Coal Mine Safety Analysis Methods and Systems Based on Big Data Analytics

Abstract

This invention relates to the field of coal mine safety assessment technology, and particularly to a coal mine safety analysis method and system based on big data analysis. The method includes the following steps: acquiring coal mine engineering environmental data and coal mine engineering geographic data, wherein the coal mine engineering environmental data includes high-frequency gas concentration data and ventilation status data; extracting geographic topological information from the coal mine engineering geographic data and integrating the coal mine engineering environmental data into an initial dataset of post-disaster gas fields; performing thermo-mass coupling diffusion analysis on the initial dataset of post-disaster gas fields to generate a residual gas concentration inversion network; and using the residual gas concentration inversion network to invert the spatial distribution of residual gases in the initial dataset of post-disaster gas fields to obtain spatial concentration residual maps of each gas component. This invention, through multi-source data fusion and thermo-mass coupling inversion, achieves high-precision dynamic monitoring of post-disaster gas fields and accurate location of explosion sources in coal mines, thereby improving the real-time assessment capability of coal mine safety risks.

Description

Technical Field

[0001] This invention relates to the field of coal mine safety assessment technology, and in particular to a coal mine safety analysis method and system based on big data analysis. Background Technology

[0002] Early coal mine safety relied primarily on manual inspections and experience-based judgment, resulting in limited monitoring scope and poor early warning timeliness. With the widespread application of sensor technology and automated equipment, coal mines began introducing real-time data acquisition systems to monitor key parameters such as gas concentration, mine pressure, and temperature online, driving the digitalization of safety monitoring. In the era of big data, coal mine safety analysis increasingly leverages massive, multi-source, and multi-dimensional data, employing data fusion, mining, and modeling techniques to enhance risk identification and early warning capabilities. Early applications of big data technology in coal mines mainly focused on data storage and simple statistical analysis, failing to delve into potential hazard patterns. With the introduction of advanced algorithms such as machine learning and artificial intelligence, coal mine safety analysis has shifted from static monitoring to dynamic prediction and intelligent decision-making, achieving precise location and trend prediction of accident hazards. However, traditional methods in gas diffusion modeling often rely on simplified models, failing to accurately reflect thermo-mass coupling effects, leading to significant errors in the spatial distribution inversion of gas concentration. Furthermore, they struggle to accurately locate the explosion initiation point, typically relying on single indicators and being susceptible to noise, thus resulting in low real-time assessment capabilities for coal mine safety risks. Summary of the Invention

[0003] Therefore, it is necessary to provide a coal mine safety analysis method and system based on big data analysis to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a coal mine safety analysis method based on big data analysis is proposed, the method comprising the following steps:

[0005] Step S1: Obtain coal mine engineering environmental data and coal mine engineering geographic data, including high-frequency gas concentration data and ventilation status data; extract geographic topology information from coal mine engineering geographic data, and integrate coal mine engineering environmental data into an initial dataset of post-disaster gas fields in coal mines;

[0006] Step S2: Perform thermo-mass coupled diffusion analysis on the initial dataset of the coal mine post-disaster gas field to generate a residual gas concentration inversion network; use the residual gas concentration inversion network to invert the spatial distribution of residual gas on the initial dataset of the coal mine post-disaster gas field to obtain the spatial concentration residual spectrum of each gas component.

[0007] Step S3: Extract the high-order concentration gradient boundary feature data of the spatial concentration residue map of each gas component, and perform reverse source tracing calculation on the high-order concentration gradient boundary feature data to generate the explosion point estimation coordinate domain; based on the explosion point estimation coordinate domain, predict the spatial distribution evolution of toxic gas residue in the spatial concentration residue map to generate the toxic gas spatial distribution evolution map.

[0008] Step S4: Couple and fuse the residual gas concentration inversion network, the explosion point estimation coordinate domain, and the toxic gas spatial distribution evolution map to construct a dynamic evolution map of air quality after a coal mine disaster; use the preset regional concentration threshold to conduct a safety risk assessment on the dynamic evolution map of air quality after a coal mine disaster in order to perform coal mine safety analysis operations.

[0009] This invention, through thermo-mass coupled diffusion analysis and a residual gas concentration inversion network, can accurately reconstruct the spatial distribution of multi-component gases in the complex post-disaster environment of coal mines, providing a reliable data foundation for subsequent safety analysis. Reverse tracing based on high-order concentration gradient boundary features effectively improves the spatial positioning accuracy of the explosion initiation point, providing crucial clues for disaster investigation and accident retrospective analysis. Utilizing the estimated coordinate domain of the explosion point to predict the spatial evolution of toxic gas residues allows for early understanding of the diffusion trajectory and concentration change trends of toxic gases in high-risk areas, providing a scientific basis for emergency rescue deployment. By coupling the inversion network, explosion coordinates, and evolution map, spatiotemporal dynamic fusion of multi-source data is achieved, forming a comprehensive, three-dimensional, and visualized air quality evolution map. Intelligent assessment of the air quality map using regional concentration thresholds quickly identifies high-risk areas, assisting coal mines in achieving automated safety monitoring and risk warning response. The entire methodology is logically rigorous, data-driven, highly scalable, and engineering adaptable, effectively improving the technical level and response efficiency of post-disaster emergency management and safety assessment in coal mines. Therefore, this invention achieves high-precision dynamic monitoring of the gas field after a coal mine disaster and accurate location of the explosion source through multi-source data fusion and thermo-mass coupling inversion, thereby improving the real-time assessment capability of coal mine safety risks.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Obtain coal mine engineering environmental data and coal mine engineering geographic data, wherein the coal mine engineering environmental data includes high-frequency gas concentration data and ventilation status data;

[0012] Step S12: Perform high-frequency time series resampling on the original coal mine engineering environment data to generate high-frequency gas concentration time data;

[0013] Step S13: Divide the coal mine ventilation status data into regional ventilation modes and generate local ventilation topology data of the coal mine;

[0014] Step S14: Perform three-dimensional topology reconstruction on the coal mine engineering geographic data to generate coal mine geographic topology grid data;

[0015] Step S15: Perform spatiotemporal fusion interpolation on high-frequency gas concentration time data and local ventilation topology data of coal mine to generate coal mine ventilation-gas joint field data; integrate coal mine ventilation-gas joint field data with coal mine geographic topology grid data to form the initial dataset of coal mine post-disaster gas field.

[0016] This invention utilizes high-frequency time-series resampling to reconstruct and optimize the temporal dimension of raw gas concentration data, enhancing the temporal continuity and sampling density of the data and providing more stable and complete input data for subsequent modeling. By dividing regional ventilation patterns using ventilation status data, a local ventilation topology structure in the coal mine is constructed, improving the ability to express local dynamic changes in the ventilation system and facilitating a more realistic simulation of gas propagation paths and behaviors. Constructing a three-dimensional geographic topological grid helps to realistically reflect the complexity of the underground spatial structure, providing a high-precision spatial framework for gas diffusion analysis. Achieving spatiotemporal fusion interpolation of high-frequency gas concentration time data and ventilation topology data forms a more complete ventilation-gas joint field, improving data consistency and enhancing the dynamic understanding of gases in both spatial and temporal dimensions. Integrating the three key elements of gas, ventilation, and geographic information forms an initial dataset of post-disaster gas fields in coal mines, providing an integrated, high-quality data foundation for subsequent gas diffusion modeling, risk assessment, and safety decision-making. The entire process revolves around data fusion, closely integrating with the actual environment of coal mine engineering. This effectively enhances the physical rationality and engineering applicability of subsequent model inference results, thereby increasing the reliability and accuracy of post-disaster air quality assessment and accident tracing.

[0017] Preferably, step S2 includes the following steps:

[0018] Step S21: Estimate the heat-mass transport coefficient of the initial dataset of the post-disaster gas field using the heat-mass co-diffusion equation;

[0019] Step S22: Perform dynamic diffusion field simulation on the initial dataset of the coal mine post-disaster gas field using the heat-mass transfer coefficient to generate post-disaster gas residual diffusion evolution data;

[0020] Step S23: Perform residual fitting on the post-disaster gas residual diffusion evolution data to construct a residual gas concentration inversion network;

[0021] Step S24: Use the residual gas concentration inversion network to perform spatial inversion calculations on the initial dataset of the gas field after the coal mine disaster to generate three-dimensional reconstruction data of residual gas concentration; perform multi-component spectrum separation and spatial clustering analysis on the three-dimensional reconstruction data of residual gas concentration to generate spatial concentration residual spectra of each gas component.

[0022] This invention employs a heat-mass co-diffusion equation to calculate the heat-mass transfer coefficient, fully considering the influence of heat on gas diffusion behavior. This makes the simulation results more consistent with the physical reality of complex post-disaster environments in coal mines, effectively improving the accuracy and adaptability of the diffusion model. Dynamic diffusion field simulation based on the heat-mass transfer coefficient captures the evolutionary trajectory of post-disaster gases in both spatial and temporal dimensions, forming predictive residual diffusion evolution data and providing a realistic evolutionary basis for subsequent inversion and prediction. By performing residual fitting on the residual diffusion evolution data, a residual gas concentration inversion network is established, improving the model's inversion accuracy in complex nonlinear gas propagation environments and enabling the deduction of gas sources and concentration distributions from residual distributions. Spatial inversion using the inversion network generates three-dimensional reconstruction data of residual gas concentrations, constructing high-resolution spatial gas concentration distributions and providing clear and visible three-dimensional data support for post-disaster assessment and emergency response. Through multi-component spectral separation and spatial clustering analysis, the distribution patterns, aggregation regions, and diffusion boundaries of different types of gases can be identified and analyzed, forming spatial residual concentration maps of each gas component, providing fine-grained information for toxicity analysis and explosion risk assessment. The entire process chain is based on a combination of physical model-driven and data-driven approaches, enabling efficient and automatic reconstruction of three-dimensional gas distribution and component identification, significantly enhancing the technical depth and application value of post-disaster environmental modeling in coal mines.

