Coal mine safety production management system for comprehensive disaster prevention and control

Abstract

The invention relates to a coal mine safety production management system for comprehensive disaster prevention and control. The method comprises the following steps: an area division module used for dividing a mining area into a plurality of local evaluation areas according to the geological structure and mining layout of a mine; the data acquisition module is used for acquiring mining environment data and miner state data based on the local evaluation area; the local disaster assessment module is used for inputting the mining environment data and the miner state data into a local disaster risk assessment model to obtain a local disaster risk assessment result, and the result comprises disaster types, risk levels and disaster characteristics of different areas; and the global disaster assessment module is used for performing global disaster risk assessment based on each local disaster risk assessment result, the mine system data and the external environment data to obtain a global disaster risk assessment result. According to the system, local and global disaster risks are accurately evaluated by monitoring the mining environment and miner states in real time, the disaster occurrence risk can be reduced, and the life safety of miners is guaranteed.

Description

Technical Field

[0001] The invention belongs to the technical field of computers and communications, and in particular relates to a coal mine safety production management system for comprehensive disaster prevention and control. Background Art

[0002] Traditional coal mine safety management often relies on a single data source, such as gas concentration or geological exploration data, and conducts risk assessments through manual regular inspections and single-point monitoring. This cannot fully and real-timely reflect the complex and changeable environmental conditions and potential disaster risks in the mine. Summary of the invention

[0003] Based on this, it is necessary to address the above-mentioned technical problems. The purpose of the present invention is to provide an efficient and intelligent coal mine safety production management system to ensure the safe production of coal mines, reduce the possibility of disasters, protect the lives of miners and improve the overall safety management level of mines.

[0004] In a first aspect, the present application provides a coal mine safety production management system for comprehensive disaster prevention and control, the system comprising:

[0005] The regional division module is used to divide the mining area into multiple local assessment areas according to the geological structure and mining layout of the mine;

[0006] A data acquisition module is used to acquire mining environment data and miner status data based on a local assessment area. The mining environment data includes gas concentration, carbon monoxide concentration, temperature, humidity, roof pressure and water level. The miner status data includes miner behavior data and miner physiological data.

[0007] A local disaster assessment module is used to input mining environment data and miner status data into a local disaster risk assessment model to obtain a local disaster risk assessment result, which includes the disaster type, risk level and disaster characteristics corresponding to each local assessment area;

[0008] The global disaster assessment module is used to conduct a global disaster risk assessment based on the local disaster risk assessment results, mine system data and external environment data to obtain a global disaster risk assessment result. The global disaster risk assessment result includes the overall disaster risk status of the mine and the current disaster prevention and control priorities.

[0009] In one embodiment, the global disaster assessment module includes:

[0010] AHP subunits are used to:

[0011] Based on the analytic hierarchy process, a judgment matrix is ​​constructed by combining the local disaster risk assessment results, mine system data and external environment data;

[0012] According to the judgment matrix, the weights of the evaluation indicators are calculated based on the eigenvector method to obtain weighted evaluation indicators. The evaluation indicators include various disaster risk indicators in the local disaster risk assessment results, ventilation system stability indicators in the mine system data, rationality indicators of mining and excavation succession plans, drainage system capacity indicators, and meteorological impact indicators in the external environment data.

[0013] Fuzzy comprehensive analysis subunit, used for:

[0014] Based on the fuzzy comprehensive evaluation method, according to the weighted evaluation indicators, the evaluation factor set is obtained and the evaluation level set is determined;

[0015] Construct a fuzzy relationship matrix, which is used to reflect the degree to which each evaluation indicator belongs to each evaluation level;

[0016] Based on the weighted evaluation index and the fuzzy relationship matrix, a fuzzy synthesis operation is performed to obtain an evaluation fuzzy vector;

[0017] The evaluation fuzzy vector is calculated based on the maximum membership principle to obtain the global disaster risk assessment result.

[0018] In one embodiment, the system further includes a disaster spread assessment module, which is used to:

[0019] According to the physical connection and mutual influence degree between different local assessment areas, a regional connection matrix is ​​established;

[0020] Based on the propagation characteristics of different disaster types in different environments, determine the disaster propagation coefficient of each local assessment area;

[0021] Based on the results of the global disaster risk assessment, the disaster risk level and disaster characteristics of each local assessment area are obtained;

[0022] The disaster spread results are obtained based on the regional correlation matrix, disaster propagation coefficient, disaster risk level and disaster characteristics, and the disaster spread results include the disaster spread probability.

