation analysis on the historical leakage data, optimize the prediction accuracy of the future leakage trend, and provide more reliable data support for the inspection decision-making. Visualize the concentration evolution of the leakage area, enabling the inspection personnel to intuitively judge the severity of potential hazards, and combining the risk assessment method, realize the dynamic grading of leakage hazards, and improve the pertinence and response speed of early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is the system flow chart of the present invention;

[0031] Figure 2 is the flow chart of obtaining the methane concentration heat map of the present invention;

[0032] Figure 3 is the flow chart of obtaining the methane concentration heat map after diffusion optimization of the present invention;

[0033] Figure 4 is the flow chart of obtaining the methane concentration distribution map after terrain analysis of the present invention;

[0034] Figure 5 is the flow chart of obtaining the predicted diffusion trend result of the present invention;

[0035] Figure 6 This is a flowchart for obtaining the identification result of gas pipeline leakage hidden danger in the present invention. Specific implementation manners

[0036] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0037] Please refer to Figure 1 , an intelligent identification system for abnormal hidden dangers in pipeline inspection based on an unmanned aerial vehicle includes:

[0038] The methane concentration detection module collects the flight data of the unmanned aerial vehicle to construct a first grid in a three-dimensional space, evenly divides the first grid into a plurality of first grid points, and maps the methane concentration value of each first grid point according to the measured laser absorption spectrum data to generate a methane concentration heat map;

[0039] The concentration data smoothing module reads all the methane concentration values in the methane concentration heat map, calculates the local methane concentration gradient of each first grid point, marks the potential leakage area according to the magnitude of the local methane concentration gradient, sets the diffusion coefficient of the corresponding first grid point to update the methane concentration value, and generates a methane concentration heat map after diffusion optimization;

[0040] The virtual diffusion field reconstruction module constructs a second grid point occupied by the terrain obstacle space on the methane concentration heat map after diffusion optimization, sets the methane concentration attenuation coefficient of the second grid point occupied by the obstacle space, analyzes the methane concentration value from the first grid point corresponding to the potential leakage area to the second grid point occupied by the terrain obstacle space according to the methane concentration attenuation coefficient, and generates a methane concentration distribution map after terrain analysis;

[0041] The leakage trend prediction module predicts the change trend of methane around the potential leakage area in the methane concentration distribution map after terrain analysis and generates a diffusion trend prediction result;

[0042] The leakage risk assessment module identifies the change trend of methane in the diffusion trend prediction result and visually displays it on the methane concentration distribution map after terrain analysis to generate the identification result of gas pipeline leakage hidden danger.

[0043] Please refer to Figure 2 , the specific steps for obtaining the methane concentration heat map are as follows:

[0044] Collect the flight data of the unmanned aerial vehicle, including the position information of the unmanned aerial vehicle and the flight trajectory data along the gas pipeline area, determine the three-dimensional coordinates of all measurement points, integrate the three-dimensional coordinates of all measurement points to construct a first grid in a three-dimensional space, evenly divide the first grid into a plurality of first grid points, and generate a first grid division result;

[0045] The high-precision GPS module (such as Trimble RTK-GNSS) and inertial measurement unit (IMU) carried by the unmanned aerial vehicle are used to obtain the position information of the unmanned aerial vehicle when flying in the gas pipeline area. At the same time, the heading angle, acceleration, and angular velocity data in the flight control system log of the unmanned aerial vehicle are recorded. These data are stored in real time by the unmanned aerial vehicle control system and can be extracted through flight control software (such as Pix4D or DJI Terra). During the flight of the unmanned aerial vehicle, the geographic coordinate information of each measurement point collected includes longitude, latitude, and altitude. These coordinate data are parsed through geographic information processing software (such as ArcGIS or QGIS), and the geographic coordinates are converted into three-dimensional coordinates of X, Y, and Z in the rectangular coordinate system through a coordinate conversion tool. During the conversion process, the global geographic coordinate system (WGS84) standard is referenced to ensure consistent coordinate accuracy. Subsequently, the three-dimensional coordinate data of all measurement points are imported into point cloud processing software (such as CloudCompare or MeshLab). Through point cloud density analysis, the spatial distribution of the measurement points is determined. On this basis, the Delaunay triangulation method is used to connect the measurement points to construct the first grid. When dividing the first grid, according to the size of the measurement area and the density of the measurement points, the division parameters are set in the point cloud processing software. The software automatically generates uniform grid cells and exports the divided grid data. After the division is completed, the first grid serves as the basic data structure in three-dimensional space.

[0046] The terrain height data is obtained, and the divided first grid points in the first grid division result are adjusted to match the current terrain structure. The laser absorption spectrum data measured by the methane laser telemeter on the unmanned aerial vehicle is collected, and the methane concentration in the air is analyzed based on the laser absorption spectrum data to generate a methane concentration value;

[0047] Combined with the terrain height data obtained by the drone, first use terrain data processing software (such as GlobalMapper or Surfer) to load and compare the digital elevation model (DEM) data of the measurement area, analyze the height difference between the measurement points and the DEM data, overlay the DEM data onto the first grid through GIS software (such as the terrain analysis tool of ArcGIS), and use the spatial adjustment tool to match the height of the first grid to ensure that the measurement point data conforms to the actual terrain situation. During the adjustment process, use the bilinear interpolation method to make the height of each grid cell of the first grid smoothly transition with the surrounding known terrain data. After the adjustment is completed, the drone is equipped with a methane laser telemetry instrument (such as PergamLaserMethanemini or SPMLiDAR) and flies along the gas pipeline area to detect the methane concentration in the air using laser scanning. This device conducts remote detection through a laser beam of a specific wavelength, and the detection data is read through methane detection software (such as Pergam data analysis software or LaserMethaneViewer), and a methane concentration data set of the measurement points is automatically generated. These concentration data are matched with the adjusted coordinate data of the first grid through data matching software (such as MATLAB or the GDAL library of Python) to integrate into a methane concentration data file in three-dimensional space.