[0023] Preferably, step S24, which involves multi-component spectral separation and spatial clustering analysis of the three-dimensional reconstruction data of residual gas concentration, includes:

[0024] Fourier transform was performed on the three-dimensional reconstruction data of residual gas concentration, and the spectral response features of CH4, CO, CO2, and H2S after transformation were extracted to generate spectral response feature data.

[0025] Blind source separation was performed on the three-dimensional reconstruction data of residual gas concentration using spectral response feature data, and the response signals of independent gases CH4, CO, CO2, and H2S were extracted to generate an independent gas component concentration dataset.

[0026] Perform three-dimensional spatial cluster analysis on independent gas component concentration datasets to generate spatial cluster map data of gas components;

[0027] Geometric fitting and boundary reconstruction are performed on the spatial clustering map data of gas components to generate spatial concentration isosurface map data;

[0028] By integrating independent gas component concentration data with isosurface map data, spatial concentration residual maps of each gas component are generated.

[0029] This invention utilizes Fourier transform on three-dimensional reconstructed residual gas concentration data and extracts the spectral response features of CH4, CO, CO2, and H2S. This allows for precise differentiation of the frequency domain characteristics of each gas, significantly improving the separability between different gases and laying a solid foundation for subsequent separation. Blind source separation using spectral response features automatically extracts independent gas component concentration data without prior labeling information, avoiding errors caused by human intervention and enhancing the model's versatility and intelligence. Three-dimensional spatial clustering analysis of independent gas components identifies high-concentration regions and diffusion trends, revealing component distribution patterns in complex terrain structures and providing spatial guidance for accurate assessment of hazardous areas. Geometric fitting and boundary reconstruction of the clustering results generate concentration isosurface maps with clear boundaries and physical morphology, transitioning from discrete point cloud data to continuous spatial representation and providing a high-quality geometric foundation for visualization and simulation analysis. Integrating independent gas concentration data with isosurface maps creates a spatial residual concentration map that comprehensively displays local high-concentration regions, boundary trends, and changes in each gas, serving as a core foundation for toxic diffusion prediction and explosion source identification. The entire process is based on frequency domain analysis and enhanced by spatial clustering and geometric reconstruction. Ultimately, it achieves intelligent deconstruction and accurate modeling of complex post-disaster gas fields, significantly improving the scientific rigor, efficiency, and practicality of post-disaster gas distribution analysis in coal mines.

[0030] Preferably, step S3 includes the following steps:

[0031] Step S31: Calculate the local concentration change rate for each type of harmful gas in the spatial concentration residual map, and extract the high-order concentration gradient boundary feature data of the spatial concentration residual map based on the local concentration change rate.

[0032] Step S32: Based on the local concentration change rate, perform toxic gas distribution analysis on each type of harmful gas in the spatial concentration residual spectrum to construct a toxic gas distribution spectrum; reconstruct the anti-diffusion vector field of the high-order concentration gradient boundary feature data to generate multi-directional equipotential vector tracking data;

[0033] Step S33: Simulate the shock wave-ventilation path co-propagation of the high-order concentration gradient boundary feature data based on the multi-directional equipotential vector tracking data, and confirm the location of the initial energy source of the explosion by combining the simulation results with the concentration peak sequence and diffusion reverse vector trajectory of the spatial concentration residual spectrum, and generate the estimated coordinate domain of the explosion point.

[0034] Step S34: Couple the estimated coordinate domain of the explosion point with the toxic gas distribution map to perform diffusion modeling and generate a time-varying initial diffusion field of toxic gas; perform time-step simulation based on the time-varying initial diffusion field data of toxic gas to generate a spatial distribution evolution map of toxic gas residue.

[0035] This invention accurately captures regions of abrupt gas concentration changes by calculating the local concentration change rate of harmful gases and extracting their higher-order concentration gradient boundary features. This constructs a spatially sensitive region that better reflects the physical characteristics of gas diffusion after an explosion, providing more precise initial information for source tracing and localization. Based on the concentration change rate, toxic gas distribution analysis generates a toxic gas distribution map that clearly presents high-risk areas and their evolution trends, further supporting subsequent multi-field coupled modeling and dynamic diffusion simulation, improving the realism and foresight of accident scene simulations. By reconstructing the anti-diffusion vector field from higher-order gradient features, multi-directional equipotential vector tracking data simulating the explosion shock wave and toxic gas diffusion path is constructed, reflecting the actual diffusion direction and path at the time of the accident, improving the physical consistency and source tracing reliability of reverse reasoning. Based on the shock wave-ventilation path collaborative propagation path simulation, the influence of coal mine ventilation layout and structure on gas diffusion is comprehensively considered, ensuring that the explosion point source tracing analysis not only remains at the static reverse path calculation level but also integrates environmental dynamic characteristics, significantly improving the realism and constraint of the explosion point estimation coordinate domain. By coupling the estimated coordinate domain of the explosion point with the toxic gas distribution map, a time-varying initial field for the diffusion of toxic gas is constructed. Time-step simulation is then performed, which can dynamically evolve the residual trajectory of toxic gas in complex space in real time. This provides refined risk evolution prediction support for emergency response. The generated spatial distribution evolution map of toxic gas residue not only has high spatial resolution but also reflects the gas diffusion state at different time points, providing a highly reliable decision-making basis for formulating post-disaster ventilation plans, personnel search and rescue routes, and the sealing off of dangerous areas.

[0036] Preferably, step S33 includes the following steps:

[0037] Step S331: Divide the regional shock wave response sensitivity into regions based on the high-order concentration gradient boundary feature data, and generate shock wave action weight distribution data;

[0038] Step S332: Perform main vector ventilation guidance identification on the multi-directional equipotential vector tracking data to generate ventilation dominant path feature data; perform joint path mapping on the shock wave impact weight distribution data and the ventilation dominant path feature data to generate shock wave-ventilation cooperative propagation simulation data;

[0039] Step S333: Extract the concentration peak sequence from the spatial concentration residual spectrum to generate explosion feature point sequence data; perform diffusion reverse vector fitting on the explosion feature point sequence data to generate explosion energy reverse propagation trajectory data;

[0040] Step S334: Perform path intersection analysis on the simulated data of shock wave-ventilation coordinated propagation and the reverse propagation trajectory data of explosion energy to generate the estimated coordinate domain of the explosion point.

[0041] This invention quantifies the response degree of different regions to explosion shock waves by dividing the boundary feature data of high-order concentration gradients into regional shock wave response sensitivity, generating shock wave impact weight distribution data. This allows explosion simulation to not only consider geometric paths but also accurately reflect the non-uniform propagation characteristics of explosion wave energy in space. By identifying the main vector ventilation guidance of the equipotential vector field and extracting ventilation-dominant path features, the propagation path of toxic gas or shock waves fully considers the actual airflow distribution and ventilation organization structure, enhancing the simulation capability of propagation paths under actual coal mine ventilation conditions. By coupling the shock wave impact weight data with the ventilation-dominant path feature data, shock wave-ventilation coordinated propagation simulation data is formed, achieving for the first time "dual-field coordinated" path modeling of post-disaster explosion diffusion, significantly improving simulation accuracy and physical rationality. Extracting the concentration peak sequence and generating explosion feature point sequence data, and using it for back-diffusion vector fitting, the energy diffusion path of the explosion source can be effectively reconstructed, forming explosion energy back-propagation trajectory data with strong physical logic, further enhancing the scientific basis for source tracing. By performing path intersection analysis on the simulated data of shock wave-ventilation coordinated propagation and the reverse propagation trajectory data of explosion energy, and integrating the two independent but complementary propagation mechanisms, an estimated coordinate domain for the explosion point is generated, which significantly improves the spatial resolution and positioning accuracy of the explosion source location.

[0042] Preferably, the main vector ventilation guidance identification for multi-directional equipotential vector tracking data includes:

[0043] Perform vector direction consistency clustering analysis on multi-directional equipotential vector tracking data to generate equipotential vector main direction cluster data; evaluate the airflow coupling strength of equipotential vector main direction cluster data to generate ventilation adaptability matching score data.

[0044] Multi-scale path topology mapping is performed on the ventilation adaptability matching score data to generate ventilation path fitting grid data; time-series wind speed dynamic playback analysis is performed on the ventilation path fitting grid data to generate dynamic ventilation flow trend map data.

[0045] A path stability and dominance weight fusion analysis was performed on the dynamic ventilation flow trend map data to generate ventilation dominant path characteristic data.