[0023] In one embodiment, the calculation formula for the probability of disaster spread is:

[0024]

[0025] Among them, P spread (i,j,t) represents the probability of disaster spreading from area i to area j at time t, λ is the attenuation factor of the propagation rate, which represents the reaction speed of disaster spread, A ij is the correlation between region i and region j, P k[i,j] is the propagation rate of disaster type k from region j to region i, R j(τ) represents the disaster risk value of region j at time τ.

[0026] In one embodiment, the region division module includes:

[0027] A data processing subunit, for:

[0028] Obtaining mine geological structure data and mining layout data. Mine geological structure data includes the mine's geological layers, vein distribution and fault structure. Mining layout data includes the location of each working face of the mine, mining methods and mining progress;

[0029] Extract features from the mine geological structure data and mining layout data to obtain feature vectors;

[0030] Cluster analysis subunit, used to:

[0031] Cluster analysis of feature vectors was performed based on the DBSCAN algorithm to obtain the preliminary clustering structure of different areas in the mining area;

[0032] Determine the number of clusters based on the preliminary cluster structure;

[0033] Based on the K-means algorithm, the preliminary clustering structure is optimized according to the number of clusters and eigenvectors to obtain multiple local evaluation areas.

[0034] In one embodiment, the system further includes a graded warning module for:

[0035] Based on the results of local disaster risk assessment and global disaster risk assessment, warning levels are set, including blue warning, yellow warning, orange warning and red warning;

[0036] Real-time monitoring of mining environment data and miner status data. When the mining environment data and miner status data meet the preset conditions, the warning level is adjusted to obtain an updated warning level.

[0037] According to the updated warning level, warning information is sent to managers at different levels through a multi-channel communication system.

[0038] In one embodiment, the local disaster risk assessment model is obtained by the following steps:

[0039] Construct a disaster risk assessment model based on the support vector machine algorithm;

[0040] The disaster risk assessment model is trained according to the historical working condition data of different local assessment areas, and the kernel function parameters and penalty coefficient of the disaster risk assessment model are adjusted through k-fold cross validation until the kernel function parameters and penalty coefficient meet the target conditions to obtain the local disaster risk assessment model.

[0041] In a second aspect, the present application also provides a coal mine safety production management method for comprehensive disaster prevention and control, the method comprising:

[0042] The mining area is divided into several local assessment areas according to the geological structure and mining layout of the mine;

[0043] Based on the local assessment area, obtain mining environment data and miner status data. The mining environment data includes gas concentration, carbon monoxide concentration, temperature, humidity, roof pressure and water level. The miner status data includes miner behavior data and miner physiological data.

[0044] Input mining environment data and miner status data into the local disaster risk assessment model to obtain local disaster risk assessment results, which include the disaster type, risk level and disaster characteristics corresponding to each local assessment area;

[0045] Based on the local disaster risk assessment results, mine system data and external environment data, a global disaster risk assessment is conducted to obtain a global disaster risk assessment result, which includes the overall disaster risk status of the mine and the current disaster prevention and control priorities.

[0046] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the coal mine safety production management system of the first aspect when executing the computer program.

[0047] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the coal mine safety production management system of the first aspect.

[0048] The above-mentioned coal mine safety production management system, method, computer equipment and storage medium for comprehensive disaster prevention and control divides the mining area into multiple local assessment areas according to the geological structure and mining layout of the mine through the regional division module, which helps to evaluate the disaster risk of each area in more detail. Based on these local assessment areas, the data acquisition module collects the mining environment data and miner status data in the mine in real time to provide sufficient data support for subsequent disaster assessment. And the local disaster assessment module conducts local disaster risk assessment on the mining environment data and miner status data to obtain the disaster type, risk level and disaster characteristics of each local assessment area. Through this process, the system can evaluate the potential disaster risk and its severity according to the specific conditions of different regions, and warn of potential safety hazards in advance.

