Coal yard safety analysis system based on infrared imaging and point cloud data fusion

Abstract

The invention discloses a coal yard safety analysis system based on infrared imaging and point cloud data fusion, and particularly relates to the technical field of safety analysis. According to the method, infrared imaging data and three-dimensional point cloud data are collected on the surface of a coal pile, an initial emissivity distribution diagram is constructed, a plurality of local grid areas are divided, and image texture features and surface structure information of each local grid area are extracted. And generating a corrected emissivity distribution diagram through local dynamic compensation on the initial emissivity. And identifying an abnormal region according to the corrected emissivity map, marking the abnormal region as a potential risk region, and evaluating the time dependency of heat diffusion by constructing a heat transfer diffusion model. And evaluating the balance degree of heat distribution in the potential risk area by adopting a fractal analysis method. Based on the time dependency and the spatial heterogeneity of heat diffusion, the safety risk level of the coal yard is evaluated, safety early warning information of the coal yard is generated, and emissivity correction and thermal risk accurate evaluation of the multi-state coal in the mixed coal pile are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of safety analysis, and more specifically, to a coal yard safety analysis system based on the fusion of infrared imaging and point cloud data. Background Art

[0002] In coal yard safety monitoring, an infrared thermal imager is often used to monitor the temperature of the coal pile surface to identify potential spontaneous combustion hazards or thermal anomaly areas. The accuracy of infrared temperature measurement highly depends on the setting of the emissivity of the measured object's surface. As a material with complex components and variable states, the emissivity of coal varies significantly with different types, batches, weathering degrees, and moisture contents in the actual scenario, and shows spatial inhomogeneity and time-varying characteristics.

[0003] In the prior art, a unified emissivity setting method is usually adopted without combining point cloud data, which will cause significant local temperature estimation deviation when dealing with mixed coal piles, and even affect the accuracy of the judgment of thermal anomaly risks.

[0004] To solve the above problems, a technical solution is provided now. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a coal yard safety intelligent analysis method and system based on the fusion of infrared imaging and point cloud data to solve the problems raised in the above background art.

[0006] To achieve the above object, the present invention provides the following technical solutions: A coal yard safety analysis system based on the fusion of infrared imaging and point cloud data, comprising: The data acquisition module collects infrared imaging data and three-dimensional point cloud data on the coal pile surface, performs multi-source information fusion processing on the infrared imaging data and the three-dimensional point cloud data, and generates an initial emissivity distribution map of the coal pile surface; The grid division module divides the coal pile surface into multiple local grid regions based on the initial emissivity distribution map, and extracts the texture features and surface structure information of each local grid region; The emission correction module performs local dynamic compensation on the initial emissivity distribution map based on the texture features and surface structure information, and generates a corrected emissivity distribution map; The anomaly detection module identifies the abnormal regions on the coal pile surface according to the corrected emissivity distribution map and marks them as potential risk regions; The diffusion evaluation module analyzes the heat distribution characteristics in the potential risk region through a heat transfer diffusion model and evaluates the time dependence of heat diffusion; The fractal evaluation module evaluates the degree of balance of heat distribution in the potential risk region through a fractal analysis method; The risk warning module evaluates the safety risk level of the coal yard based on the time dependence of heat diffusion and the degree of heat distribution balance, and generates coal yard safety warning information.

[0007] In a preferred embodiment, infrared imaging data and three-dimensional point cloud data are collected on the surface of the coal pile, and multi-source information fusion processing is performed on the infrared imaging data and the three-dimensional point cloud data to generate an initial emissivity distribution map of the coal pile surface, specifically: Use an infrared thermal imaging device to collect infrared imaging data on the surface of the coal pile to obtain an infrared radiation intensity distribution image; Use a three-dimensional laser scanning device to collect spatial position coordinate data and spatial surface structure feature data on the surface of the coal pile to obtain three-dimensional point cloud data of the coal pile surface; Perform spatial coordinate alignment and timestamp alignment on the infrared radiation intensity distribution image and the three-dimensional point cloud data to establish a mapping relationship between infrared image pixel points and point cloud coordinate points; Based on the mapping relationship between infrared image pixel points and point cloud coordinate points, generate an initial emissivity distribution map of the coal pile surface.

[0008] In a preferred embodiment, based on the initial emissivity distribution map, the surface of the coal pile is divided into multiple local grid regions, and the texture features and surface structure information of each local grid region are extracted, specifically: Determine the local spatial boundary of the coal pile surface based on the initial emissivity distribution map, and divide the coal pile surface into multiple local grid regions; For each local grid region, extract surface structure information based on the three-dimensional point cloud data; For each local grid region, extract texture features based on the infrared radiation intensity distribution image.

[0009] In a preferred embodiment, local dynamic compensation is performed on the initial emissivity distribution map based on the texture features and surface structure information to generate a corrected emissivity distribution map, specifically: Establish a mapping relationship between each local grid region in the initial emissivity distribution map and the corresponding texture features and surface structure information; Within each local grid region, construct a spatial structure model according to the three-dimensional point cloud data; Within each local grid region, construct an image texture feature model according to the infrared radiation intensity distribution image; Perform joint fitting on the spatial structure model and the image texture feature model to obtain an emissivity adjustment factor for each local grid region; Based on the emissivity adjustment factor of each local grid region, perform local dynamic compensation on the original emissivity value to generate a corrected emissivity distribution map.