[0046] This invention utilizes vector direction consistency clustering analysis on multi-directional equipotential vector tracking data to effectively extract airflow paths with similar directions in space, generating equipotential vector principal direction cluster data. This significantly reduces the impact of multi-path disturbances on the determination of the principal propagation direction, improving the accuracy and robustness of ventilation guidance identification. Based on the principal directions of equipotential vectors, an airflow coupling strength evaluation method is introduced to generate ventilation adaptability matching score data. This quantifies the coupling degree between different directional vectors and the actual ventilation system, addressing the technical shortcoming of traditional methods that cannot measure the fit between gas migration direction and the ventilation system. By performing multi-scale path topology mapping on the ventilation adaptability score data, the fitted path structure under different ventilation levels can be reconstructed, generating ventilation path fitting grid data. This enables digital modeling of complex ventilation networks in coal mines, exhibiting strong ventilation path adaptability. Based on the fitted grid, further time-series wind speed dynamic playback analysis is conducted to generate dynamic ventilation flow trend map data. This not only simulates instantaneous airflow distribution but also reconstructs the gas diffusion path changes at different times, facilitating post-disaster rescue decision-making and ventilation optimization simulation. By integrating path stability and dominance weight analysis, key factors influencing gas propagation paths were extracted, ultimately generating highly directional ventilation-dominant path characteristic data, providing high-quality path data for subsequent post-disaster gas tracking and source tracing.

[0047] Preferably, the time-step simulation based on the initial field data of the time-varying diffusion of toxic gas in step S34 includes:

[0048] Based on the initial field data of time-varying diffusion of toxic gas, multi-parameter thermal and mass transport coefficients are extracted to generate a set of diffusion evolution control parameters. The multi-parameter thermal and mass transport coefficient extraction includes the mass diffusion coefficient, thermal diffusion coefficient, and concentration gradient change rate of each gas.

[0049] The diffusion evolution control parameter set data is initialized with a three-dimensional multiphysics temporal grid to generate time-step cell data of toxic gas diffusion; the time-step cell data of toxic gas diffusion is then dynamically solved based on steady state and boundary perturbation to generate multi-time concentration evolution field data of toxic gas.

[0050] High-order spatial interpolation and continuity enhancement processing are performed on the multi-time concentration evolution field data of toxic gas to generate a continuous temporal evolution map of toxic gas concentration.

[0051] A regional residual intensity cluster analysis was performed on the continuous temporal evolution map of toxic gas concentration to generate a spatial distribution evolution map of toxic gas residue.

[0052] This invention extracts multiple thermo-mass transport coefficients, such as mass diffusion coefficient, thermal diffusion coefficient, and concentration gradient change rate, from the initial field of time-varying toxic gas diffusion, establishing a complete set of diffusion evolution control parameters. This enables realistic physical field-driven simulation of toxic gas diffusion behavior, overcoming the bottleneck of coarse approximations in traditional single diffusion models. Using the diffusion evolution control parameter set data for three-dimensional multiphysics temporal grid initialization, highly discretized time-step cell data of toxic gas diffusion can be generated, supporting subsequent multiphysics joint dynamic evolution at each time step and each spatial cell, improving the resolution and sensitivity of space-time coupled simulations. A dynamic temporal solution is performed using a steady-state and boundary perturbation coupling mechanism to simulate the non-steady-state response behavior of toxic gas under boundary abrupt changes or local perturbations, generating multi-time-step concentration evolution field data of toxic gas. This data can be used to assess the risks of toxic gas fluctuations, peak migration, and regional accumulation during diffusion, enhancing the adaptability and early warning capabilities of post-disaster diffusion prediction. By performing high-order spatial interpolation and continuity enhancement on multi-time-phase evolution data, the generated continuous evolution map of toxic gas concentration possesses high temporal resolution and smoothness. It visually represents the dynamic evolution trend of concentration gradients throughout the entire toxic gas diffusion process, enhancing the perceptibility and decision support effect of the data results. Using the continuous evolution map for regional residual intensity cluster analysis, it is possible to effectively identify areas where high concentrations of toxic gas remain after long-term evolution, areas difficult to diffuse and clear, or areas with multiple overlapping sources, generating a spatial distribution evolution map of toxic gas residues. This provides precise support for post-disaster cleanup planning and personnel evacuation route planning.

[0053] Preferably, step S4 includes the following steps:

[0054] Step S41: Spatial fitting and reconstruction of the residual gas concentration inversion network to generate high-dimensional gas concentration inversion matrix data;

[0055] Step S42: Superimpose the estimated coordinate domain of the explosion point with the high-dimensional inversion matrix data of gas concentration to generate perturbation-enhanced gas concentration field data.

[0056] Step S43: Perform three-dimensional multi-temporal field fusion of the perturbation-enhanced gas concentration field data and the spatial distribution evolution map of toxic gas to generate a dynamic evolution map of air quality after a coal mine disaster.

[0057] Step S44: Use the preset regional concentration threshold to determine the regional concentration threshold of the dynamic evolution map of air quality after the coal mine disaster, and generate the concentration exceeding the limit identification data of dangerous sections; perform spatial distribution clustering and temporal evolution trend analysis on the concentration exceeding the limit identification data of dangerous sections, and generate a coal mine safety risk level labeling map to perform coal mine safety analysis operations.

[0058] This invention generates high-dimensional gas concentration inversion matrix data by spatially fitting and reconstructing a residual gas concentration inversion network. This overcomes the limitations of traditional low-dimensional approximate modeling, reconstructing a gas concentration field with rich spatial distribution details and higher resolution, thus improving the modeling ability of the microscopic distribution patterns of residual toxic gases and laying a data foundation for subsequent dynamic analysis. By superimposing the estimated coordinate domain of the explosion point with the high-dimensional concentration matrix data through local perturbation response, a perturbation-enhanced gas concentration field data is constructed. This dynamically reflects the secondary excitation and aggregation effects of the initial explosion perturbation on the distribution of toxic gases, improving the accuracy and sensitivity of simulating the anomaly trends of polluted areas after disasters. By fusing the perturbation-enhanced concentration field with the spatial evolution map of toxic gases in three dimensions and multiple time series, a dynamic evolution map of air quality after coal mine disasters is constructed. This enables joint tracking and trend visualization of toxic gas diffusion on both temporal and spatial scales, comprehensively improving the reliability of dynamic assessment of environmental risks after accidents. By using preset regional concentration thresholds to identify air quality evolution maps, data on concentration exceedances in hazardous areas can be generated. This allows for the rapid identification of areas with excessive concentrations, persistently high-risk sections, and convergence points at the tail end of diffusion, enhancing the targeting and efficiency of post-disaster ventilation, containment management, and personnel evacuation. Spatial distribution clustering analysis and temporal evolution trend projection are performed on the concentration exceedance identification data for hazardous areas to generate a coal mine safety risk level labeling map. This supports the establishment of an intelligent and dynamic risk assessment and grading mechanism based on comprehensive indicators such as spatial distribution, concentration evolution, and duration, assisting in coal mine safety command and decision-making.

[0059] This specification provides a coal mine safety analysis system based on big data analytics for executing the aforementioned coal mine safety analysis method based on big data analytics. The coal mine safety analysis system based on big data analytics includes:

[0060] The gas field identification module is used to acquire coal mine engineering environmental data and coal mine engineering geographic data. The coal mine engineering environmental data includes high-frequency gas concentration data and ventilation status data. It extracts the geographic topology information of the coal mine engineering geographic data and integrates the coal mine engineering environmental data into an initial dataset of gas fields after a coal mine disaster.

[0061] The concentration analysis module is used to perform thermo-mass coupled diffusion analysis on the initial dataset of the gas field after a coal mine disaster, and generate a residual gas concentration inversion network. The residual gas concentration inversion network is used to invert the spatial distribution of residual gas on the initial dataset of the gas field after a coal mine disaster, and obtain the spatial concentration residual spectrum of each gas component.

[0062] The distribution evolution module is used to extract high-order concentration gradient boundary feature data of the spatial concentration residue map of each gas component, and to perform reverse source tracing calculation of the explosion initiation point of the high-order concentration gradient boundary feature data to generate the explosion point estimation coordinate domain; based on the explosion point estimation coordinate domain, the spatial distribution evolution of toxic gas residue is predicted in the spatial concentration residue map to generate the toxic gas spatial distribution evolution map.

[0063] The safety assessment module is used to couple and fuse the residual gas concentration inversion network, the explosion point estimation coordinate domain, and the toxic gas spatial distribution evolution map to construct a dynamic evolution map of air quality after a coal mine disaster. It uses preset regional concentration thresholds to conduct a safety risk assessment on the dynamic evolution map of air quality after a coal mine disaster in order to perform coal mine safety analysis operations.