[0049] Finally, the global disaster assessment module can conduct a global disaster risk assessment based on the local disaster risk assessment results, mine system data, and external environment data, and then obtain the overall disaster risk status of the mine and the current disaster prevention and control priorities. This module can comprehensively consider the risk factors of each area within the mine and the impact of the external environment on mine safety, formulate the best disaster prevention and control measures and resource allocation strategies, and ensure the accurate and efficient implementation of disaster prevention and control work.

[0050] Compared with traditional mine safety management systems, this system can more accurately identify and predict safety risks within mines through the collaborative work of regional division, data acquisition, local and global disaster assessment modules, identify potential disaster risks in advance, and dynamically adjust disaster prevention and control measures according to disaster types and risk levels, effectively improving the overall effectiveness of coal mine safety management and providing strong protection for mine production safety and the lives of miners. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 A schematic diagram of the structure of a coal mine safety production management system for comprehensive disaster prevention and control provided by an exemplary embodiment of the present invention;

[0053] Figure 2 A flow chart of a coal mine safety production management method for comprehensive disaster prevention and control is provided as an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] In one embodiment, Figure 1 As shown, a coal mine safety production management system 100 for comprehensive disaster prevention and control is provided. This embodiment takes the application of the system to a terminal as an example. It can be understood that the system can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the system includes the following structure:

[0056] The area division module 101 is used to divide the mining area into multiple local assessment areas according to the geological structure and mining layout of the mine.

[0057] Specifically, the geological structure and mining layout of the mine are key factors that affect the occurrence and spread of disasters. Geological structures such as faults, folds, coal seam inclination and rock properties will affect the storage of gas, the stability of the roof and the flow of groundwater. Different geological conditions may lead to different types of disasters and risks. The mining layout directly affects the working environment of the mine and the safety of miners. Different mining methods, mining progress and tunnel layout make the safety risks in different areas different. Schematically, the area division module 101 can scientifically divide the mining area into multiple local evaluation areas through a clustering algorithm or a graph segmentation algorithm, so that each area has relative consistency or correlation in geological and mining characteristics, so as to facilitate subsequent accurate data collection and disaster risk assessment for different areas.

[0058] The data acquisition module 102 is used to acquire mining environment data and miner status data based on the local assessment area. The mining environment data includes gas concentration, carbon monoxide concentration, temperature, humidity, roof pressure and water level. The miner status data includes miner behavior data and miner physiological data.

[0059] Specifically, by integrating a variety of sensor devices, such as gas detectors, temperature and humidity sensors, pressure sensors, heart rate monitors, location tracking systems, etc., the mining environment data of different local assessment areas can be obtained in real time. Miner status data can be collected through smart wearable devices worn by miners. Among them, miner physiological data can include information such as miners' movement trajectory, work status, labor intensity, etc. Miner physiological data can include physiological indicators such as heart rate, body temperature, and respiratory rate. In addition, the miner's behavioral data can be used to analyze whether the operation is in accordance with the operating procedures and whether there are any abnormal action patterns. The miner's physiological data can be used to analyze whether the miner's physical state is in a safe state, so as to issue early warnings in time, thereby avoiding accidents caused by improper operation or physical problems.

[0060] The local disaster assessment module 103 is used to input mining environment data and miner status data into the local disaster risk assessment model to obtain local disaster risk assessment results. The local disaster risk assessment results include the disaster type, risk level and disaster characteristics corresponding to each local assessment area.

[0061] Specifically, the local disaster risk assessment models of different regions in the above-mentioned local disaster assessment module 103 are not consistent. The local disaster risk assessment model is trained through the existing historical data and disaster laws of different regions. It can be evaluated through the mining environment data and miner status data obtained in the current local assessment area, and targetedly judge whether there is a potential risk of disaster in this area, and then obtain the local disaster risk assessment result. Among them, the types of mine disasters mainly include gas explosions, carbon monoxide poisoning, landslides, floods and fires, etc., and their corresponding risk levels can be divided into high risk, medium risk, and low risk, and it can also describe the characteristics of disasters such as the possible intensity of gas explosions, the scope of roof collapse, the spread trend of fire, etc., so as to provide scientific basis and guidance for disaster prevention and control in local assessment areas and improve the overall safety management level of mines.

[0062] The global disaster assessment module 104 is used to perform a global disaster risk assessment based on the local disaster risk assessment results, mine system data and external environment data to obtain a global disaster risk assessment result, which includes the overall disaster risk status of the mine and the current disaster prevention and control priority.