[0048] Fill the gaps in the methane concentration values between the measurement points through interpolation methods and map them to each first grid point in three-dimensional space to generate a methane concentration heat map;

[0049] After obtaining the methane concentration data of the measurement points, first, for the vacant areas existing between the data points, select the interpolation tool provided by GIS software (such as ArcGIS or Surfer) for interpolation filling. The interpolation method can adopt inverse distance weighted interpolation (IDW) or Kriging interpolation. In ArcGIS, use the interpolation analysis tool, input the methane concentration values of the known measurement points, and the software automatically calculates and fills the concentration data of the unknown measurement points. After the interpolation is completed, import the generated complete concentration data into three-dimensional visualization software (such as ParaView or Tecplot360) to map the methane concentration on the first grid. The concentration values correspond one by one to the grid cells, and a three-dimensional heat map is generated. The heat map visually presents the spatial distribution of the methane concentration through color changes and is finally exported as a standard GIS format file or a visualization format.

[0050] Collect flight data through drones, construct a fine three-dimensional grid, achieve high-precision spatial division of the inspection area, and thus improve the accuracy of gas pipeline detection. Adjust the grid structure in combination with terrain height data to make the measurement results more in line with the actual terrain features and enhance the authenticity and reliability of the data. The methane laser telemetry instrument provides hyperspectral data, and interpolates to fill in the missing values to ensure the integrity of the concentration distribution. Finally, map the methane concentration values with a three-dimensional grid and generate a heat map to accurately reflect the spatial distribution of gas leakage.

[0051] Please refer to Figure 3 , and the steps for obtaining the heat map of methane concentration after diffusion optimization are specifically as follows:

[0052] Read all the methane concentration values in the heat map of methane concentration, calculate the local methane concentration gradient of each first grid point, compare the local methane concentration gradient with a preset change threshold, mark the potential leakage areas where the local methane concentration gradient exceeds the change threshold, and generate the marking result of potential leakage areas;

[0053] For calculating the local methane concentration gradient of each first grid point, the formula is used:

[0054]

[0055] Calculate the local methane concentration gradient G( i,j ) at the current first grid point (i, j) in the heat map of methane concentration;

[0056] Among them, C is the methane concentration value of the current first grid point in the heat map of methane concentration, with the unit of ppm, and this value is collected by a methane sensor; is the partial derivative of methane concentration in the x direction, indicating the concentration change trend per unit distance. This value is calculated by the finite difference method: is the partial derivative of methane concentration in the y direction, indicating the concentration change trend per unit distance. This value is calculated by the finite difference method: i, j) is the coordinate of the current first grid point, representing the number of the current grid cell. This value is automatically set by the grid division rule and is generally obtained based on the geographical location or the sensor layout plan; i + 1 and i - 1 respectively represent the adjacent grid points on the right and left of the current first grid point coordinate (i, j); j + 1 and j - 1 respectively represent the adjacent grid points above and below the current first grid point coordinate (i, j); Δx and Δy are the grid steps (unit: m) of the current first grid point in the x direction and y direction, which are determined by the grid division plan, such as a grid spacing of 1m. Usually obtained by GIS (Geographic Information System) or the sensor layout plan.

[0057] Assume that the methane concentration C(i,j) and the concentrations of adjacent points are C(i,j) = 5 ppm, C(i+1,j) = 12 ppm (methane concentration on the right side of this point), C(i-1,j) = 3 ppm (methane concentration on the left side of this point), C(i,j+1) = 11 ppm (methane concentration above this point), and C(i,j-1) = 2 ppm (methane concentration below this point).

[0058] Calculation process:

[0059]

[0060] This result indicates that the change in methane concentration at the current first grid point is 6.36 ppm / m.

[0061] Set the change threshold G th To identify possible methane leakage areas, the setting of this threshold is based on laboratory gas diffusion tests, historical leakage data, environmental parameters (temperature, humidity, wind speed), and sensitivity analysis of monitoring equipment. Usually, the value range is between 3.0 ppm / m and 4.0 ppm / m. In this calculation, G th = 3.5 ppm / m is selected as the initial setting value. The purpose is to distinguish between normal diffusion areas and abnormal concentration change areas. Under normal environmental conditions, the change in methane concentration gradient is usually relatively stable. Lower concentration gradients (such as less than 2 ppm / m) mostly appear in stable diffusion areas, while higher concentration gradients (such as greater than 3.5 ppm / m) usually mean that the local concentration changes sharply, which may be caused by point source leakage, local concentration accumulation, or external disturbances (such as wind speed changes). Therefore, when the methane concentration gradient G( i,j ) of a certain grid unit exceeds 3.5 ppm / m, it is considered that there may be potential leakage in this area, and its diffusion situation needs to be further analyzed. When the concentration gradient is lower than this threshold, it is considered that this area belongs to the concentration stable area and does not require immediate leakage treatment. Combining the calculation results, the concentration gradient G( i,j ) at the current grid point (i,j) = 6.36 ppm / m, far exceeding the set threshold G th = 3.5 ppm / m. Therefore, this grid unit is marked as a potential leakage area, which is used as the basis for setting the diffusion coefficient in the follow-up to further calculate the diffusion change trend of methane concentration in this area.