[0064] The beneficial effects of this invention lie in the fact that the gas field identification module, by integrating high-frequency gas concentration data, ventilation status data, and coal mine engineering geographical topology information, achieves systematic collection and fusion of complex post-disaster environmental data in coal mines. This ensures the comprehensiveness, timeliness, and spatial accuracy of the initial dataset of post-disaster gas fields, providing a solid data foundation for subsequent diffusion analysis. The concentration analysis module, relying on a thermo-mass coupling diffusion model, constructs a residual gas concentration inversion network, accurately capturing the multi-physics diffusion characteristics of post-disaster gases in coal mines. It achieves high-precision inversion and component separation of spatial concentration residual spectra for each gas component, effectively revealing the spatial distribution patterns of post-disaster gas diffusion. The distribution evolution module utilizes high-order concentration gradient boundary feature data, combined with a reverse source tracing algorithm, to accurately locate the explosion initiation point, significantly improving the spatial accuracy of explosion source estimation. Based on the spatial distribution evolution prediction of toxic gas residues in the explosion point estimation coordinate domain, it realizes dynamic tracking and evolution simulation of the post-disaster toxic gas diffusion process. The safety assessment module couples and fuses residual gas concentration inversion networks, explosion point estimation coordinate domains, and toxic gas spatial distribution evolution maps in multiple dimensions to form a dynamic three-dimensional evolution map of post-disaster air quality, enabling real-time monitoring and trend prediction of spatiotemporal changes in air pollution. By setting concentration thresholds for risk assessment on the dynamic evolution map, it achieves rapid identification of hazardous areas and classification of safety levels, providing scientific and quantitative decision support for coal mine safety management and emergency response, and significantly improving the efficiency and accuracy of post-disaster safety analysis in coal mines. Therefore, this invention, through multi-source data fusion and thermo-mass coupling inversion, achieves high-precision dynamic monitoring of post-disaster gas fields and accurate location of explosion sources in coal mines, enhancing the real-time assessment capability of coal mine safety risks. Attached Figure Description

[0065] Figure 1 This is a flowchart illustrating the steps of a coal mine safety analysis method based on big data analytics.

[0066] Figure 2 for Figure 1 A detailed flowchart illustrating the implementation steps of step S2.

[0067] Figure 3 for Figure 1 A detailed flowchart illustrating the implementation steps of step S3.

[0068] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0069] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0070] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0071] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0072] To achieve the above objectives, please refer to Figures 1 to 3 A coal mine safety analysis method based on big data analysis, the method comprising the following steps:

[0073] Step S1: Obtain coal mine engineering environmental data and coal mine engineering geographic data, including high-frequency gas concentration data and ventilation status data; extract geographic topology information from coal mine engineering geographic data, and integrate coal mine engineering environmental data into an initial dataset of post-disaster gas fields in coal mines;

[0074] Step S2: Perform thermo-mass coupled diffusion analysis on the initial dataset of the coal mine post-disaster gas field to generate a residual gas concentration inversion network; use the residual gas concentration inversion network to invert the spatial distribution of residual gas on the initial dataset of the coal mine post-disaster gas field to obtain the spatial concentration residual spectrum of each gas component.

[0075] Step S3: Extract the high-order concentration gradient boundary feature data of the spatial concentration residue map of each gas component, and perform reverse source tracing calculation on the high-order concentration gradient boundary feature data to generate the explosion point estimation coordinate domain; based on the explosion point estimation coordinate domain, predict the spatial distribution evolution of toxic gas residue in the spatial concentration residue map to generate the toxic gas spatial distribution evolution map.

[0076] Step S4: Couple and fuse the residual gas concentration inversion network, the explosion point estimation coordinate domain, and the toxic gas spatial distribution evolution map to construct a dynamic evolution map of air quality after a coal mine disaster; use the preset regional concentration threshold to conduct a safety risk assessment on the dynamic evolution map of air quality after a coal mine disaster in order to perform coal mine safety analysis operations.

[0077] This invention, through thermo-mass coupled diffusion analysis and a residual gas concentration inversion network, can accurately reconstruct the spatial distribution of multi-component gases in the complex post-disaster environment of coal mines, providing a reliable data foundation for subsequent safety analysis. Reverse tracing based on high-order concentration gradient boundary features effectively improves the spatial positioning accuracy of the explosion initiation point, providing crucial clues for disaster investigation and accident retrospective analysis. Utilizing the estimated coordinate domain of the explosion point to predict the spatial evolution of toxic gas residues allows for early understanding of the diffusion trajectory and concentration change trends of toxic gases in high-risk areas, providing a scientific basis for emergency rescue deployment. By coupling the inversion network, explosion coordinates, and evolution map, spatiotemporal dynamic fusion of multi-source data is achieved, forming a comprehensive, three-dimensional, and visualized air quality evolution map. Intelligent assessment of the air quality map using regional concentration thresholds quickly identifies high-risk areas, assisting coal mines in achieving automated safety monitoring and risk warning response. The entire methodology is logically rigorous, data-driven, highly scalable, and engineering adaptable, effectively improving the technical level and response efficiency of post-disaster emergency management and safety assessment in coal mines. Therefore, this invention achieves high-precision dynamic monitoring of the gas field after a coal mine disaster and accurate location of the explosion source through multi-source data fusion and thermo-mass coupling inversion, thereby improving the real-time assessment capability of coal mine safety risks.

[0078] In this embodiment of the invention, reference Figure 1 The diagram shown is a flowchart illustrating the steps of a coal mine safety analysis method based on big data analysis according to the present invention. In this example, the coal mine safety analysis method based on big data analysis includes the following steps:

[0079] Step S1: Obtain coal mine engineering environmental data and coal mine engineering geographic data, including high-frequency gas concentration data and ventilation status data; extract geographic topology information from coal mine engineering geographic data, and integrate coal mine engineering environmental data into an initial dataset of post-disaster gas fields in coal mines;

[0080] Step S2: Perform thermo-mass coupled diffusion analysis on the initial dataset of the coal mine post-disaster gas field to generate a residual gas concentration inversion network; use the residual gas concentration inversion network to invert the spatial distribution of residual gas on the initial dataset of the coal mine post-disaster gas field to obtain the spatial concentration residual spectrum of each gas component.

[0081] Step S3: Extract the high-order concentration gradient boundary feature data of the spatial concentration residue map of each gas component, and perform reverse source tracing calculation on the high-order concentration gradient boundary feature data to generate the explosion point estimation coordinate domain; based on the explosion point estimation coordinate domain, predict the spatial distribution evolution of toxic gas residue in the spatial concentration residue map to generate the toxic gas spatial distribution evolution map.

[0082] Step S4: Couple and fuse the residual gas concentration inversion network, the explosion point estimation coordinate domain, and the toxic gas spatial distribution evolution map to construct a dynamic evolution map of air quality after a coal mine disaster; use the preset regional concentration threshold to conduct a safety risk assessment on the dynamic evolution map of air quality after a coal mine disaster in order to perform coal mine safety analysis operations.

[0083] In this embodiment of the invention, environmental data from coal mine engineering is collected, including: high-frequency gas concentration data: the concentrations of methane (CH4), carbon monoxide (CO), carbon dioxide (CO2), and hydrogen sulfide (H2S) that change frequently after an explosion are obtained through laser spectral sensors and infrared sensors; ventilation status data: including the working status of ventilation fans, wind speed sensor data, airflow direction, and cross-sectional ventilation parameters. The three-dimensional structure of the mine shafts, ventilation paths, node topology, and their spatial relationships are extracted from the coal mine engineering geographic data; a graph topology modeling method is used to construct a spatial grid topology model of the coal mine, forming the geometric basis for coupling environmental data. The high-frequency gas concentration data is spatially registered with the geographic topology; a multi-source data fusion algorithm (such as Bayesian estimation or Kalman filtering) is used to integrate ventilation status and gas data, generating an initial dataset of the post-disaster gas field under a unified timestamp. A thermo-mass coupled diffusion model is constructed, based on the coupled derivation of the Navier-Stokes equation and Fick's diffusion law, to model the linkage between the gas temperature gradient and mass diffusion; the initial dataset of the post-disaster gas field is input, and the residual gas distribution equation is iteratively solved by combining the ventilation disturbance function. A deep learning model, such as a multi-scale convolutional residual network (ResUNet), is constructed for concentration inversion in the spatial-temporal dimensions. Network training samples can be generated based on historical coal mine accident scenario simulations. The output is a concentration prediction tensor for each gas, and residual concentration distribution results are generated through inversion. The inversion results are mapped back into a 3D topological model of the mine shaft to generate a spatial distribution map of gas components. The output includes residual spatial concentration maps of gases such as CH4, CO, and H2S at different time frames. Multi-order gradient operators (such as Laplacian of Gaussian and higher-order Sobol filtering) are applied to the residual spatial concentration maps. The boundaries of regions with abrupt changes in gas concentration are extracted as suspected detonation source boundary features. Vector direction field backtracking is performed using the feature boundary points. Possible paths to the detonation point are calculated using a gas source tracing streamline inversion algorithm combined with backward Euler Approximation. Cluster analysis is performed on the intersection regions of all paths to generate an estimated coordinate domain for the explosion point. Based on the estimated detonation coordinates and current gas concentration, a time-recursive gas transport equation is used for prediction. A Moving Source Gaussian Plume Model is introduced to predict the toxic gas diffusion trajectory. A three-dimensional dynamic map of the spatial concentration evolution of toxic gas over time is output, i.e., the spatial distribution evolution map of toxic gas. The residual gas concentration inversion network, the estimated coordinates of the explosion point, and the toxic gas evolution map are coupled. Based on a multi-dimensional fusion algorithm (such as tensor fusion or graph neural network GNN), a dynamic evolution map of post-coal mine disaster air quality is constructed. The map supports querying air quality risk areas by time slice and supports multi-gas hierarchical visualization.Set regional concentration thresholds (e.g., CH4>2%, CO>30ppm, etc.); perform threshold comparison analysis on any spatial cell and time slice in the spectrum; areas above the threshold are marked as "high-risk areas", and the system automatically generates a safety risk level map and corresponding emergency response strategy suggestions.