[0063] Since coal mine disasters are often holistic and related, local disasters may spread and spread, thereby affecting the safety of the entire mine. Therefore, the global disaster assessment module 104 can integrate the results of local disaster risk assessments to conduct a comprehensive disaster risk assessment. In addition, the global disaster assessment module 104 further analyzes the disaster situation faced by the entire mine in depth and comprehensively by combining the mine system data and the external environment data, so as to accurately determine the current disaster prevention and control priority and improve the coal mine safety production management level. Among them, the mine system data can include the air volume, wind pressure, and wind flow direction of the ventilation system, the excavation succession plan such as the advancement speed of the excavation working face, the excavation sequence, the connection arrangement of the excavation area, and the matching degree of resource reserves and mining progress, as well as drainage system data such as the drainage capacity of the drainage pump, the capacity of the water tank, the diameter and laying of the drainage pipe, and the real-time water level monitoring data. The external environment data can include meteorological data such as rainfall, temperature, and air pressure in the area where the mine is located, and surrounding geological environment data such as earthquake activity, landslides, and stratum subsidence in the surrounding area of ​​the mine.

[0064] The above-mentioned coal mine safety production management system divides the mining area into multiple local assessment areas according to the geological structure and mining layout of the mine through the regional division module 101, thereby ensuring that disaster risks can be independently assessed and managed for different areas; the mining environment data such as gas concentration, carbon monoxide concentration, temperature and humidity, etc., as well as miner behavior data and physiological data of different local assessment areas can be obtained through the data acquisition module 102. By collecting these data in real time, the system can fully grasp the environmental conditions in the mine and the physical condition of the miners; in the local disaster assessment module 103, the acquired real-time data can be input into the local disaster risk assessment model, so as to obtain the disaster type, risk level and disaster characteristics of each local assessment area. This assessment result helps to identify and analyze the potential disaster risks in the mine and provide a scientific basis for the implementation of local prevention and control measures.

[0065] In addition, the global disaster assessment module 104 can be used to conduct a global disaster risk assessment based on the local disaster risk assessment results, mine system data and external environment data, and then the overall disaster risk status of the mine and the current disaster prevention and control priority can be determined. Through this global risk assessment, the system can determine the priority areas and measures for prevention and control, further improving the efficiency and accuracy of disaster prevention and control work. Through the collaborative work of these four modules, the system can comprehensively monitor the safety status of coal mines, assess potential disaster risks in real time, and take effective prevention and control measures based on the risk assessment results of different regions and the whole world, so as to ensure the safety of coal mine production and the life safety of miners.

[0066] In an exemplary embodiment, the global disaster assessment module includes:

[0067] AHP subunits are used to:

[0068] Based on the analytic hierarchy process, a judgment matrix is ​​constructed by combining the local disaster risk assessment results, mine system data and external environment data;

[0069] According to the judgment matrix, the weights of the evaluation indicators are calculated based on the eigenvector method to obtain weighted evaluation indicators. The evaluation indicators include various disaster risk indicators in the local disaster risk assessment results, ventilation system stability indicators in the mine system data, rationality indicators of mining and excavation succession plans, drainage system capacity indicators, and meteorological impact indicators in the external environment data.

[0070] Fuzzy comprehensive analysis subunit, used for:

[0071] Based on the fuzzy comprehensive evaluation method, according to the weighted evaluation indicators, the evaluation factor set is obtained and the evaluation level set is determined;

[0072] Construct a fuzzy relationship matrix, which is used to reflect the degree to which each evaluation indicator belongs to each evaluation level;

[0073] Based on the weighted evaluation index and the fuzzy relationship matrix, a fuzzy synthesis operation is performed to obtain an evaluation fuzzy vector;

[0074] The evaluation fuzzy vector is calculated based on the maximum membership principle to obtain the global disaster risk assessment result.