[0062] Based on the magnitude of the local methane concentration gradient of each potential leakage area corresponding to the first grid point in the potential leakage area marking result, set the diffusion coefficient of the first grid point corresponding to the potential leakage area. According to the diffusion coefficient, update the methane concentration value of the first grid point corresponding to the potential leakage area through the partial differential diffusion equation to generate a heat map of methane concentration after diffusion optimization;

[0063] The diffusion coefficient D(i,j) of methane reflects the diffusion ability of the gas in space. The value of the diffusion coefficient is usually determined through experiments or set by referring to meteorological parameters and literature data. Under normal atmospheric conditions, the molecular diffusion coefficient of methane in air is approximately 0.1 - 0.3 m 2 / s, and it may increase to 0.5 - 1.0 m 2 / s under the influence of strong winds or turbulence. In this calculation, the diffusion coefficient is set based on the local methane concentration gradient G(i,j) at the grid points. A higher concentration gradient usually means a more drastic concentration change, and the corresponding diffusion ability may be enhanced. Therefore, a segmented method is used to set the diffusion coefficient to make the diffusion calculation more in line with the actual situation. The setting rules are as follows: When G(i,j) < 2 ppm / m, it is considered that the concentration change in this area is gentle, and the diffusion coefficient takes a smaller value D(i,j) = 0.1 m 2 / s; when 2 ≤ G(i,j) < 3.5 ppm / m, it is considered that the concentration change is moderate, and the diffusion coefficient takes D(i,j) = 0.2 m 2 / s; when G(i,j) ≥ 3.5 ppm / m, it is considered that the concentration changes drastically, and there may be a leakage source or a high-diffusion area, and the diffusion coefficient takes a larger value D(i,j) = 0.6 m 2 / s. Combining the calculation results, the concentration gradient G(i,j) at the current grid point is 6.36 ppm / m, exceeding the set high-gradient threshold G th =

[0064] 3.5 ppm / m. Therefore, the diffusion coefficient of this grid point is set to D(i,j) = 0.6 m 2 / s to simulate the temporal change trend of methane concentration in this area.

[0065] For updating the methane concentration value at the first grid point corresponding to the potential leakage area through the partial differential diffusion equation, the formula:

[0066]

[0067] is used to calculate the updated methane concentration value C new (i,j) at the first grid point (i,j) corresponding to the potential leakage area;

[0068] where C(i,j) is the methane concentration value corresponding to the first grid point (i,j) in the potential leakage area, which is obtained by sensor monitoring; D(i,j) is the diffusion coefficient set according to the first grid point in the potential leakage area (unit: m 2 / s), which is obtained based on experimental measurements and gas diffusion characteristics; Δx and Δy are the grid steps (in m) of the first grid point corresponding to the potential leakage area in the x - direction and y - direction. In a uniform grid, Δx = Δy, but in a non - uniform grid, they need to be calculated separately; Δt is the time step set according to the grid step, used to discretize the time derivative, and is usually selected according to the simulation accuracy requirements, such as 1 s, 0.5 s, etc.; S x is the Laplacian term of the methane concentration at the first grid point corresponding to the potential leakage area in the x - direction, used to calculate the diffusion effect in the x - axis direction, S x = C(i + 1,j)+C(i - 1,j)-2C(i,j); S y is the Laplacian term of the methane concentration at the first grid point corresponding to the potential leakage area in the y - direction, used to calculate the diffusion effect in the y - axis direction, S y = C(i,j + 1)+C(i,j - 1)-2C(i,j), (i,j) is the coordinate of the first grid point corresponding to the potential leakage area, representing the number of the grid cell corresponding to the potential leakage area, which is automatically set by the grid division rule, generally obtained based on the geographical location or the sensor layout scheme; i + 1 and i - 1 respectively represent the adjacent grid points on the right and left of the coordinate (i,j) of the first grid point corresponding to the potential leakage area; j + 1 and j - 1 respectively represent the adjacent grid points above and below the coordinate (i,j) of the first grid point corresponding to the potential leakage area. 2C(i,j) represents twice the methane concentration at the first grid point (i,j) corresponding to the potential leakage area, and its function is to ensure that the concentration at the current point forms a dynamic balance with the concentrations of its adjacent points in the diffusion calculation, determining the concentration change trend of this point in the diffusion calculation; and Both factors are dimensionless and represent the contribution ratio of the diffusion effect to the concentration update within this time step.

[0069] Assume C(i,j)=5 ppm, C(i + 1,j)=12 ppm (right - hand grid), C(i - 1,j)=3 ppm (left - hand grid), C(i,j + 1)=11 ppm (upper grid), C(i,j - 1)=2 ppm (lower grid), D(i,j0 = 0.6 m 2 / s, Δt = 1 s, Δx = Δy = 1 m.

[0070] Calculate S x : S x = C(i + 1,j)+C(i - 1,j)-2C(i,j)=12 + 3-2(5)=5;

[0071] Calculate S y : S y = C(i,j + 1)+C(i,j - 1)-2C(i,j)=11 + 2-2(5)=3;

[0072] Calculate C new (i,j):

[0073] The results show that the methane concentration at this grid point rises from 5 ppm to 9.8 ppm within one time step, indicating that diffusion causes the concentration to converge towards this point, which is in line with the characteristics of the high-gradient diffusion region. Subsequently, multiple time steps can be iteratively calculated to further analyze the changing trend of methane concentration and determine the potential location of the leakage source. The updated methane concentration data obtained from the calculation are remapped to the original three-dimensional grid to ensure that the new concentration values correspond one-to-one with each grid cell. Then, the updated concentration data are imported into visualization software in CSV, VTK, or NetCDF format to generate a heat map of methane concentration after diffusion optimization.