[0010] In a preferred embodiment, the abnormal areas on the surface of the coal pile are identified according to the corrected emissivity distribution map and marked as potential risk areas, specifically as follows: Perform spatial neighborhood analysis on the corrected emissivity distribution map to determine the local statistical threshold of the emissivity within each local grid area; Based on the local statistical threshold, determine the degree of abnormal deviation of the emissivity within each local grid area, and generate emissivity anomaly intensity data; According to the emissivity anomaly intensity data, determine the spatial position boundary of the abnormal area on the surface of the coal pile; Perform spatial connectivity division on the abnormal area on the surface of the coal pile to determine the overall spatial range of the abnormal area; Mark the overall spatial range of the abnormal area to obtain the potential risk area.

[0011] In a preferred embodiment, analyze the heat distribution characteristics within the potential risk area through a heat transfer diffusion model and evaluate the time dependence of heat diffusion, specifically as follows: Based on the overall spatial range of the potential risk area, establish a heat transfer diffusion model; According to the heat transfer diffusion model, perform numerical simulation of heat diffusion on the potential risk area to determine the heat distribution data of each local grid area within the potential risk area; Based on the heat distribution data of each local grid area within the potential risk area, analyze the heat diffusion trend; According to the heat diffusion trend, evaluate the time dependence of heat diffusion within the potential risk area to obtain the time characteristic data of heat diffusion.

[0012] In a preferred embodiment, evaluate the degree of balance of heat distribution within the potential risk area through a fractal analysis method, specifically as follows: Extract the heat distribution data of each local grid area within the potential risk area; Map the heat distribution data of each local grid area within the potential risk area into a spatial heat distribution matrix; Perform multi-scale fractal dimension calculation on the spatial heat distribution matrix to obtain a fractal dimension sequence of the potential risk area at different spatial scales; According to the change trend of the fractal dimension sequence, evaluate the spatial balance degree of heat distribution within the potential risk area to obtain the spatial characteristic data of heat diffusion.

[0013] In a preferred embodiment, based on the time dependence of heat diffusion and the degree of balance of heat distribution, evaluate the safety risk level of the coal yard and generate coal yard safety warning information, specifically as follows: Perform eigenvector splicing based on the heat diffusion time characteristic data and the heat diffusion spatial characteristic data to obtain a comprehensive risk assessment input data set, Based on a preset coal yard risk assessment model, combined with the comprehensive risk assessment input data set, perform the risk level assessment of potential risk areas and output the risk level values of potential risk areas; According to the risk level values, divide the potential risk areas into different risk levels to generate a risk level map of potential risk areas; Generate corresponding coal yard safety warning information according to the risk level map.

[0014] The technical effects and advantages of a coal yard safety analysis system based on the fusion of infrared imaging and point cloud data according to the present invention: By fusing infrared imaging data and three-dimensional point cloud data to generate an initial emissivity distribution map, the basic characterization accuracy of the thermal characteristics of coal piles is improved; by dividing the coal pile into local grid areas and extracting texture and structural features, the perception of spatial fine-grained differences is realized; based on local features to dynamically compensate the emissivity, the temperature measurement deviation problem caused by a single emissivity setting is solved; by identifying abnormal areas through the corrected emissivity map, the accuracy of high-temperature hidden danger location is enhanced; using the heat transfer diffusion model to analyze the time dependence, the prediction of the risk development trend is realized; using fractal analysis to evaluate the spatial heterogeneity, the discrimination ability of complex thermal distribution structures is improved; finally, based on the time dependence of heat diffusion and the degree of balance of heat distribution, the risk level of the coal yard is evaluated and warning information is generated, enhancing the response ability and early identification ability for abnormal states of complex coal piles. Description of the Drawings

[0015] Figure 1 It is a structural schematic diagram of a coal yard safety analysis system based on the fusion of infrared imaging and point cloud data according to the present invention. Detailed Embodiments

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] Embodiment 1

[0018] Figure 1 A coal yard safety analysis system based on the fusion of infrared imaging and point cloud data according to the present invention is provided, including: The data acquisition module collects infrared imaging data and three-dimensional point cloud data on the surface of the coal pile, performs multi-source information fusion processing on the infrared imaging data and three-dimensional point cloud data, and generates an initial emissivity distribution map of the surface of the coal pile; Based on the initial emissivity distribution map, the mesh generation module divides the surface of the coal pile into multiple local mesh regions, and extracts the texture features and surface structure information of each local mesh region; The emission correction module performs local dynamic compensation on the initial emissivity distribution map based on the texture features and surface structure information to generate a corrected emissivity distribution map; The anomaly detection module identifies the abnormal regions on the surface of the coal pile according to the corrected emissivity distribution map and marks them as potential risk regions; The diffusion evaluation module analyzes the heat distribution characteristics in the potential risk regions through a heat transfer diffusion model and evaluates the time dependence of heat diffusion; The fractal evaluation module evaluates the degree of balance of heat distribution in the potential risk regions through a fractal analysis method; Based on the time dependence of heat diffusion and the degree of balance of heat distribution, the risk warning module evaluates the safety risk level of the coal yard and generates coal yard safety warning information.