[0075] Schematically, the analytic hierarchy process is a method that decomposes complex problems into multiple levels and conducts decision analysis by comparing the relative importance of various factors. In the above-mentioned analytic hierarchy process subunit, each indicator in the local disaster risk assessment results, mine system data and external environment data can be compared pairwise to construct a judgment matrix. Among them, the judgment matrix is ​​a comparison of the relative importance of different factors. For example, the stability of the mine ventilation system may be more important than the meteorological impact. In the judgment matrix, the value of the ventilation system stability will be greater than the value of the meteorological impact. Then the system can calculate the weight of each evaluation indicator based on the constructed judgment matrix using the eigenvector method. Specifically, the eigenvector method can obtain the weight of each evaluation indicator by solving the maximum eigenroot of the judgment matrix and its corresponding eigenvector, and normalizing the eigenvector, that is, obtaining a weighted evaluation indicator. The weighted evaluation indicator can reflect the importance of each indicator in the global disaster risk assessment.

[0076] In the fuzzy comprehensive analysis subunit, the fuzzy comprehensive analysis method is used to integrate the fuzzy information of multiple evaluation indicators to obtain a global evaluation result. Among them, the evaluation factor set is the set of weighted evaluation indicators of all participating evaluations, such as the above-mentioned various disaster risk indicators, ventilation system stability indicators, etc. At the same time, the weighted evaluation indicators can be divided into different levels such as high risk, medium risk, and low risk according to the actual situation to construct an evaluation level set. Subsequently, the relationship between each weighted evaluation indicator and each evaluation level can be quantified to construct a fuzzy relationship matrix. The fuzzy relationship matrix is ​​used to reflect the degree to which each weighted evaluation indicator belongs to each evaluation level. Schematically, the evaluation fuzzy vector can be obtained by performing matrix multiplication operation on the weighted evaluation indicator and the fuzzy relationship matrix. The evaluation fuzzy vector integrates the influence of various factors on the global disaster risk assessment. Finally, the evaluation fuzzy vector is quantitatively calculated based on the maximum membership principle, that is, the evaluation level corresponding to the element with the largest membership in the evaluation fuzzy vector is taken as the global disaster risk assessment result.

[0077] Through the collaborative work of the above-mentioned hierarchical analysis subunit and fuzzy comprehensive analysis subunit, the global disaster assessment module 104 can comprehensively consider various factors, conduct a comprehensive, objective and accurate assessment of the disaster risk of the entire mine, and derive the overall disaster risk status of the mine and the current disaster prevention and control priorities, providing a scientific basis for coal mine safety production management.

[0078] In an exemplary embodiment, the local disaster risk assessment model is obtained by the following steps:

[0079] Construct a disaster risk assessment model based on the support vector machine algorithm;

[0080] The disaster risk assessment model is trained according to the historical working condition data of different local assessment areas, and the kernel function parameters and penalty coefficient of the disaster risk assessment model are adjusted through k-fold cross validation until the kernel function parameters and penalty coefficient meet the target conditions to obtain the local disaster risk assessment model.

[0081] Specifically, support vector machine is a supervised learning method, which is widely used in classification and regression problems. In the above process, a disaster risk assessment model can be constructed for the local assessment area based on support vector machine to conduct disaster risk assessment, and the model can be trained through historical working condition data, so that the model can learn the intrinsic relationship between different data feature combinations and the occurrence and severity of actual disasters, so as to predict the disaster risk of mines. K-fold cross validation is a common method for evaluating model performance and adjusting model parameters, which can effectively prevent model overfitting. In the process of cross-validation of the disaster risk assessment model, by continuously trying different combinations of kernel function parameters and penalty coefficients, the performance index changes of the model on the validation set are observed. When the kernel function parameters and penalty coefficients meet the target conditions, a local disaster risk assessment model can be obtained. Exemplarily, this target condition can be that the model reaches the preset accuracy, F1 value and other performance index requirements on the validation set, or after multiple attempts, finds the parameter combination that makes the model performance optimal and stable.

[0082] In an exemplary embodiment, the system further includes a disaster spread assessment module 105, which is used to:

[0083] According to the physical connection and mutual influence degree between different local assessment areas, a regional connection matrix is ​​established;

[0084] Based on the propagation characteristics of different disaster types in different environments, determine the disaster propagation coefficient of each local assessment area;

[0085] Based on the results of the global disaster risk assessment, the disaster risk level and disaster characteristics of each local assessment area are obtained;

[0086] The disaster spread results are obtained based on the regional correlation matrix, disaster propagation coefficient, disaster risk level and disaster characteristics, and the disaster spread results include the disaster spread probability.