[0074] Precisely identify potential leakage areas by calculating the methane concentration gradient, effectively avoid misjudgment caused by environmental interference, and improve the accuracy of leakage detection. Set the diffusion coefficient and optimize the concentration data in combination with the partial differential diffusion equation to make the gas diffusion mode more in line with the actual situation and enhance the dynamic adaptability to the leakage trend. At the same time, the optimized heat map can clearly display the concentration distribution, improve the readability of the data and the scientific nature of decision-making, and provide strong support for accurately locating the leakage point and optimizing the inspection strategy.

[0075] Please refer to Figure 4 , and the specific steps for obtaining the methane concentration distribution map after terrain analysis are as follows:

[0076] Collect the three-dimensional terrain point cloud data scanned by the UAV LiDAR, construct the second grid points occupied by the terrain obstacles on the heat map of methane concentration after diffusion optimization according to the three-dimensional terrain point cloud data, and discretize the methane diffusion path around the potential leakage area by using the finite volume method with reference to the position and distribution of the second grid points to generate the processing results of the methane diffusion path;

[0077] First, set the flight altitude, scanning frequency, and laser emission angle of the UAV to ensure coverage of the terrain information of the potential leakage area. During the flight of the UAV, the LiDAR device emits laser pulses and measures the time difference of the returned signals to obtain the three-dimensional coordinate information of the terrain surface. After the data collection, the point cloud is position-corrected by combining the inertial measurement unit (IMU) and global navigation satellite system (GNSS) data of the UAV to ensure that the error of spatial positioning is within the set threshold range. Subsequently, the abnormal points are removed by using a filtering method, and the terrain obstacle area is extracted based on the distribution characteristics of the point cloud. The judgment criterion is the joint threshold setting of the point cloud density and elevation change. If the point cloud density in a certain area exceeds 500 points / m 2If the elevation change exceeds 2m, it is determined that there are topographic obstacles in the area. According to the spatial occupancy of the point cloud data, the second grid points of the topographic obstacle spatial occupancy are constructed on the methane concentration heat map after diffusion optimization. The grid is divided into units of a fixed 1m×1m×1m. The occupancy state of each unit is determined by the point cloud density. If the point cloud density exceeds the set threshold, it is marked as an obstacle; otherwise, it is marked as idle. After completing the grid construction, according to the position and distribution of the second grid points, the finite volume method (FVM) is used to discretize the methane diffusion path around the potential leakage area. First, the computational domain is divided, and the boundary conditions between the grids are set. Inside each grid unit, the mass conservation equation is applied to calculate the gas concentration, and the flux exchange between the grids is adjusted according to the wind speed, wind direction, and terrain influence. Finally, the discretized diffusion path data is stored.

[0078] Obtain the real-time wind speed, wind direction, temperature, and humidity data corresponding to the topographic obstacle area in the methane diffusion path processing results, analyze the total flow deviation of methane in the topographic obstacle area, and set the methane concentration attenuation coefficient of the second grid points of the obstacle spatial occupancy according to the total flow deviation.

[0079] For analyzing the total flow deviation of methane in the topographic obstacle area, the formula: Calculate the normalized deviation ΔD of the current wind speed in the topographic obstacle area relative to the historical wind speed range of the area V , and the numerical range is from 0 to 1. The larger the value, the stronger the influence of the wind speed on methane diffusion. If ΔD V is close to 1, it indicates that the current wind speed is close to the historical maximum wind speed of the area, which is conducive to methane diffusion. If ΔD V is close to 0, it indicates that the wind speed is low and the diffusion ability is weak; where V is the real-time wind speed, obtained through a wind speed sensor or a weather station; V min , V max are respectively the minimum wind speed and the maximum wind speed (unit: m / s) around the topographic obstacle area. Based on historical meteorological data, the wind speed range in the area is statistically analyzed, usually obtaining data from a meteorological database (such as NOAA or a local meteorological monitoring station) and analyzing the data for the past year to determine the extreme value range.

[0080] Use the formula: ΔD θ =1 - cos(θ - θ0); calculate the deviation degree ΔD of the current wind direction in the topographic obstacle area from the main methane diffusion direction θ , and the numerical range is from 0 to 2. The larger the value, the greater the wind direction deviation, and the main direction of methane diffusion is more interfered. If ΔD θ =0, it indicates that the wind directions are exactly the same, which is conducive to the propagation of methane along the main diffusion path; if ΔD θ≈2 indicates that the wind directions are completely opposite and the diffusion is strongly inhibited. Here, θ is the real-time wind direction (unit: °), obtained through a wind direction sensor or a weather station, and θ0 is the main diffusion direction (unit: °), obtained by statistically analyzing the long-term average dominant wind direction between the methane leakage point and the surrounding air currents in combination with historical wind direction data. A wind rose diagram can be used to analyze the wind direction changes in the past month or year, and the main wind direction is taken as θ0.

[0081] Use the formula: Calculate the normalized deviation ΔD of the temperature in the current terrain obstacle area from the preset reference temperature T , with a numerical range from 0 to 1. The larger the value, the more obvious the influence of temperature on diffusion. The main ways in which temperature affects diffusion are by changing air density and turbulence intensity. If ΔD T = 0, it indicates that the temperature is close to the reference value and the temperature influence is small; if ΔD T = 1, it indicates that the temperature is in an extreme range, which may lead to abnormal diffusion patterns (such as thermal convection or temperature inversion layers). Here, T is the real-time temperature (unit: K), obtained through a temperature sensor or a weather station, T ref is the standard temperature (unit: K), set according to environmental standards, usually based on 298K (25°C), T min , T max are respectively the minimum and maximum temperatures (unit: K) in the monitoring area, based on the statistical temperature range in the area from historical meteorological data, usually obtained from a meteorological database, and analyzing the highest and lowest temperatures in the past year.