[0019] Specifically, infrared imaging data and three-dimensional point cloud data are collected on the surface of the coal pile, and the multi-source information fusion processing is performed on the infrared imaging data and the three-dimensional point cloud data to generate the initial emissivity distribution map of the surface of the coal pile, including: Use an infrared thermal imaging device to collect the infrared imaging data of the surface of the coal pile to obtain an infrared radiation intensity distribution image; Specifically, a high-resolution infrared thermal imaging device is used to continuously capture the surface of the coal pile at a fixed sampling frequency to obtain an infrared radiation intensity image covering all regions of the surface of the coal pile. At least five image samplings are performed at each position, and the average value of the five image sampling data is calculated to obtain the infrared radiation intensity distribution value at each position, so as to reduce the random error caused by environmental factors and improve the data reliability. The data collected by the infrared thermal imaging device is an infrared radiation intensity distribution image in a two-dimensional space. Each pixel point of the infrared radiation intensity distribution image corresponds to a specific position in the real space on the surface of the coal pile.

[0020] Use a three-dimensional laser scanning device to collect the spatial position coordinate data and spatial surface structure feature data of the surface of the coal pile to obtain the three-dimensional point cloud data of the surface of the coal pile; Specifically, a laser pulse is emitted to the surface of the coal pile through a three-dimensional laser scanning device, and the flight time of the laser pulse from emission to return is measured. Then, the actual spatial distance of the corresponding position on the surface of the coal pile is obtained by dividing the product of the speed of light and the flight time by two. The laser scanning device scans with a spatial accuracy of millimeters, and a three-dimensional coordinate data of a spatial point is generated at each scanning position. The three-dimensional space coordinate data point cloud set of all regions on the surface of the coal pile is obtained by continuously scanning.

[0021] Perform spatial coordinate alignment and timestamp alignment on the infrared radiation intensity distribution image and the three-dimensional point cloud data to establish the mapping relationship between the infrared image pixel points and the point cloud coordinate points; Specifically, the infrared radiation intensity distribution image is two-dimensional spatial data, and the point cloud data is three-dimensional spatial data. Therefore, a spatial mapping algorithm is needed to correspond the pixels of the two-dimensional infrared radiation intensity distribution image with the three-dimensional spatial coordinates. The spatial mapping algorithm is specifically as follows: According to the spatial coordinates of the three-dimensional point cloud data and the preset scanning view angle parameters of the three-dimensional laser scanning device, project each spatial coordinate point onto the two-dimensional image plane to determine the correspondence between each point cloud coordinate point and the infrared image pixel position. The high-precision time synchronization protocol is used to ensure that the acquisition of the infrared image and the point cloud data is completed at the same time node, and each spatial coordinate point and the infrared image pixel point have the same timestamp to ensure the effectiveness of spatial alignment and temporal synchronization. Through the dual calibration of spatial coordinates and timestamps, the data matching accuracy during the fusion process can be ensured.

[0022] Based on the mapping relationship between the infrared image pixel points and the point cloud coordinate points, generate the initial emissivity distribution map of the coal pile surface; Specifically, the calculation of the initial emissivity is based on the object infrared radiation theory, and the specific value of the emissivity is determined by the relationship between the infrared radiation intensity and the surface temperature and ambient temperature of the coal pile. Specifically: Obtain the infrared radiation intensity of each pixel point by using the infrared radiation intensity distribution image, based on the spatial characteristics of the coal pile surface determined by the point cloud data and the temperature distribution at the corresponding position, considering the surface temperature distribution and ambient temperature conditions of the coal pile, and use the principle of conservation of infrared radiation energy for conversion to obtain the initial emissivity value of each spatial position. The calculation method is specifically as follows: The initial emissivity value is equal to the ratio of the infrared radiation intensity to the blackbody radiation intensity value at the corresponding surface position. The blackbody radiation intensity value is calculated by combining the temperature value at the corresponding surface position with Planck's radiation law. Obtain the initial emissivity value of each position on the coal pile surface through the above method, and draw a complete initial emissivity distribution map of the coal pile surface according to the spatial coordinate position.

[0023] Specifically, based on the initial emissivity distribution map, divide the coal pile surface into multiple local grid regions, and extract the texture features and surface structure information of each local grid region, including: Determine the local spatial boundary of the coal pile surface based on the initial emissivity distribution map, and divide the coal pile surface into multiple local grid regions; Specifically, the spatial coordinate range corresponding to the coal pile surface is obtained based on the initial emissivity distribution map, and the minimum bounding rectangle is determined. The minimum bounding rectangle is divided into two-dimensional grids according to the equal spacing division rule to ensure that the coal pile surface covered by each grid area is continuous in spatial distribution and has no overlap. During the division process, the minimum side length of a single grid area is set to several times the minimum effective ranging unit of the three-dimensional laser scanning device to avoid the loss of structural details due to insufficient spatial resolution. The grid numbers after division are identified using a row and column numbering system, and the initial emissivity value set corresponding to each grid area is extracted as input data for feature analysis.