[0087] Specifically, there are various physical connections between different local assessment areas in the mine. For example, through the ventilation system, gas disasters such as gas and fire smoke can be transmitted between areas, or through underground water channels or rock cracks, water hazards may spread from one area to adjacent areas, and stress changes caused during the mining process may cause disasters such as roof collapse to affect each other between areas with certain mechanical connections. Therefore, it is necessary to assign an association value to each local assessment area according to the physical connection and mutual influence between different local assessment areas, so as to construct a regional association matrix. The regional association matrix is ​​used to represent the mutual connection and mutual influence between local assessment areas.

[0088] In addition, different types of disasters, such as gas outburst, roof collapse, water seepage, fire, etc., have different propagation characteristics under different environmental conditions. For example, for gas disasters, in open areas with good ventilation, gas may be diluted and diffused quickly, and the disaster propagation coefficient is relatively small; while in areas with poor ventilation, narrow lanes and more closed spaces, gas is easy to accumulate and the propagation speed may be accelerated, and the disaster propagation coefficient will be larger. The disaster propagation coefficients for different types of disasters in each local assessment area can be determined by analyzing historical disaster data, calculating theoretical models and verifying actual monitoring data, so as to accurately describe the difficulty and speed of disaster propagation in the area. And the disaster spread assessment module 105 can obtain the disaster risk level and corresponding detailed disaster characteristics of each local assessment area according to the global disaster risk assessment results. This information provides basic data for the subsequent accurate calculation of disaster spread. Based on the obtained regional correlation matrix, disaster propagation coefficient, disaster risk level and disaster characteristics, disaster simulation can be carried out by constructing a disaster propagation model, and then the probability of disaster spread can be accurately predicted through model output, which not only helps to improve the accuracy and efficiency of disaster management, but also provides strong data support and theoretical basis for disaster prevention and control decision-making.

[0089] In an exemplary embodiment, the calculation formula for the probability of disaster spread is:

[0090]

[0091] Among them, P spread (i,j,t) represents the probability of disaster spreading from area i to area j at time t, λ is the attenuation factor of the propagation rate, which represents the reaction speed of disaster spread, A ij is the correlation between region i and region j, P k[i,j]is the propagation rate of disaster type k from region j to region i, R j (τ) represents the disaster risk value of region j at time τ.

[0092] The above formula quantitatively calculates the probability of disaster spread between different regions over time by comprehensively considering the speed of disaster spread, the connection between regions, the propagation characteristics of specific disasters, and the cumulative disaster risk of the region, providing an important theoretical basis for disaster warning and prevention. j (τ) is integrated to reflect the sum of disaster risks in region j over a period of time. The higher the cumulative disaster risk, the greater the possibility that disasters will spread from region j to other regions.

[0093] In an exemplary embodiment, the region division module 101 includes:

[0094] A data processing subunit, for:

[0095] Obtaining mine geological structure data and mining layout data. Mine geological structure data includes the mine's geological layers, vein distribution and fault structure. Mining layout data includes the location of each working face of the mine, mining methods and mining progress;

[0096] Extract features from the mine geological structure data and mining layout data to obtain feature vectors;

[0097] Cluster analysis subunit, used to:

[0098] Cluster analysis of feature vectors was performed based on the DBSCAN algorithm to obtain the preliminary clustering structure of different areas in the mining area;

[0099] Determine the number of clusters based on the preliminary cluster structure;

[0100] Based on the K-means algorithm, the preliminary clustering structure is optimized according to the number of clusters and eigenvectors to obtain multiple local evaluation areas.

[0101] In coal mining, different strata have different characteristics such as lithology, hardness, stability and gas content, and these differences will have a significant impact on the disaster risk during the mining process. For example, soft strata may increase the risk of roof collapse, and the rock near the fault is broken, which is prone to roof accidents. In addition, in the process of coal mining, the location of each working face determines the spatial distribution of mining activities, and the working faces at different locations face different geological conditions and potential disaster risks. The mining methods used, such as longwall mining, shortwall mining, and fully mechanized mining, will also affect the stress distribution of the roof, the degree of coal seam crushing, and the law of gas outburst. Too fast or unreasonable mining progress may also lead to problems such as stress concentration and excessive goaf area, which in turn cause disasters such as roof collapse and rock burst. Therefore, it is necessary to divide the mine area to facilitate targeted disaster risk assessment.