[0084] Preferably, step S1 includes the following steps:

[0085] Step S11: Obtain coal mine engineering environmental data and coal mine engineering geographic data, wherein the coal mine engineering environmental data includes high-frequency gas concentration data and ventilation status data;

[0086] Step S12: Perform high-frequency time series resampling on the original coal mine engineering environment data to generate high-frequency gas concentration time data;

[0087] Step S13: Divide the coal mine ventilation status data into regional ventilation modes and generate local ventilation topology data of the coal mine;

[0088] Step S14: Perform three-dimensional topology reconstruction on the coal mine engineering geographic data to generate coal mine geographic topology grid data;

[0089] Step S15: Perform spatiotemporal fusion interpolation on high-frequency gas concentration time data and local ventilation topology data of coal mine to generate coal mine ventilation-gas joint field data; integrate coal mine ventilation-gas joint field data with coal mine geographic topology grid data to form the initial dataset of coal mine post-disaster gas field.

[0090] In this embodiment of the invention, coal mine engineering environmental data is acquired using a coal mine sensor network system, specifically including: high-frequency gas concentration data: collected through underground distributed sensors, with a sampling frequency of not less than 1Hz, covering key gases such as methane (CH4), carbon monoxide (CO), carbon dioxide (CO2), and hydrogen sulfide (H2S); ventilation status data: wind speed, wind pressure, wind direction, and fan operating status at each ventilation node are collected. Simultaneously, the data is integrated into a coal mine geographic information system (MineGIS) to export coal mine engineering geographic data, including shaft and tunnel structure, goaf, ventilation zones, and control point coordinates. Due to noise and inconsistent sampling intervals in the original sensor data, a unified time reference is required. The original gas concentration data is calibrated on the time axis using an interpolation-based time resampling algorithm: linear interpolation or spline interpolation is used to fill in time periods with missing data; ensuring consistent time steps after resampling (e.g., 1s or 0.5s), generating high-frequency gas concentration time data, represented as a gas concentration time tensor G(t, x, y, z). Based on ventilation status data and mine roadway spatial information, the ventilation operation characteristics of different areas are identified. Clustering algorithms (such as K-means or DBSCAN) are used to classify wind speed and direction data into patterns, forming regional ventilation pattern labels. Ventilation patterns are embedded in the 3D roadway network to construct local coal mine ventilation topology data, represented as a graph structure V = (N, E), where node N is the ventilation control point, edge E is the airflow channel, and weighted attributes (such as wind speed and ventilation pattern number) are added. Spatial reconstruction of the coal mine engineering geographic data is performed using voxel modeling or tetrahedral meshing methods for 3D topology reconstruction. 3D Delaunay triangulation technology is used to construct coal mine geographic topology mesh data, with a multi-level nested mesh structure. Each mesh cell has the following attributes: mesh coordinate range; roadway type (main roadway, auxiliary roadway, return airway, etc.); adjacency topology relationships; and boundary attributes. Spatial interpolation is performed between the high-frequency gas concentration time data obtained in step S12 and the local ventilation topology obtained in step S13. High-dimensional Kriging interpolation or inverse distance weighting (IDW) is used to expand the gas data within the ventilation topology structure, forming multi-point spatiotemporally coupled data. Coal mine ventilation-gas joint field data is constructed, represented as a five-dimensional tensor F(t, x, y, z, c), where c represents the gas type channel dimension. The joint field data F is spatially bound to a three-dimensional geographic topology grid. Corresponding gas-ventilation information is injected into each geographic grid cell through grid attribute indexing and topological constraint rules. The final output is the initial dataset of the coal mine post-disaster gas field, represented as: the concentration changes of various gases and ventilation vectors corresponding to each spatial cell (voxel) in a three-dimensional structure; possessing time-series attributes, it can be used for subsequent simulation and inversion analysis.

[0091] As an example of the present invention, reference is made to Figure 2 As shown, in this example, step S2 includes:

[0092] Step S21: Estimate the heat-mass transport coefficient of the initial dataset of the post-disaster gas field using the heat-mass co-diffusion equation;

[0093] Step S22: Perform dynamic diffusion field simulation on the initial dataset of the coal mine post-disaster gas field using the heat-mass transfer coefficient to generate post-disaster gas residual diffusion evolution data;

[0094] Step S23: Perform residual fitting on the post-disaster gas residual diffusion evolution data to construct a residual gas concentration inversion network;

[0095] Step S24: Use the residual gas concentration inversion network to perform spatial inversion calculations on the initial dataset of the gas field after the coal mine disaster to generate three-dimensional reconstruction data of residual gas concentration; perform multi-component spectrum separation and spatial clustering analysis on the three-dimensional reconstruction data of residual gas concentration to generate spatial concentration residual spectra of each gas component.

[0096] In this embodiment of the invention, the diffusion characteristics of the gas field after a coal mine disaster are quantified to determine the gas propagation speed and path under the coupled influence of high temperature and ventilation. First, a simulation scenario is established based on the three-dimensional spatial grid of the coal mine and the initial gas concentration distribution. Temperature and gas concentration change data are collected at different times and locations after the explosion. Combined with the ventilation status of different areas of the coal mine, a coupled analysis is performed using simulation algorithms (such as finite difference or finite element methods). By comparing historical data with simulation results, the diffusion capacity of the gas in different areas is estimated, i.e., the thermal diffusivity and concentration diffusivity. Finally, a set of data describing the heat-mass transfer characteristics is formed for subsequent simulation analysis. This study simulates the diffusion trajectory and changes of residual hazardous gases in coal mine tunnels and cavities after an explosion, applying estimated diffusion coefficient data to the initial gas field. Using 3D gas simulation software or a self-built model, factors such as post-disaster ventilation changes and the presence of local heat sources are considered. Dynamic simulation is initiated, continuously advancing multiple time steps to observe how different gas components propagate and dilute in space. Simulation results are output in time-series format, forming high-resolution data on the evolution of residual gas diffusion. The data includes the concentration changes of various gases at different times and spaces, used to analyze trends in high-risk areas. An intelligent model is established to predict gas distribution at a specific time point based on initial data, improving the accuracy of spatial distribution estimation. The simulation results are compared with data collected by actual sensors to extract simulation error information. Based on this error information, a multi-layer three-dimensional neural network is constructed, with an input layer, a convolutional processing layer, a residual correction layer, and an output layer. The initial gas field of the coal mine is used as the model input, and the error is used as the training objective to iteratively train the network. After training, the inversion network can intelligently infer a more accurate spatial distribution of gas concentration based on the initial environment. The model has generalization ability and can adapt to different ventilation structures and gas composition combinations. The spatial distribution characteristics of different gas components are identified from the predicted three-dimensional gas distribution results, and their residual hotspots are analyzed. The gas concentration distribution map in the coal mine space is reconstructed using the results output by the inversion network. For multiple component gases, feature extraction algorithms are used for separation processing to clarify the distribution characteristics of each type of gas in different regions. Spatial clustering analysis is performed on the distribution of each gas to identify its high-concentration residual regions and boundaries. During the clustering analysis, voxels are divided into different levels, and the correlation between adjacent high-concentration regions is identified. Finally, a three-dimensional concentration residual map of each component gas is generated for subsequent explosion point location and toxic gas evolution analysis.

[0097] Preferably, step S24, which involves multi-component spectral separation and spatial clustering analysis of the three-dimensional reconstruction data of residual gas concentration, includes:

[0098] Fourier transform was performed on the three-dimensional reconstruction data of residual gas concentration, and the spectral response features of CH4, CO, CO2, and H2S after transformation were extracted to generate spectral response feature data.

[0099] Blind source separation was performed on the three-dimensional reconstruction data of residual gas concentration using spectral response feature data, and the response signals of independent gases CH4, CO, CO2, and H2S were extracted to generate an independent gas component concentration dataset.

[0100] Perform three-dimensional spatial cluster analysis on independent gas component concentration datasets to generate spatial cluster map data of gas components;

[0101] Geometric fitting and boundary reconstruction are performed on the spatial clustering map data of gas components to generate spatial concentration isosurface map data;

[0102] By integrating independent gas component concentration data with isosurface map data, spatial concentration residual maps of each gas component are generated.