[0024] For each local mesh area, surface structure information is extracted based on 3D point cloud data; Specifically, in each divided local grid area, all three-dimensional point cloud coordinate data within the coverage area of the local grid area are extracted. Local geometric structure calculation is performed within each set of three-dimensional point cloud coordinate data to obtain the spatial structure feature information of the surface of the local grid area: Calculate the direction of the spatial normal vector: Within each point cloud subset, the least squares plane fitting method is used to perform local plane approximation modeling on the point set, and then the regional normal vector is determined based on the vertical direction vector of the fitting plane to reflect the inclination direction of the coal pile surface in the area.

[0025] Calculate the local curvature change value: calculate the surface curvature of the grid area based on the change amplitude of the spatial normal vector distribution. The curvature calculation adopts the weighted average method based on the change amount of the normal vector angle of the point cloud tangent plane. The more drastic the angle change, the higher the curvature, which reflects whether there are abnormal protrusions or depressions on the surface structure of the coal pile.

[0026] Counting point cloud density: Counting the number of point clouds per unit area to determine the integrity and visibility of the structural information in the area. Areas with too low point cloud density will be marked as incomplete feature areas.

[0027] For each local grid area, texture features are extracted based on the infrared radiation intensity distribution image; Specifically, grayscale normalization is performed on the image area corresponding to each local grid area in the initial emissivity distribution map to eliminate errors caused by device response offset and brightness non-uniformity.

[0028] Based on the standard texture analysis method, the following feature extraction operations are performed on each local grid area in the image: Calculate the grayscale co-occurrence matrix: construct a two-dimensional grayscale relationship matrix based on the image grayscale difference to reflect the grayscale correlation between pixels in the area; Extract texture contrast parameters: Calculate the image clarity change trend based on the weighted average of different grayscale differences in the grayscale co-occurrence matrix; Extract entropy value parameter: It measures the randomness of the gray distribution within a region. The higher the entropy value, the more complex the internal structure of the region is; Calculate the homogeneity parameter: It reflects the degree of gray similarity in the image and is used to identify whether there are local radiation anomalies in the region.

[0029] Specifically, based on the texture features and surface structure information, perform local dynamic compensation on the initial emissivity distribution map to generate a corrected emissivity distribution map, including: Establish the mapping relationship between each local grid region in the initial emissivity distribution map and the corresponding texture features and surface structure information; Specifically, based on the local grid division, for each clearly numbered local grid region, combine and encode the corresponding image texture features and spatial structure features of the region to form a feature mapping table. The feature mapping table uses the local grid number as an index, and its content includes: the set of infrared radiation image texture feature parameters of the grid region (including texture contrast parameter, entropy value parameter, homogeneity parameter) and the set of spatial point cloud structure parameters (including spatial normal vector direction, local curvature change value, point cloud density), as well as the original emissivity value of the region in the initial emissivity distribution map.

[0030] Within each local grid region, construct a spatial structure model based on the three-dimensional point cloud data; Specifically, in each grid region, use the spatial normal vector direction and local curvature as the main structure parameters to construct a spatial structure model. The specific process is as follows: Based on the point cloud normal vector, construct a directional tensor matrix, perform eigenvalue decomposition on the tensor matrix, and extract the main direction change distribution to reflect the geometric trend of the coal pile surface in this grid region. At the same time, combined with the curvature change situation, weight and combine the direction tensor and curvature index according to specific weight rules to form the spatial structure model of this grid region. The model can be used to quantify whether there are complex landform features on the coal pile surface in this region, such as protrusions, depressions or folding surfaces.

[0031] Within each local grid region, construct an image texture feature model based on the infrared radiation intensity distribution image; Specifically, construct an image texture model based on texture feature parameters: Based on the texture contrast parameter, entropy value parameter, and homogeneity parameter extracted from the gray-level co-occurrence matrix, construct a multi-dimensional feature space of local image texture. Use the principal component analysis algorithm to perform dimensionality reduction processing on the above parameters to form a set of main texture expression factors. The main texture expression factors are used to characterize the typical change pattern of the infrared image in this region in the visual space.

[0032] Jointly fit the spatial structure model and the image texture feature model to obtain the emissivity adjustment factor for each local grid region; Specifically, a weighted regression model is used with the output value of the spatial structure model and the main texture expression factor of the image texture feature model as independent variables, and the emissivity value of this area in the initial emissivity distribution map as the dependent variable to establish a joint mapping regression equation. Through the minimum residual optimization process, the adjustment weight of the characteristic response of this area to the emissivity deviation value is determined. Finally, the emissivity adjustment factor of this grid area is calculated by the regression equation. The magnitude of the emissivity adjustment factor represents the actual response ability of the structure and image features of the current grid in the current thermal field, and is used to reflect the correction degree of the original emissivity value.

[0033] Based on the emissivity adjustment factor of each local grid area, local dynamic compensation is performed on the original emissivity value to generate a corrected emissivity distribution map; Specifically, for each local grid area, the calculation method of the corrected emissivity is as follows: multiply the original emissivity value by the emissivity adjustment factor of this area to obtain the preliminary compensation result of this area; introduce a spatial smoothing factor to balance the emissivity transition difference between this area and its directly adjacent local grid areas. The value of the spatial smoothing factor is equal to the difference between the average value of the original emissivities of the eight directly adjacent local grid areas of this area and the original emissivity of this area; the corrected emissivity value is equal to the weighted average of the preliminary compensation result and the spatial smoothing factor.