[0082] Use the formula: Calculate the normalized deviation ΔD of the humidity in the current terrain obstacle area from the preset reference humidity H , with a numerical range from 0 to 1. The larger the value, the greater the influence of humidity on diffusion. The ways in which humidity affects diffusion include changing the buoyancy of air and affecting the particle sedimentation rate, etc. If ΔD H = 0, it indicates that the humidity is close to the reference value and the influence is small; if ΔD H = 1, it indicates that the humidity is in an extreme range, which may affect the detection of methane concentration. Here, H is the real-time humidity (unit: %), obtained through a humidity sensor or a weather station, H ref is the reference humidity (unit: %), usually with 50% as the reference humidity, and the average humidity is taken as the reference value, H min , H max are respectively the minimum and maximum humidities (unit: %) in the monitoring area, analyzing the historical humidity range from meteorological data, usually obtained from meteorological monitoring station data, and analyzing the humidity changes in the past year.

[0083] Use the formula: ΔD' = w V ΔD V + w θΔD θ +w T ΔD T +w H ΔD H ; Calculate the total flow deviation ΔD'; where, w V 、w θ 、w T 、w H respectively represent the relative influence weights of wind speed, wind direction, temperature, and humidity on methane diffusion.

[0084] Use the formula: k = k0×(1 - ΔD); Calculate the methane concentration decay coefficient k; where, k0 is the preset basic decay term according to the current terrain obstacle area (unit: m -1 ), which is determined by the characteristics of terrain obstacles.

[0085] Assume the real-time monitoring data are: wind speed: V = 5.5 m / s, wind direction: θ = 210°, temperature: T = 305 K, humidity: H = 65%. Historical range data: V min = 1.2, V max = 8.0 m / s, θ0 = 200°, T min = 280, T max = 320 K, H min = 30%, H max = 90%. The basic decay coefficient is set as:

[0086] k0 = 0.08 m -1 , where, the basic decay coefficient k0 is mainly determined by the characteristics of terrain obstacles, reflecting the initial hindrance effect of obstacles on methane diffusion. The setting basis is as follows: when the obstacle density is high (such as high-rise buildings, mountains, etc.), the air circulation is restricted, the diffusion resistance is large, and k0 takes a higher value (0.1 - 0.2 m -1 ). When the obstacle density is low (such as open plains, open waters, etc.), the diffusion is less hindered, and k0 takes a lower value (0.02 - 0.08 m -1 ). Rough terrain (such as forests, hills, etc.) forms more turbulence, making the diffusion path more complex, and the k0 value is higher. Flat ground (such as deserts, airport runways, etc.) has smoother diffusion, and the k0 value is lower. Measure the methane concentration decay under different terrains through wind tunnel experiments, and fit the k0 value. Use computational fluid dynamics (CFD) to simulate the diffusion mode under different wind speeds, temperatures, and humidities, calculate the k0 adapted to a specific environment, and correct it through actual measurement data.

[0087] Calculate the wind speed deviation: Calculate the wind direction deviation: ΔD θ = 1 - cos(210° - 200°) = 0.0152; Calculate the temperature deviation Calculate the humidity deviation The calculation results show that the influence of wind speed is the greatest (deviation 0.632). A higher wind speed plays a greater role in promoting diffusion, so its weight is set to the highest (w V = 0.3). The influence of wind direction is the smallest (deviation 0.0152), indicating that the wind direction is very close to the main diffusion direction, so its weight is the lowest (w θ = 0.2). The influences of temperature and humidity are moderate (deviations 0.175 and 0.25), so both are given relatively high weights (w T = 0.25, w H = 0.25), and the sum of the weights is 1, which is dynamically set according to the actual situation.

[0088] Calculate the total flow deviation: ΔD' = (0.3×0.632)+(0.2×0.0152)+(0.25×0.175)+0.25×0.25) = 0.299.

[0089] Calculate the methane concentration decay coefficient: k = 0.08×(1 - 0.299) = 0.0561m -1 .

[0090] The final decay coefficient k drops to 0.0561m -1 , indicating that due to the higher wind speed, the diffusion path is elongated and the decay rate of methane concentration slows down (the diffusion range expands). In addition, if the wind speed is low or the wind direction deviates greatly from the main diffusion direction, the total flow deviation ΔD' increases, resulting in a smaller decrease in the methane concentration decay coefficient k and a smaller diffusion range, and the methane concentration is more likely to accumulate in local areas. According to the wind speed range 1.2 ≤ V ≤ 8.0m / s, if V < 3.0m / s, then the wind speed deviation ΔD V > 0.7, which causes ΔD' to rise, resulting in k approaching the basic decay coefficient k0 and the diffusion path being restricted. If the deviation of the wind direction from the main diffusion direction exceeds 30°, then the wind direction deviation ΔD θ > 0.5, which causes ΔD' to increase and the diffusion path to deviate severely. If the temperature is higher than the standard value and the wind speed is large, the air convection increases, and ΔD T depends on T min = 280K and T max = 320K. If T > 310K, then ΔD T > 0.5, resulting in a decrease in ΔD' and k being lower than the basic decay coefficient k0, and the diffusion range expands. If the temperature is close to the reference value of 298K, then ΔD T < 0.2, and ΔD' is mainly determined by the wind speed and wind direction, and the influence of temperature on diffusion is small. In a high-humidity environment, with the humidity range 30% ≤ H ≤ 90%, if H > 80%, then ΔD H> 0.5, which causes ΔD' to increase and k to decrease slowly, leading to the accumulation of methane in the near-surface layer. If the humidity is close to 50%, ΔD H < 0.2, the influence of humidity is small, and ΔD' is mainly controlled by wind speed and direction. The diffusion pattern is similar to that under low humidity conditions. If the terrain is complex, such as a canyon or a high-density building area, where the wind speed and direction fluctuate greatly, ΔD' may vary significantly in different regions, resulting in uneven high and low values of k within a local range. If the height of the terrain obstacle is greater than 10 m, the air flow is disturbed, causing different values of ΔD V and ΔD θ in the calculation results. Eventually, the variation range of k increases, manifested as rapid diffusion of methane in some regions while the concentration remains at a relatively high level for a long time in other regions.