[0103] In this embodiment of the invention, frequency domain transformation processing is performed on the three-dimensional reconstructed data of residual gas concentration. A three-dimensional Fourier transform method is used to map the spatial variation of gas concentration at each location to the frequency domain. The main frequency response features of the target gases (CH4, CO, CO2, H2S) in the frequency domain, such as peak position, spectral amplitude, and frequency domain energy distribution, are extracted. A multi-dimensional feature vector dataset containing spectral response features is constructed to provide a basis for subsequent signal separation. Finally, spectral response feature data is formed, which reflects the variation patterns of different gases in the spatial frequency domain. Blind source separation algorithms such as Independent Component Analysis (ICA) are used to process the spectral response feature data. Without relying on prior gas templates, the independent concentration signals exhibited by each gas in space are automatically extracted. A three-dimensional concentration dataset of independent gas components such as CH4, CO, CO2, and H2S is generated. This dataset has clear component attribution and spatial distribution characteristics, significantly improving the accuracy of subsequent cluster analysis. Based on each independent gas component concentration dataset, density-based clustering methods (such as DBSCAN and OPTICS) are used for three-dimensional spatial clustering. The clustering analysis fully considers the concentration similarity and spatial connectivity between neighboring voxels. The aggregation centers, high-concentration distribution areas, and boundary structures of various gases within the mine space are identified. The output is a spatial clustering map of gas components, including the geometric extent and component characteristics of each cluster region. Geometric surface reconstruction is performed on each cluster region in the spatial clustering map. Three-dimensional isosurface extraction algorithms (such as Marching Cubes) are used to extract the isoconcentration boundaries of each cluster region. The extracted isosurfaces are smoothed and structurally fitted to enhance boundary discernibility. Finally, spatial concentration isosurface map data is generated, representing the high, medium, and low concentration levels of each gas in space. The concentration data of independent gas components are registered and fused with the corresponding spatial isosurface maps; the concentration levels of different components are classified and labeled according to the concentration range and spatial location; a unified spatial concentration residual map is constructed, which has three-dimensional display capabilities and attribute query functions; each type of gas in the map has an independent level, clear structural boundaries, and clear spatial variation trends, which is suitable for subsequent spatial reasoning and evolution simulation.

[0104] As an example of the present invention, reference is made to Figure 3 As shown, step S3 in this example includes:

[0105] Step S31: Calculate the local concentration change rate for each type of harmful gas in the spatial concentration residual map, and extract the high-order concentration gradient boundary feature data of the spatial concentration residual map based on the local concentration change rate.

[0106] Step S32: Based on the local concentration change rate, perform toxic gas distribution analysis on each type of harmful gas in the spatial concentration residual spectrum to construct a toxic gas distribution spectrum; reconstruct the anti-diffusion vector field of the high-order concentration gradient boundary feature data to generate multi-directional equipotential vector tracking data;

[0107] Step S33: Simulate the shock wave-ventilation path co-propagation of the high-order concentration gradient boundary feature data based on the multi-directional equipotential vector tracking data, and confirm the location of the initial energy source of the explosion by combining the simulation results with the concentration peak sequence and diffusion reverse vector trajectory of the spatial concentration residual spectrum, and generate the estimated coordinate domain of the explosion point.

[0108] Step S34: Couple the estimated coordinate domain of the explosion point with the toxic gas distribution map to perform diffusion modeling and generate a time-varying initial diffusion field of toxic gas; perform time-step simulation based on the time-varying initial diffusion field data of toxic gas to generate a spatial distribution evolution map of toxic gas residue.

[0109] In this embodiment of the invention, by traversing the three-dimensional data of each type of hazardous gas in the spatial concentration residual spectrum, the concentration change rate per unit volume within its local voxel neighborhood is calculated; spatial differentiation processing is performed on the change rate to identify high-gradient regions with significant concentration changes; high-order concentration gradient boundary features are extracted, including boundary shape, continuity, abrupt change points, and direction of change; high-order concentration gradient boundary feature data are output for subsequent anti-diffusion and vector tracking analysis. Based on the toxicological hazard level of each type of gas and combined with the local concentration change rate, multiple risk concentration classification thresholds are set; a toxic gas distribution spectrum is constructed, spatial ranges are divided according to toxicity level, and key high-risk areas are marked; the spectrum contains attribute information such as three-dimensional location, concentration level, and distribution range. Vector back-diffusion modeling is performed on the extracted high-order concentration gradient boundary features; the source tracing path of the gas is simulated, and a multi-directional equipotential vector field is constructed; multi-directional equipotential vector tracing data is generated as a path reference for subsequent energy propagation simulation; the multi-directional equipotential vector tracing data is coupled with the coal mine ventilation topology; the back propagation trend of the shock wave along the main ventilation path is simulated; ventilation factors such as wind speed, wind direction, and drag coefficient are considered during the simulation; and a cooperative propagation path map of the shock wave and ventilation path is output. The concentration peak sequence and its diffusion back-diffusion vector trajectory are extracted from the spatial concentration residual spectrum; they are spatially superimposed with the cooperative propagation path map; the overlapping region of the concentration peak source and the vector convergence point is found; the explosion point estimation coordinate domain is generated, and the output is the probability distribution range of the three-dimensional spatial location. The explosion point estimation coordinate domain is spatially coupled with the toxic gas distribution spectrum; initial boundary conditions such as initial concentration distribution, wind conditions, and structural obstacles are set; and a time-varying initial diffusion field of toxic gas is constructed, including diffusion initiation, direction, and velocity models. The initial diffusion field of toxic gas is simulated in discrete time steps to calculate the spatial distribution at different time points. The effects of ventilation disturbance, adsorption, and gas density differences on the propagation path are considered. A three-dimensional residual concentration map of toxic gas is output at each time step to form a continuous evolution map. Finally, a spatial distribution evolution map of toxic gas residue is generated for safety assessment and emergency decision support.

[0110] Preferably, step S33 includes the following steps:

[0111] Step S331: Divide the regional shock wave response sensitivity into regions based on the high-order concentration gradient boundary feature data, and generate shock wave action weight distribution data;

[0112] Step S332: Perform main vector ventilation guidance identification on the multi-directional equipotential vector tracking data to generate ventilation dominant path feature data; perform joint path mapping on the shock wave impact weight distribution data and the ventilation dominant path feature data to generate shock wave-ventilation cooperative propagation simulation data;

[0113] Step S333: Extract the concentration peak sequence from the spatial concentration residual spectrum to generate explosion feature point sequence data; perform diffusion reverse vector fitting on the explosion feature point sequence data to generate explosion energy reverse propagation trajectory data;

[0114] Step S334: Perform path intersection analysis on the simulated data of shock wave-ventilation coordinated propagation and the reverse propagation trajectory data of explosion energy to generate the estimated coordinate domain of the explosion point.

[0115] In this embodiment of the invention, high-order concentration gradient boundary feature data are mapped onto a three-dimensional spatial grid. Shock wave response is evaluated for each spatial region (voxel unit) based on factors such as concentration abrupt change intensity, boundary continuity, and spatial topological complexity. Regions are classified into high-sensitivity, medium-sensitivity, and low-sensitivity areas according to their response levels. Corresponding shock wave impact weights are assigned to each type of region, forming a spatial hierarchical structure. Shock wave impact weight distribution data is output for collaborative modeling of ventilation paths. Vector direction clustering is performed on multi-directional equipotential vector tracking data. Paths with stable flow directions and significant flow velocities are selected based on ventilation system design diagrams, ventilation velocity distribution, or sensor data. The dominant airflow path in the ventilation system is extracted, and ventilation dominant path feature data is output. The shock wave impact weight distribution data and ventilation dominant path feature data are spatially mapped and fused. During the fusion process, the guiding effect of the ventilation dominant direction on the shock wave propagation trend is considered. Shock wave-ventilation collaborative propagation simulation data is constructed to reflect the interactive dynamics between the post-explosion pressure wave and the ventilation system. Peak concentration points, abrupt concentration change points, and boundary convergence points are identified in the spatial concentration residual spectrum. These points are then used to construct a temporally and spatially continuous sequence of explosion indication points, outputting a sequence of explosion characteristic points. Based on the spatial distribution and temporal trend of the explosion characteristic point sequence, a spatial vector trajectory fitting and backtracking method is applied to construct potential reverse propagation paths of explosion energy. This outputs reverse propagation trajectory data of explosion energy, which is used for intersection analysis with cooperative propagation simulations. A three-dimensional spatial path intersection analysis is performed on the shock wave-ventilation cooperative propagation simulation data and the reverse propagation trajectory data of explosion energy. Dense areas of intersection points, areas with high probability of path overlap, and spatial segments with significant directional consistency are identified. Combined with information such as spatial terrain and obstacle structures, inaccessible or physically unreasonable areas are excluded. Finally, the estimated coordinate domain of the explosion point, i.e., the inferred candidate area of ​​the explosion source, is output, which can be used for emergency response or accident investigation.

[0116] Preferably, the main vector ventilation guidance identification for multi-directional equipotential vector tracking data includes:

[0117] Perform vector direction consistency clustering analysis on multi-directional equipotential vector tracking data to generate equipotential vector main direction cluster data; evaluate the airflow coupling strength of equipotential vector main direction cluster data to generate ventilation adaptability matching score data.

[0118] Multi-scale path topology mapping is performed on the ventilation adaptability matching score data to generate ventilation path fitting grid data; time-series wind speed dynamic playback analysis is performed on the ventilation path fitting grid data to generate dynamic ventilation flow trend map data.

[0119] A path stability and dominance weight fusion analysis was performed on the dynamic ventilation flow trend map data to generate ventilation dominant path characteristic data.