[0034] While realizing local compensation, consider the continuity of the emissivity transition between regions to avoid single-point mutations. Finally, the emissivity values of all locally grid areas after compensation calculation are combined and plotted to form a complete corrected emissivity distribution map of the coal pile surface.

[0035] Specifically, identify the abnormal areas on the coal pile surface according to the corrected emissivity distribution map and mark them as potential risk areas, including: Perform spatial neighborhood analysis on the corrected emissivity distribution map to determine the local statistical threshold of the emissivity within each local grid area; Specifically, divide the corrected emissivity distribution map of the coal pile surface into multiple local grid areas, each area contains a central grid and its eight adjacent peripheral grids, a total of nine spatial units. For each central grid area, extract the emissivity values of itself and the eight adjacent areas, and calculate the statistical average value and statistical standard deviation of the nine emissivity values. Use the statistical average value plus the statistical standard deviation as the local statistical threshold of this central grid area.

[0036] Based on the local statistical threshold, determine the abnormal deviation degree of the emissivity within each local grid area to generate emissivity anomaly intensity data; Specifically, for each local grid area, calculate the difference between the corrected emissivity value and the local statistical threshold. If the difference is positive, it indicates that the emissivity of this area has exceeded the normal fluctuation range, and this difference is the emissivity anomaly intensity; if the difference is zero or negative, it indicates that this area has not exceeded the local threshold, and the emissivity anomaly intensity is set to zero.

[0037] Spatially splice the anomaly intensity values corresponding to all local grid areas to generate an emissivity anomaly intensity data map covering the entire coal pile surface. The emissivity anomaly intensity data map serves as the spatial basis for quantifying the degree of thermal anomaly and provides a basis for locating the anomaly boundary.

[0038] Determine the spatial position boundary of the abnormal area on the coal pile surface according to the emissivity anomaly intensity data; Specifically, traverse all grids in the emissivity anomaly intensity data map, identify the set of areas with anomaly intensity greater than zero, and mark them as initial abnormal area candidate points. Use eight-neighborhood recursion to merge adjacent abnormal candidate points into spatially connected areas to form a preliminary set of abnormal blocks.

[0039] In the set of abnormal blocks, calculate the boundary position coordinates of each block, including the minimum horizontal number, the maximum horizontal number, the minimum vertical number, and the maximum vertical number, to form a two-dimensional bounding box of this abnormal area on the emissivity image, which serves as the actual position range of this abnormal area in the image space.

[0040] Conduct a spatial connectivity division on the abnormal areas on the coal pile surface to determine the overall spatial range of the abnormal areas; Specifically, based on the preliminary set of bounding boxes, conduct an overlapping analysis of the bounding boxes. If there is spatial overlap or boundary contact between two bounding boxes, merge them into a new abnormal area. The merging process uses the extended boundary comparison method, that is, determine whether there is an intersection of consecutive numbers in the horizontal or vertical direction between two bounding boxes. If so, logically merge the two bounding boxes into a spatial whole.

[0041] After completing the connectivity discrimination for all sets of abnormal blocks, output the final set of abnormal areas. Each abnormal area has a clear number identifier and a spatial boundary range, including the internal emissivity anomaly intensity data, including the maximum value, the average value, and the area.

[0042] Mark the overall spatial range of the abnormal areas to obtain potential risk areas; Specifically, mark each subset of abnormal areas determined through the overlapping analysis as a potential risk area.

[0043] Specifically, analyze the heat distribution characteristics within the potential risk areas through a heat transfer diffusion model and evaluate the time dependence of heat diffusion, including: Based on the overall spatial scope of the potential risk area, a heat transfer and diffusion model is established; Specifically, after the identification of potential risk areas is completed, the two-dimensional boundary scope corresponding to each potential risk area is extracted. This boundary scope is used as the computational domain boundary to define the spatial boundary conditions for the model to calculate the potential risk area. The definition principle of the spatial boundary is as follows: The spatial boundary should cover the complete extension of the potential risk area and expand one unit grid outward at the boundary to introduce the influence of boundary heat diffusion; The emissivity value and temperature distribution within the boundary area are jointly determined based on the corrected emissivity map and the externally collected temperature data to ensure the accuracy of the initial boundary conditions of the model.

[0044] A two-dimensional steady-state heat conduction model is established within the determined spatial boundary range. The model assumes that the heat diffusion on the surface of the coal pile is mainly in the in-plane direction, and the vertical heat exchange amount can be simplified to a steady background heat flux, so that approximate modeling can be carried out on the spatial plane. The heat diffusion process is discretely modeled using the finite difference method. The heat conduction differential equation is approximated by differences at each grid node to form a linear equation system for describing the heat propagation behavior during the time evolution process.