[0091] According to the methane concentration decay coefficient, analyze the methane concentration values corresponding to the first grid point of the potential leakage area to the second grid point occupied by the terrain obstacle in space, and generate a methane concentration distribution map after terrain analysis;

[0092] Analyze the methane concentration value C corrected , using the formula: C corrected = C new (i,j)×e -k×d ;

[0093] where d is the distance from the first grid point corresponding to the potential leakage area to the second grid point occupied by the terrain obstacle in space, e is the base of the exponential function to keep the decay rate changing smoothly, and k represents the methane concentration decay coefficient.

[0094] Substitute the values into the formula: C corrected = 9.8×e -0.0561×50 ≈ 0.593 ppm.

[0095] After considering the influence of the terrain obstacle, the methane concentration value C corrected from the first grid point corresponding to the potential leakage area to the second grid point occupied by the terrain obstacle in space is 0.593 ppm, indicating the significant hindrance effect of the obstacle on methane diffusion. On the methane concentration heat map after diffusion optimization, add the methane concentration value from the first grid point corresponding to the potential leakage area to the second grid point of the terrain obstacle, and use unified visualization software (such as ParaView, Tecplot, or MATLAB) to present the complete methane concentration distribution after terrain correction, generating a methane concentration distribution map after terrain analysis.

[0096] Precise three-dimensional terrain data is obtained through UAV LiDAR scanning. Combining with the methane concentration heat map optimized by diffusion, a spatial occupancy model of terrain obstacles is constructed to make gas diffusion analysis more in line with the actual terrain characteristics. The finite volume method is used to discretize the diffusion path to ensure more refined gas flow calculation, which helps to reduce misjudgment caused by complex terrain. Analyze the flow deviation in combination with real-time environmental parameters (wind speed, wind direction, temperature, humidity), and set the concentration attenuation coefficient to make the change trend of gas concentration more in line with the actual diffusion law. The finally generated methane concentration distribution map after terrain analysis can more accurately reflect the diffusion situation in the leakage area, providing a more scientific basis for leakage risk assessment and early warning.

[0097] Please refer to Figure 5 , and the steps for obtaining the diffusion trend prediction result are specifically as follows:

[0098] Identify the diffusion direction of methane around the potential leakage area in the methane concentration distribution map after terrain analysis, and generate the methane diffusion direction analysis result;

[0099] Obtain the concentration data of the first grid point in the potential leakage area and its surrounding grids, call the GIS spatial analysis tool, screen out the matching historical wind field conditions from the known wind speed and wind direction data, and combine with the spatial distribution of terrain obstacles to determine the influence range of the dominant wind direction on methane diffusion. Within a specific time step, track the change of methane concentration through time series data, observe the movement trajectory of the high-concentration area with the wind direction, extract the methane concentration values in multiple time periods according to the UAV cruise data, superimpose and compare the concentration distributions at different times, and judge the direction trend of methane diffusion. Further, screen out the representative diffusion directions. Suppose in a certain scenario, the terrain is a valley terrain, the wind speed is about 5 m / s, and the wind direction is west by southwest. After methane leakage, its main diffusion direction will spread along the valley low-lying area to east by northeast. In an open terrain, due to the wider diffusion range of the air flow, the diffusion direction of methane concentration may be more uniform. Finally, superimpose the obtained diffusion direction information on the original methane concentration distribution map after terrain analysis in the form of arrow marks to ensure the visualization of the diffusion trend around the potential leakage area.

[0100] Based on the methane diffusion direction analysis result, obtain all the records of historical methane leakage, and combine with the turbulent diffusion theory to predict the change trend of methane concentration in the future time, and generate the diffusion trend prediction result;

[0101] First, call the historical leakage data repository to screen historical cases that meet the current terrain, wind speed, wind direction, relative humidity and other conditions, and extract the methane concentration data of the corresponding time period. Perform time series analysis on the selected data, remove data outliers and sensor failure points, and ensure data integrity. Then, organize the screened data in chronological order, observe the changing trend of methane concentration, combine turbulent diffusion theory, use ANSYS Fluent or OpenFOAM for simulation, import LiDAR scanned terrain data, perform air flow analysis based on the k-ε turbulence model, set boundary conditions, including inlet wind speed, wind direction, leakage source concentration, and surface roughness, and import historical leakage source location data. Observe the movement trajectory of the leaked gas through the Lagrangian particle tracking method, use ParaView for visualization, compare the concentration changes at different time steps, and screen out the diffusion trend that matches the current environmental conditions. Further, store the predicted concentration changes in chronological order to generate diffusion trend prediction results, so that the possible path of methane diffusion in the future can be clearly presented.