[0120] In this embodiment of the invention, multi-directional equipotential vector tracking data is mapped to a three-dimensional vector field; consistent clustering of vector directions is performed using direction cosine or spherical clustering algorithms; vector groups with high directional stability and small fluctuations are preferentially retained in the clusters; the clustered equipotential vector principal direction cluster data is output for subsequent airflow adaptability analysis. The equipotential vector principal direction clusters are spatially compared with the actual ventilation layout data of the mine; the consistency of each cluster direction with the duct structure, air pressure direction, and known velocity distribution is analyzed; the coupling strength of each direction cluster is scored using an adaptability scoring method; ventilation adaptability matching score data is output as an important basis for selecting the dominant path. Based on the adaptability matching score, direction clusters with high adaptability are selected; spatial projection and path reconstruction are performed on them at different scales (coarse-medium-fine); ventilation path fitting grid data reflecting the continuity and unobstructedness of airflow channels are constructed; the node connection relationships with unobstructed dominant directions and good geometric continuity are retained in the grid. Existing wind speed observation data, simulation data, or time-series boundary conditions are mapped to a ventilation path fitting mesh. A time-series progressive analysis is performed within the mesh structure to simulate the propagation trend of wind speed over time. Dynamic ventilation flow trend data is output to assess the stability and dominance of the path. The stability of the dynamic ventilation flow trend map is evaluated, including indicators such as wind speed fluctuation amplitude and direction retention rate. Simultaneously, dominance weight analysis is performed, considering factors such as ventilation volume percentage and the path's control over traversed areas. The stability analysis results are weighted and fused with the dominance indicators to form characteristic data of the dominant ventilation path reflecting the main airflow channels, which is used for co-modeling with the shock wave propagation path.

[0121] Preferably, step S4 includes the following steps:

[0122] Step S41: Spatial fitting and reconstruction of the residual gas concentration inversion network to generate high-dimensional gas concentration inversion matrix data;

[0123] Step S42: Superimpose the estimated coordinate domain of the explosion point with the high-dimensional inversion matrix data of gas concentration to generate perturbation-enhanced gas concentration field data.

[0124] Step S43: Perform three-dimensional multi-temporal field fusion of the perturbation-enhanced gas concentration field data and the spatial distribution evolution map of toxic gas to generate a dynamic evolution map of air quality after a coal mine disaster.

[0125] Step S44: Use the preset regional concentration threshold to determine the regional concentration threshold of the dynamic evolution map of air quality after the coal mine disaster, and generate the concentration exceeding the limit identification data of dangerous sections; perform spatial distribution clustering and temporal evolution trend analysis on the concentration exceeding the limit identification data of dangerous sections, and generate a coal mine safety risk level labeling map to perform coal mine safety analysis operations.

[0126] In this embodiment of the invention, a deep inversion neural network is constructed based on historical concentration sampling data, residual gas observation point data, and gas physical diffusion laws. The network input includes features such as spatial coordinates, gas type, wind speed and direction, and temperature. High-density sampling and fitting are performed on the entire coal mine space to output a high-dimensional fitted concentration matrix. Finally, a high-dimensional gas concentration inversion matrix data is generated as the basic descriptive unit for post-disaster spatial concentration. The estimated coordinate domain of the explosion point obtained in step S33 is extracted and used as the center of the disturbance source. Local disturbance response modeling is applied to the high-dimensional gas concentration inversion matrix data. The explosion intensity parameters, impact radius, and superimposed gas diffusion weighting factors in the disturbance model are considered. The output is disturbance-enhanced gas concentration field data with local pressure disturbance amplification characteristics. The data on the enhanced gas concentration field due to disturbance are aligned with the spatial distribution evolution map of toxic gases generated in step S34 using a three-dimensional temporal field. Differential evolution modeling is performed for multiple time points (e.g., 5 min, 15 min, 30 min, 1 h). Gas types are classified and fused, including toxic gases such as methane, carbon monoxide, and hydrogen sulfide. A visual representation of post-coal mine air quality is generated: a dynamic evolution map of post-coal mine air quality, used for dynamic monitoring and decision support. Based on the safety thresholds for various gas concentrations stipulated by the enterprise, regional concentration exceedance standards are defined. These concentration thresholds are mapped to the dynamic evolution map of coal mine air quality, and time-series judgments are performed on a region-by-region basis. Spatial location data of concentration anomaly sections are output, i.e., concentration exceedance identification data of dangerous sections. Spatial clustering (e.g., DBSCAN) and temporal trend analysis (e.g., sliding window regression) are performed on the exceedance sections. Risk classification is performed based on parameters such as the degree of exceedance, duration, and spatial range. Finally, a coal mine safety risk level labeling map for production scheduling and emergency command is generated, providing auxiliary decision-making basis for mine operation safety analysis.

[0127] This specification provides a coal mine safety analysis system based on big data analytics for executing the aforementioned coal mine safety analysis method based on big data analytics. The coal mine safety analysis system based on big data analytics includes:

[0128] The gas field identification module is used to acquire coal mine engineering environmental data and coal mine engineering geographic data. The coal mine engineering environmental data includes high-frequency gas concentration data and ventilation status data. It extracts the geographic topology information of the coal mine engineering geographic data and integrates the coal mine engineering environmental data into an initial dataset of gas fields after a coal mine disaster.

[0129] The concentration analysis module is used to perform thermo-mass coupled diffusion analysis on the initial dataset of the gas field after a coal mine disaster, and generate a residual gas concentration inversion network. The residual gas concentration inversion network is used to invert the spatial distribution of residual gas on the initial dataset of the gas field after a coal mine disaster, and obtain the spatial concentration residual spectrum of each gas component.

[0130] The distribution evolution module is used to extract high-order concentration gradient boundary feature data of the spatial concentration residue map of each gas component, and to perform reverse source tracing calculation of the explosion initiation point of the high-order concentration gradient boundary feature data to generate the explosion point estimation coordinate domain; based on the explosion point estimation coordinate domain, the spatial distribution evolution of toxic gas residue is predicted in the spatial concentration residue map to generate the toxic gas spatial distribution evolution map.

[0131] The safety assessment module is used to couple and fuse the residual gas concentration inversion network, the explosion point estimation coordinate domain, and the toxic gas spatial distribution evolution map to construct a dynamic evolution map of air quality after a coal mine disaster. It uses preset regional concentration thresholds to conduct a safety risk assessment on the dynamic evolution map of air quality after a coal mine disaster in order to perform coal mine safety analysis operations.

[0132] The beneficial effects of this invention lie in the fact that the gas field identification module, by integrating high-frequency gas concentration data, ventilation status data, and coal mine engineering geographical topology information, achieves systematic collection and fusion of complex post-disaster environmental data in coal mines. This ensures the comprehensiveness, timeliness, and spatial accuracy of the initial dataset of post-disaster gas fields, providing a solid data foundation for subsequent diffusion analysis. The concentration analysis module, relying on a thermo-mass coupling diffusion model, constructs a residual gas concentration inversion network, accurately capturing the multi-physics diffusion characteristics of post-disaster gases in coal mines. It achieves high-precision inversion and component separation of spatial concentration residual spectra for each gas component, effectively revealing the spatial distribution patterns of post-disaster gas diffusion. The distribution evolution module utilizes high-order concentration gradient boundary feature data, combined with a reverse source tracing algorithm, to accurately locate the explosion initiation point, significantly improving the spatial accuracy of explosion source estimation. Based on the spatial distribution evolution prediction of toxic gas residues in the explosion point estimation coordinate domain, it realizes dynamic tracking and evolution simulation of the post-disaster toxic gas diffusion process. The safety assessment module couples and fuses residual gas concentration inversion networks, explosion point estimation coordinate domains, and toxic gas spatial distribution evolution maps in multiple dimensions to form a dynamic three-dimensional evolution map of post-disaster air quality, enabling real-time monitoring and trend prediction of spatiotemporal changes in air pollution. By setting concentration thresholds for risk assessment on the dynamic evolution map, it achieves rapid identification of hazardous areas and classification of safety levels, providing scientific and quantitative decision support for coal mine safety management and emergency response, and significantly improving the efficiency and accuracy of post-disaster safety analysis in coal mines. Therefore, this invention, through multi-source data fusion and thermo-mass coupling inversion, achieves high-precision dynamic monitoring of post-disaster gas fields and accurate location of explosion sources in coal mines, enhancing the real-time assessment capability of coal mine safety risks.

[0133] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0134] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A coal mine safety analysis method based on big data analysis, characterized in that, The method comprises the following steps: Step S1: obtaining coal mine engineering environment data and coal mine engineering geographic data, wherein the coal mine engineering environment data comprises high-frequency gas concentration data and ventilation state data; extracting geographic topological information of the coal mine engineering geographic data, and integrating the coal mine engineering environment data as initial data set of a coal mine post-disaster gas field; Step S2: performing heat-mass coupled diffusion analysis on the initial data set of the coal mine post-disaster gas field to generate a residual gas concentration inversion network; using the residual gas concentration inversion network to perform residual gas spatial distribution inversion on the initial data set of the coal mine post-disaster gas field to obtain a spatial concentration residual map of each gas component; Step S3: extracting high-order concentration gradient boundary feature data of the spatial concentration residual map of each gas component, and performing explosion starting point source reverse tracing calculation on the high-order concentration gradient boundary feature data to generate an explosion point estimation coordinate domain; based on the explosion point estimation coordinate domain, performing toxic gas residual space distribution evolution prediction on the spatial concentration residual map to generate a toxic gas space distribution evolution map; Step S4: coupling and fusing the residual gas concentration inversion network, the explosion point estimation coordinate domain and the toxic gas space distribution evolution map to construct a coal mine post-disaster air quality dynamic evolution map; using a preset regional concentration threshold to perform safety risk assessment on the coal mine post-disaster air quality dynamic evolution map to perform a coal mine safety analysis operation; Step S4 comprises the following steps: Step S41: performing spatial fitting reconstruction on the residual gas concentration inversion network to generate high-dimensional inversion matrix data of gas concentration; Step S42: superimposing the explosion point estimation coordinate domain and the high-dimensional inversion matrix data of gas concentration to generate perturbation enhanced gas concentration field data; Step S43: performing three-dimensional multi-time field fusion on the perturbation enhanced gas concentration field data and the toxic gas space distribution evolution map to generate a coal mine post-disaster air quality dynamic evolution map; Step S44: using a preset regional concentration threshold to perform regional concentration threshold judgment on the coal mine post-disaster air quality dynamic evolution map to generate dangerous section concentration overrun identification data; performing spatial distribution clustering and time sequence evolution trend analysis on the dangerous section concentration overrun identification data to generate a coal mine safety risk level labeling map to perform a coal mine safety analysis operation.