[0045] Based on the heat transfer and diffusion model, numerical simulation of heat diffusion is carried out on the potential risk area to determine the heat distribution data of each local grid area within the potential risk area; Specifically, after the discretization of the heat conduction model is completed, heat diffusion simulation calculation is carried out on the model. The simulation initial conditions are set according to the corrected emissivity map and the infrared temperature distribution map. The initial heat value of each local grid is jointly calculated from the corrected emissivity value and the actual temperature value of this area: The initial heat value is equal to the emissivity value multiplied by the surface temperature, and then multiplied by the unit specific heat capacity and the unit thickness.

[0046] The explicit time iteration method is adopted in the simulation process, and an equal-interval time step is set. At each time step, the temperature value of each grid cell is updated according to the difference format of the heat conduction equation, and then the heat value of each cell is updated. Every time a time step update is completed, a snapshot of the heat distribution of all grids in the potential risk area is obtained.

[0047] The entire simulation cycle lasts for several time steps until the heat diffusion process reaches the preset equilibrium state, that is, the temperature change rate of all grids is lower than the specified change threshold. After the simulation ends, the complete heat distribution data sequence corresponding to each time step is output to form a heat time evolution matrix.

[0048] Based on the heat distribution data of each local grid area within the potential risk area, analyze the diffusion trend of heat; Specifically, using the heat distribution data at each time step in the heat time evolution matrix, perform time series difference calculations for each local grid to obtain a sequence of heat change values per unit time. Then, based on the sequence of change values, statistically analyze the changing trend of the heat diffusion rate for each grid.

[0049] The specific method is as follows: taking the sum of the squares of the heat differences as the calculation index, calculate the total amplitude of heat change for each grid; then calculate the changing direction of the total amplitude of heat change over time during the entire simulation period to determine whether the heat diffusion shows an accelerating, decelerating, or stabilizing state.

[0050] According to the heat diffusion trend, evaluate the time dependence of heat diffusion within the potential risk area to obtain the time characteristic data of heat diffusion; Specifically, the time dependence evaluation is based on trend analysis data to comprehensively judge the degree of correlation between heat change and time. The evaluation method is as follows: For each local grid cell, extract the sequence of heat values at consecutive multiple time steps, and use the Pearson correlation coefficient algorithm to calculate the linear correlation coefficient between the heat value and the time step number. The value of the correlation coefficient ranges from zero to one, indicating the monotonicity intensity of the heat diffusion process of the grid cell; a correlation coefficient close to one indicates strong monotonic diffusion, and close to zero indicates large fluctuations in the diffusion direction; Apply the sliding extreme value recognition algorithm to the heat time series of each local grid, set a fixed time window width, identify the positions of local maxima and local minima in the sequence, and define each trend reversal as an inflection point; count the total number of inflection points in the entire heat diffusion process to reflect whether there are violent fluctuations or phased mutations in the heat diffusion process.

[0051] Integrate the linear correlation coefficient and the total number of inflection points as the time characteristic data of heat diffusion with time dependence in the potential risk area.

[0052] Specifically, evaluate the equilibrium degree of heat distribution within the potential risk area through fractal analysis methods, including: Extract the heat distribution data of each local grid area within the potential risk area; Specifically, from the heat time evolution matrix, select the stable state time step data after the heat diffusion process ends, and extract the heat values of all local grids within the potential risk area at this moment. Each local grid area corresponds to a unique heat value, representing the thermal energy accumulation level in the final heat balance stage.

[0053] Map the heat distribution data of each local grid area within the potential risk area into a spatial heat distribution matrix; Specifically, the value of each element in the spatial heat distribution matrix represents the heat value of the corresponding grid, and each row and each column correspond to the spatial position coordinates on the surface of the coal pile in sequence. The spatial heat distribution matrix is standardized, and all heat values are normalized between zero and one.

[0054] Apply heat level classification processing to the standardized spatial heat distribution matrix. Divide the entire numerical range into several grade segments. For example, divide the heat values into three categories: low heat area, medium heat area, and high heat area. Each grade corresponds to a gray scale coding to form a heat distribution grade image.

[0055] Calculate the multi-scale fractal dimension of the spatial heat distribution matrix to obtain the fractal dimension sequence of the potential risk area at different spatial scales; Specifically, select the box dimension method to perform multi-scale box covering analysis on the heat distribution grade image: Set multiple square box grids of different sizes on the heat distribution grade image. Starting from the smallest cell, each time expand the box size by a fixed ratio to form a series of multi-scale box division sets; At each scale, perform box grid covering on the heat grade image, and count the number of boxes containing non-empty pixels (i.e., there are high heat grade points) in the current box grid; the high heat grade point is the representation unit of the high heat area in the heat distribution grade image and they correspond to each other.

[0056] Record the box size and the corresponding number of non-empty boxes data at each scale, and plot a double logarithmic image of the number of boxes and the box size in a logarithmic coordinate system for linear regression analysis; The absolute value of the slope of the regression line is the fractal dimension value of the current heat distribution grade image, indicating the complexity degree of the spatial heat structure at the current scale.

[0057] Repeat the above process to calculate the fractal dimension at multiple scales and obtain the fractal dimension sequence of the potential risk area.