[0102] By identifying the diffusion direction of methane, the diffusion trend of the leakage area is made more intuitive, which helps to accurately determine the movement path of the gas. Combining historical leakage data and turbulent diffusion theory, the trend of future changes in methane concentration is predicted, and the ability to predict the evolution of leakage is improved. This process can reduce the impact of environmental interference on diffusion analysis, improve prediction accuracy, enable inspection personnel to identify potential high-risk areas in advance, optimize inspection scheduling, enhance early warning capabilities, and improve the active protection level of gas pipeline leakage detection.

[0103] See also Figure 6 , the specific steps for obtaining the results of gas pipeline leakage hazard identification are as follows:

[0104] Visualize the methane concentration change trend in the future time in the diffusion trend prediction results on the methane concentration distribution map after terrain analysis, identify the concentration of methane in different potential leakage areas, and obtain a methane concentration evolution display map;

[0105] First, call the diffusion trend prediction data, extract the methane concentration values at each time step in the predicted time series, and spatially align the data according to the geographical coordinates to ensure the matching relationship with the original three-dimensional terrain grid. Then, use a GIS visualization tool (such as ArcGIS or QGIS) or a fluid simulation visualization software (such as ParaView or Tecplot) to load the diffusion trend prediction data and set the time stepping parameters so that the visualization interface can display the concentration distribution changes at different times. When specifically presenting, to ensure the readability of the data, set a color gradient mapping scheme, mark the high-concentration areas in red and the low-concentration areas in blue, and use transparency control to avoid the overlapping effect of different concentration intervals. At the same time, to enhance the trend display effect, overlay the wind direction vector field during the visualization process and use the wind field data to drive the dynamic rendering of the diffusion trajectory. At each time step, smooth the concentration data by grid interpolation to reduce the numerical jumps caused by the grid boundaries. Finally, generate a dynamic heat map animation so that users can observe the evolution of methane concentration in the future time.

[0106] Based on the methane concentration change trend in the methane concentration evolution display chart, evaluate the risk level of the current potential leakage area and generate the identification result of gas pipeline leakage hazards.

[0107] First, based on the diffusion trend prediction data, extract the methane concentration change rate within a specific time window and the corresponding spatial distribution range of this change rate. According to the existing leakage trend data, set risk assessment indicators. For example, if the methane concentration in a certain area increases by more than 50% within one time step, it is marked as a high-risk area; if the concentration increase is between 20% - 50%, it is marked as a medium-risk area; and the area with an increase lower than 20% but still significantly higher than the background concentration is marked as a low-risk area. Then, call the historical leakage data, extract the historical leakage events at the same spatial location, calculate the similarity between the current diffusion trend and the historical events, and use the time series comparison method to analyze whether the methane concentration growth rate is abnormal. For example, within one time step, the methane concentration at a certain grid point rises from 5 ppm to 9.8 ppm, with an increase of about 96%, and this area is marked as a high-risk area, while another grid point rises from 5 ppm to 6 ppm, with an increase of 20%, and is marked as a medium-risk area. Subsequently, combine the terrain data to analyze whether the terrain obstacles affect the diffusion direction. If the high-risk area is in the concentrated area of the air duct, the risk level can be appropriately increased; conversely, if it is in a low-lying area, the risk level may decrease. Finally, generate an identification result of gas pipeline leakage hazards, mark the high, medium, and low-risk areas in different colors respectively, and output it to the GIS system or visualization platform.

[0108] By visually displaying the future trend of methane concentration, the dynamic evolution of the leakage area becomes more intuitive, which helps the inspection personnel quickly grasp the gas diffusion situation. Combining the concentration aggregation characteristics to analyze the leakage risk level can improve the accuracy and pertinence of potential hazard identification, and reduce the possibility of false alarms and missed alarms. Finally, based on the leakage hazard identification results generated by the dynamic risk assessment, it provides a scientific basis for the inspection decision-making, enhances the early warning ability and emergency response efficiency of the gas pipeline inspection, and thus more effectively prevents potential safety risks.

[0109] The above are only the preferred embodiments of the present invention, and the present invention is not limited to other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent identification system for abnormal hidden dangers in pipeline inspection based on drones, characterized in that: The system includes: The methane concentration detection module collects the UAV flight data to construct a first grid in the three-dimensional space, evenly divides the first grid into a plurality of first grid points, and maps the methane concentration value of each first grid point according to the measured laser absorption spectrum data to generate a methane concentration heat map; The concentration data smoothing module reads all methane concentration values ​​in the methane concentration heat map and calculates the local methane concentration gradient of each first grid point. According to the local methane concentration gradient, it marks the potential leakage area and sets the diffusion coefficient corresponding to the first grid point to update the methane concentration value, thus generating a diffusion-optimized methane concentration heat map. The virtual diffusion field reconstruction module constructs the second grid point occupied by the terrain obstacle space on the methane concentration heat map after diffusion optimization, sets the methane concentration attenuation coefficient of the second grid point, analyzes the methane concentration value from the first grid point to the second grid point according to the methane concentration attenuation coefficient, and generates a methane concentration distribution map after terrain analysis; The leakage trend prediction module predicts the changing trend of methane around the potential leakage area in the methane concentration distribution map after terrain analysis, and generates the diffusion trend prediction result; The leakage risk assessment module identifies the changing trend of methane in the diffusion trend prediction results and visualizes it on the methane concentration distribution map after terrain analysis, generating gas pipeline leakage hazard identification results.