2. The coal mine safety analysis method based on big data analysis according to claim 1, characterized in that, Step S1 comprises the following steps: Step S11: obtaining coal mine engineering environment data and coal mine engineering geographic data, wherein the coal mine engineering environment data comprises high-frequency gas concentration data and ventilation state data; Step S12: performing high-frequency time sequence resampling on the coal mine engineering environment original data to generate high-frequency gas concentration time data; Step S13: performing regional ventilation mode division on the coal mine ventilation state data to generate coal mine local ventilation topological structure data; Step S14: performing three-dimensional topological reconstruction on the coal mine engineering geographic data to generate coal mine geographic topological grid data; Step S15: performing space-time fusion interpolation on the high-frequency gas concentration time data and the coal mine local ventilation topological structure data to generate coal mine ventilation-gas combined field data; integrating the coal mine ventilation-gas combined field data and the coal mine geographic topological grid data as the initial data set of the coal mine post-disaster gas field.

3. The coal mine safety analysis method based on big data analysis according to claim 1, characterized in that, Step S2 comprises the following steps: Step S21: Estimate the heat-mass transfer coefficient of the initial data set of the post-disaster gas field in the coal mine by using the heat-mass coupled diffusion equation; Step S22: Perform dynamic diffusion field simulation on the initial data set of the post-disaster gas field in the coal mine by using the heat-mass transfer coefficient, to generate residual diffusion evolution data of the post-disaster gas; Step S23: Perform residual fitting on the residual diffusion evolution data of the post-disaster gas to construct a residual gas concentration inversion network; Step S24: Perform spatial inversion calculation on the initial data set of the post-disaster gas field in the coal mine by using the residual gas concentration inversion network, to generate three-dimensional reconstruction data of the residual gas concentration; perform multi-component spectral separation and spatial clustering analysis on the three-dimensional reconstruction data of the residual gas concentration, to generate a spatial concentration residual map of each gas component.

4. The coal mine safety analysis method based on big data analysis according to claim 3, characterized in that, The multi-component spectral separation and spatial clustering analysis on the three-dimensional reconstruction data of the residual gas concentration in step S24 includes: Perform Fourier transform on the three-dimensional reconstruction data of the residual gas concentration, and extract the spectral response characteristics of CH4, CO, CO2 and H2S after transformation to generate spectral response characteristic data; Perform blind source separation on the three-dimensional reconstruction data of the residual gas concentration by using the spectral response characteristic data, extract the response signals of independent gas components CH4, CO, CO2 and H2S, and generate an independent gas component concentration data set; Perform three-dimensional spatial clustering analysis on the independent gas component concentration data set to generate gas component spatial clustering map data; Perform geometric fitting and boundary reconstruction on the gas component spatial clustering map data to generate spatial concentration isosurface map data; Integrate the independent gas component concentration data and the isosurface map data to generate a spatial concentration residual map of each gas component.

5. The coal mine safety analysis method based on big data analysis according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Calculate the local concentration change rate of each type of harmful gas in the spatial concentration residual map, and extract high-order concentration gradient boundary feature data of the spatial concentration residual map based on the local concentration change rate; Step S32: Perform toxic gas distribution analysis on each type of harmful gas in the spatial concentration residual map based on the local concentration change rate, to construct a toxic gas distribution map; perform inverse diffusion vector field reconstruction on the high-order concentration gradient boundary feature data to generate multi-directional equipotential vector tracking data; Step S33: Perform shock wave-ventilation path collaborative propagation path simulation on the high-order concentration gradient boundary feature data according to the multi-directional equipotential vector tracking data, and perform explosion initial energy source position confirmation on the simulation results and the concentration peak sequence of the spatial concentration residual map and its diffusion inverse vector trajectory, to generate an explosion point estimation coordinate domain; Step S34: Perform coupling diffusion modeling on the explosion point estimation coordinate domain and the toxic gas distribution map to generate a toxic gas time-varying initial diffusion field; perform time step simulation based on the toxic gas time-varying diffusion initial field data to generate a toxic gas residual spatial distribution evolution map.

6. The coal mine safety analysis method based on big data analysis according to claim 5, characterized in that, Step S33 includes the following steps: Step S331: Divide the high-order concentration gradient boundary feature data into regions according to the response sensitivity of the shock wave, to generate shock wave action weight distribution data; Step S332: main vector ventilation guide identification is performed on the multi-directional isopotential vector tracking data to generate ventilation main path feature data; and joint path mapping is performed on the shock wave action weight distribution data and the ventilation main path feature data to generate shock wave-ventilation collaborative propagation simulation data; Step S333: a concentration peak sequence of the spatial concentration residual map is extracted to generate an explosion feature point sequence data; and diffusion reverse vector fitting is performed on the explosion feature point sequence data to generate explosion energy reverse propagation trajectory data; Step S334: path intersection analysis is performed on the shock wave-ventilation collaborative propagation simulation data and the explosion energy reverse propagation trajectory data to generate an explosion point estimated coordinate domain.

7. The coal mine safety analysis method based on big data analysis according to claim 6, characterized in that, The main vector ventilation guide identification on the multi-directional isopotential vector tracking data comprises: vector direction consistency clustering analysis is performed on the multi-directional isopotential vector tracking data to generate isopotential vector main direction cluster data; and wind flow coupling strength evaluation is performed on the isopotential vector main direction cluster data to generate ventilation adaptability matching score data; multi-scale path topological mapping is performed on the ventilation adaptability matching score data to generate ventilation path fitting grid data; and time sequence wind speed dynamic playback analysis is performed on the ventilation path fitting grid data to generate dynamic ventilation flow trend map data; path stability and main direction weight fusion analysis is performed on the dynamic ventilation flow trend map data to generate ventilation main path feature data.

8. The coal mine safety analysis method based on big data analysis according to claim 5, characterized in that, The time step simulation based on the toxic gas time-varying diffusion initial field data in step S34 comprises: multi-parameter thermal mass transport coefficient extraction is performed based on the toxic gas time-varying diffusion initial field data to generate diffusion evolution control parameter set data, wherein the multi-parameter thermal mass transport coefficient extraction comprises mass diffusion coefficient, thermal diffusion coefficient and concentration gradient change rate of each gas; three-dimensional multi-physical field time sequence grid initialization is performed on the diffusion evolution control parameter set data to generate toxic gas diffusion time step cell data; and dynamic time sequence solving based on stable state and boundary disturbance is performed on the toxic gas diffusion time step cell data to generate toxic gas multi-time concentration evolution field data; high-order spatial interpolation and continuity enhancement processing is performed on the toxic gas multi-time concentration evolution field data to generate toxic gas concentration time continuous evolution map; toxic gas residual space distribution evolution map is generated by performing regional residual intensity clustering analysis on the toxic gas concentration time continuous evolution map.

9. A coal mine safety analysis system based on big data analysis, characterized in that, The coal mine safety analysis system based on the big data analysis for performing the coal mine safety analysis method as claimed in claim 1 comprises: a gas field identification module, configured to acquire coal mine engineering environment data and coal mine engineering geographic data, wherein the coal mine engineering environment data comprises high-frequency gas concentration data and ventilation state data; extract geographic topological information of the coal mine engineering geographic data, and integrate the coal mine engineering environment data into a coal mine post-disaster gas field initial data set; a concentration analysis module, configured to perform thermal mass coupled diffusion analysis on the coal mine post-disaster gas field initial data set to generate a residual gas concentration inversion network; and perform residual gas spatial distribution inversion on the coal mine post-disaster gas field initial data set by using the residual gas concentration inversion network to obtain a spatial concentration residual map of each gas component; The distribution evolution module is configured to extract high-order concentration gradient boundary feature data of a spatial concentration residual map of each gas component, perform explosion starting point source backtracking calculation on the high-order concentration gradient boundary feature data, and generate an explosion point estimation coordinate domain; perform toxic gas residual spatial distribution evolution prediction on the spatial concentration residual map based on the explosion point estimation coordinate domain, and generate a toxic gas spatial distribution evolution map. The safety evaluation module is configured to couple and fuse the residual gas concentration inversion network, the explosion point estimation coordinate domain, and the toxic gas spatial distribution evolution map to construct a coal mine post-disaster air quality dynamic evolution map; perform safety risk evaluation on the coal mine post-disaster air quality dynamic evolution map by using a preset regional concentration threshold, and execute a coal mine safety analysis operation.

Images