[0058] According to the change trend of the fractal dimension sequence, evaluate the spatial equilibrium degree of the heat distribution in the potential risk area to obtain the spatial characteristic data of heat diffusion; Specifically, the spatial characteristic data includes: fractal mean index: divide the sum of the fractal dimension values corresponding to all scales in the fractal dimension sequence by the sequence length to obtain the average fractal dimension of the potential risk area, which is used to quantify the overall spatial distribution complexity; Fractal fluctuation index: calculate the difference between the maximum value and the minimum value of the fractal dimension value and use it as the fluctuation amplitude to quantify the change intensity of the fractal complexity at different spatial scales; Principal scale position: In the fractal dimension sequence, the scale number corresponding to the maximum fractal dimension value is used as the principal scale position, indicating that the heat distribution is the most uneven at this spatial scale; Equilibrium index: The calculation result of dividing the fractal mean index by the fractal fluctuation index is used as the equilibrium index to reflect the stability degree of the spatial distribution; the larger the equilibrium index, the smoother the change of the overall fractal complexity and the more balanced the spatial structure.

[0059] Specifically, based on the time dependence of heat diffusion and the equilibrium degree of heat distribution, evaluate the safety risk level of the coal yard and generate coal yard safety warning information, including: Perform feature vector splicing based on heat diffusion time feature data and heat diffusion spatial feature data to obtain a comprehensive risk assessment input data set; Specifically, merge the heat diffusion time feature data and the heat diffusion spatial feature data into a feature vector, construct a feature vector sample for each potential risk area, and obtain a comprehensive risk assessment input data set.

[0060] Based on a preset coal yard risk assessment model, combined with the comprehensive risk assessment input data set, perform a risk level assessment of potential risk areas and output the risk level values of potential risk areas; Specifically, the coal yard risk assessment model adopts a multi-dimensional input risk mapping structure, and the structural form is: map the input feature vector to a set of risk score intervals, and output the potential risk level value according to the linear weighted assessment rule.

[0061] Each feature has a preset weight parameter in the risk scoring model. The model weight parameters are determined based on the training results of historical annotation samples. In the training stage, the least mean square error optimization strategy is used to adjust the parameters to output the minimum deviation between the risk level value and the manually annotated level. The training sample data comes from typical historical cases of coal pile safety monitoring and has been preprocessed by standard feature normalization.

[0062] The model calculation method is: jointly input the heat diffusion time feature sub-vector and the heat diffusion spatial feature sub-vector, multiply them by the corresponding risk weight coefficients respectively and then sum, and normalize them to the risk level value through a first-order activation function, and the value range is between zero and one.

[0063] The output result is the risk level value of each potential risk area, which is used for risk level classification and construction of the risk level atlas.

[0064] Perform risk level division on potential risk areas according to the risk level value to generate a risk level atlas of potential risk areas; Specifically, divide the risk level values of all potential risk areas, and adopt a three-level segmentation standard: If the risk level value is greater than or equal to seventy percent, it is classified as a high-level potential risk area; If the risk level value is greater than or equal to 40% and less than 70%, it is classified as a medium-level potential risk area; If the risk level value is less than 40%, it is classified as a low-level potential risk area.

[0065] Each potential risk area is assigned a corresponding risk level label according to the above classification criteria and superimposed on the two-dimensional space map of the coal pile surface to form a spatial distribution map of potential risk areas, which is the risk level map.

[0066] Generate corresponding coal yard safety warning information according to the risk level map; Specifically, based on the risk level map, safety warning information is generated for potential risk areas of different levels, including: Risk level classification labels (high level, medium level, low level); Recommended response measures (e.g., local remeasurement, activation of cooling system).

[0067] The generated warning information is stored in the system database in a structured data format and synchronously pushed to the central monitoring interface of the coal yard to achieve the linked release of graphic annotation and warning text.

[0068] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters and threshold selection in the formulas are set by those skilled in the art according to the actual situation.

[0069] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more collections of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0070] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0071] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and modules described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0072] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or modules can be in electrical, mechanical, or other forms.

[0073] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules. They can be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0074] In addition, the functional modules in each embodiment of this application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0075] If the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0076] As described above, the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

[0077] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A coal yard safety analysis system based on the fusion of infrared imaging and point cloud data, characterized in that, Including: The data acquisition module collects infrared imaging data and three-dimensional point cloud data on the surface of the coal pile, performs multi-source information fusion processing on the infrared imaging data and three-dimensional point cloud data, and generates an initial emissivity distribution map of the coal pile surface; The grid division module divides the surface of the coal pile into multiple local grid regions based on the initial emissivity distribution map, and extracts the texture features and surface structure information of each local grid region; The emission correction module performs local dynamic compensation on the initial emissivity distribution map based on the texture features and surface structure information, and generates a corrected emissivity distribution map; The anomaly detection module identifies the abnormal regions on the surface of the coal pile according to the corrected emissivity distribution map and marks them as potential risk regions; The diffusion evaluation module analyzes the heat distribution characteristics in the potential risk region through a heat transfer diffusion model and evaluates the time dependence of heat diffusion; The fractal evaluation module evaluates the degree of balance of heat distribution in the potential risk region through a fractal analysis method; The risk warning module evaluates the safety risk level of the coal yard based on the time dependence of heat diffusion and the degree of balance of heat distribution, and generates a safety warning message for the coal yard.