2. The pipeline inspection abnormal hidden danger intelligent identification system based on drone according to claim 1 is characterized in that: The steps for obtaining the methane concentration thermal map are specifically as follows: Collecting UAV flight data, including UAV location information and flight trajectory data along the gas pipeline area, determining the three-dimensional coordinates of all measurement points, integrating the three-dimensional coordinates of all measurement points to construct a first grid in the three-dimensional space, evenly dividing the first grid into a plurality of first grid points, and generating a first grid division result; Acquire terrain height data, adjust the first grid points divided in the first grid division result to match the current terrain structure, collect laser absorption spectrum data measured by a methane laser telemeter on the UAV, analyze the methane concentration in the air according to the laser absorption spectrum data, and generate a methane concentration value; The gaps in the methane concentration values ​​between the measurement points are filled by an interpolation method and mapped to each first grid point in the three-dimensional space to generate a methane concentration heat map.

3. The pipeline inspection abnormal hidden danger intelligent identification system based on drone according to claim 1 is characterized in that: The steps for obtaining the methane concentration thermodynamic map after the diffusion optimization are specifically as follows: Reading all methane concentration values ​​in the methane concentration thermodynamic map, and calculating the local methane concentration gradient of each first grid point, comparing the local methane concentration gradient with a preset change threshold, marking a potential leakage area where the local methane concentration gradient exceeds the change threshold, and generating a potential leakage area marking result; The diffusion coefficient of the first grid point corresponding to the potential leakage area is set based on the local methane concentration gradient of each potential leakage area corresponding to the first grid point in the potential leakage area marking result, and the methane concentration value of the first grid point corresponding to the potential leakage area is updated through the partial differential diffusion equation according to the diffusion coefficient to generate a methane concentration thermodynamic map after diffusion optimization.

4. The pipeline inspection abnormal hidden danger intelligent identification system based on drone according to claim 3 is characterized in that: Through the partial differential diffusion equation, the formula is adopted: Calculate the updated methane concentration value C corresponding to the first grid point (i, j) in the potential leakage area new (i,j); Where C(i,j) is the methane concentration value corresponding to the first grid point (i,j) in the potential leakage area, D(i,j) is the diffusion coefficient set according to the first grid point in the potential leakage area, Δx, Δy are the grid steps along the x and y directions of the first grid point in the potential leakage area, Δt is the time step set according to the grid step, S x is the Laplace term of the methane concentration along the x direction at the first grid point corresponding to the potential leakage area, S y is the Laplace term of the methane concentration along the y direction at the first grid point corresponding to the potential leakage area, and Both factors are dimensionless and represent the proportion of the contribution of diffusion to the concentration update during that time step.

5. The pipeline inspection abnormal hidden danger intelligent identification system based on drone according to claim 1 is characterized in that: The steps for obtaining the methane concentration distribution map after the terrain analysis are specifically as follows: Collecting three-dimensional terrain point cloud data scanned by UAV LiDAR, constructing a second grid point occupied by the terrain obstacle space on the methane concentration heat map after the diffusion optimization according to the three-dimensional terrain point cloud data, and discretizing the methane diffusion path around the potential leakage area by using the finite volume method with reference to the position and distribution of the second grid point, and generating a methane diffusion path processing result; Obtain the real-time wind speed, wind direction, temperature, and humidity data of the terrain obstacle area corresponding to the methane diffusion path processing results, analyze the total flow deviation of methane in the terrain obstacle area, and set the methane concentration attenuation coefficient of the second grid point occupied by the obstacle space according to the total flow deviation; The methane concentration value from the first grid point corresponding to the potential leakage area to the second grid point occupied by the terrain obstacle space is analyzed according to the methane concentration attenuation coefficient to generate a methane concentration distribution map after terrain analysis.

6. The pipeline inspection abnormal hidden danger intelligent identification system based on drone according to claim 5 is characterized in that: The analysis of the total flow deviation of methane in the terrain obstacle area adopts the formula: ΔD'=w V ΔD V +in θ ΔD θ +in T ΔD T +in H ΔD H The total flow deviation ΔD' is calculated; Among them, w V 、w θ 、w T 、w H Respectively represent the relative influence weights of wind speed, wind direction, temperature and humidity on methane diffusion, ΔD V is the normalized deviation of the wind speed in the current terrain obstacle area relative to the historical wind speed range in the area, ΔD θ is the deviation between the wind direction in the current terrain obstacle area and the main diffusion direction of methane, ΔD T is the normalized deviation between the current terrain obstacle area temperature and the preset reference temperature, ΔD H It is the normalized deviation of the humidity in the current terrain obstacle area from the preset reference humidity.

7. The pipeline inspection abnormal hidden danger intelligent identification system based on drone according to claim 1 is characterized in that: The steps for obtaining the diffusion trend prediction result are specifically as follows: Identifying the diffusion direction of methane around the potential leakage area in the methane concentration distribution map after the terrain analysis, and generating a methane diffusion direction analysis result; Based on the methane diffusion direction analysis results, all records of historical methane leakage are obtained, and the changing trend of methane concentration in the future is predicted in combination with turbulent diffusion theory to generate diffusion trend prediction results.

8. The pipeline inspection abnormal hidden danger intelligent identification system based on drone according to claim 1 is characterized in that: The steps for obtaining the gas pipeline leakage hidden danger identification result are specifically as follows: Visually display the methane concentration change trend in the future time in the diffusion trend prediction result on the methane concentration distribution map after the terrain analysis, identify the aggregation of methane concentration in different potential leakage areas, and obtain a methane concentration evolution display map; Based on the methane concentration change trend in the methane concentration evolution display diagram, the risk level of the current potential leakage area is evaluated, and a gas pipeline leakage hazard identification result is generated.

Images