2. The coal yard safety analysis system based on the fusion of infrared imaging and point cloud data according to claim 1, characterized in that, Collect infrared imaging data and three-dimensional point cloud data on the surface of the coal pile, perform multi-source information fusion processing on the infrared imaging data and three-dimensional point cloud data, and generate an initial emissivity distribution map of the coal pile surface. Specifically: Use an infrared thermal imaging device to collect infrared imaging data on the surface of the coal pile to obtain an infrared radiation intensity distribution image; Use a three-dimensional laser scanning device to collect the spatial position coordinate data and spatial surface structure feature data on the surface of the coal pile to obtain the three-dimensional point cloud data of the coal pile surface; Perform spatial coordinate alignment and timestamp alignment on the infrared radiation intensity distribution image and the three-dimensional point cloud data to establish a mapping relationship between the infrared image pixel points and the point cloud coordinate points; Based on the mapping relationship between the infrared image pixel points and the point cloud coordinate points, generate an initial emissivity distribution map of the coal pile surface.

3. The coal yard safety analysis system based on the fusion of infrared imaging and point cloud data according to claim 2, wherein, Based on the initial emissivity distribution map, divide the surface of the coal pile into multiple local grid regions, and extract the texture features and surface structure information of each local grid region. Specifically: Determine the local spatial boundary of the coal pile surface based on the initial emissivity distribution map, and divide the surface of the coal pile into multiple local grid regions; For each local grid region, extract the surface structure information based on the three-dimensional point cloud data; For each local grid region, extract the texture features based on the infrared radiation intensity distribution image.

4. A coal yard safety analysis system based on the fusion of infrared imaging and point cloud data according to claim 3, characterized in that, Perform local dynamic compensation on the initial emissivity distribution map based on the texture features and surface structure information, and generate a corrected emissivity distribution map. Specifically: Establish a mapping relationship between each local grid region in the initial emissivity distribution map and the corresponding texture features and surface structure information; Within each local grid region, construct a spatial structure model according to the three-dimensional point cloud data; Within each local grid region, construct an image texture feature model according to the infrared radiation intensity distribution image; Jointly fit the spatial structure model and the image texture feature model to obtain the emissivity adjustment factor of each local grid region; Based on the emissivity adjustment factor of each local grid region, perform local dynamic compensation on the original emissivity value to generate a corrected emissivity distribution map.

5. The coal yard safety analysis system based on the fusion of infrared imaging and point cloud data according to claim 4, characterized in that, Identify the abnormal areas on the surface of the coal pile according to the corrected emissivity distribution map, and mark them as potential risk areas, specifically: Conduct a spatial neighborhood analysis on the corrected emissivity distribution map to determine the local statistical threshold of the emissivity within each local grid area; Based on the local statistical threshold, determine the abnormal deviation degree of the emissivity within each local grid area, and generate emissivity abnormal intensity data; Determine the spatial position boundary of the abnormal area on the surface of the coal pile according to the emissivity abnormal intensity data; Conduct a spatial connectivity division on the abnormal area on the surface of the coal pile to determine the overall spatial range of the abnormal area; Mark the overall spatial range of the abnormal area to obtain the potential risk area.

6. The coal yard safety analysis system based on the fusion of infrared imaging and point cloud data according to claim 5, characterized in that, Analyze the heat distribution characteristics within the potential risk area through a heat transfer diffusion model, and evaluate the time dependence of heat diffusion, specifically: Based on the overall spatial range of the potential risk area, establish a heat transfer diffusion model; Conduct a numerical simulation of heat diffusion on the potential risk area according to the heat transfer diffusion model to determine the heat distribution data of each local grid area within the potential risk area; Based on the heat distribution data of each local grid area within the potential risk area, analyze the heat diffusion trend; According to the heat diffusion trend, evaluate the time dependence of heat diffusion within the potential risk area to obtain the time characteristic data of heat diffusion.

7. The coal yard safety analysis system based on the fusion of infrared imaging and point cloud data according to claim 6, characterized in that, Evaluate the degree of balance of heat distribution within the potential risk area through a fractal analysis method, specifically: Extract the heat distribution data of each local grid area within the potential risk area; Map the heat distribution data of each local grid area within the potential risk area into a spatial heat distribution matrix; Conduct a multi-scale fractal dimension calculation on the spatial heat distribution matrix to obtain a fractal dimension sequence of the potential risk area at different spatial scales; According to the change trend of the fractal dimension sequence, evaluate the spatial balance degree of heat distribution within the potential risk area to obtain the spatial characteristic data of heat diffusion.

8. The coal yard safety analysis system based on the fusion of infrared imaging and point cloud data according to claim 7, characterized in that, Based on the time dependence of heat diffusion and the degree of balance of heat distribution, evaluate the safety risk level of the coal yard and generate a coal yard safety warning message, specifically: Conduct feature vector splicing based on the heat diffusion time characteristic data and the heat diffusion spatial characteristic data to obtain a comprehensive risk assessment input data set; Based on a preset coal yard risk assessment model, combined with the comprehensive risk assessment input data set, perform a risk level assessment of the potential risk area and output the risk level value of the potential risk area; Conduct a risk level division on the potential risk area according to the risk level value to generate a risk level map of the potential risk area; Generate a corresponding coal yard safety warning message according to the risk level map.

Images