[0102] In the data processing subunit, based on the acquired mine geological structure data and mining layout data, data preprocessing and feature selection can be used to extract features such as the thickness of the stratum, hardness coefficient, density of the vein, strike angle, the fall of the fault, and the degree of influence of the mining method on the roof and coal body, and these features are combined to form a feature vector that can fully reflect the characteristics of each region, providing a data basis for subsequent cluster analysis. Specifically, in the cluster analysis subunit, DBSCAN (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) is a density-based clustering algorithm that can preliminarily cluster the mine area according to the extracted feature vector and preliminarily identify different areas in the mining area, that is, the preliminary clustering structure. According to the clustering results of DBSCAN, the actual number of clusters can be estimated, that is, how many areas need to be optimized and evaluated. Subsequently, the preliminary clustering structure can be refined and optimized by the K-means algorithm to obtain a more accurate regional division, that is, multiple local evaluation areas. Each local assessment area has unique geological characteristics and mining conditions, which helps to carry out reasonable resource management, evaluation and decision-making during the mine mining process and optimize the efficiency and safety of mine mining.

[0103] In an exemplary embodiment, the system further includes a graded warning module 106, which is used to:

[0104] Based on the results of local disaster risk assessment and global disaster risk assessment, warning levels are set, including blue warning, yellow warning, orange warning and red warning;

[0105] Real-time monitoring of mining environment data and miner status data. When the mining environment data and miner status data meet the preset conditions, the warning level is adjusted to obtain an updated warning level.

[0106] According to the updated warning level, warning information is sent to managers at different levels through a multi-channel communication system.

[0107] Specifically, the local disaster risk assessment results focus on the possible disasters in each local assessment area, covering information such as disaster type, risk level and disaster characteristics; while the global disaster risk assessment results focus on the overall disaster risk status of the entire mine, the possibility of disaster spread between different regions, the current disaster prevention and control priorities, etc. By integrating these two aspects of information, the graded warning module 106 can grasp the risk level faced by the mine from different levels and scopes, and then reasonably set the corresponding warning level, for example, blue warning corresponds to lower risk, yellow warning indicates that the risk has increased, orange warning means higher risk, and red warning represents an extremely high disaster risk situation.

[0108] In addition, the hierarchical warning module 106 is also used to monitor the mining environment data and miner status data in real time. When these data meet these preset conditions, the set warning level can be dynamically adjusted to obtain an updated warning level, so as to more accurately reflect the real-time risk status faced by the current mine and take effective countermeasures in time. The preset conditions can be determined based on a large number of historical disaster cases, scientific research and safety production experience. For example, when the gas concentration in a local area exceeds a certain threshold and lasts for a period of time, and the miner behavior data in the area shows abnormal behaviors such as panic and disorderly gathering, it is necessary to increase the warning level. And with the help of multi-channel communication systems such as sound and light alarms, underground broadcasts and SMS notifications, it is ensured that the warning information can be accurately, timely and effectively conveyed to managers at different levels, so as to take effective prevention and control measures in time. This module monitors the mining environment and miner status data in real time, combines local and global disaster risk assessment results, and dynamically adjusts the warning level, which can ensure the safety of miners and reduce the losses of potential disasters, and provide scientific decision-making support for disaster prevention and emergency response.

[0109] Based on the same inventive concept, Figure 2 As shown, the embodiment of the present application also provides a coal mine safety production management method for comprehensive disaster prevention and control, the method comprising:

[0110] S201: Divide the mining area into several local assessment areas based on the geological structure and mining layout of the mine;

[0111] S202: Based on the local assessment area, mining environment data and miner status data are obtained, the mining environment data including gas concentration, carbon monoxide concentration, temperature, humidity, roof pressure and water level, and the miner status data including miner behavior data and miner physiological data;

[0112] S203: inputting the mining environment data and the miner status data into a local disaster risk assessment model to obtain a local disaster risk assessment result, wherein the local disaster risk assessment result includes the disaster type, risk level and disaster characteristics corresponding to each local assessment area;

[0113] S204: Based on the local disaster risk assessment results, mine system data and external environment data, a global disaster risk assessment is performed to obtain a global disaster risk assessment result, which includes the overall disaster risk status of the mine and the current disaster prevention and control priority.

[0114] In the above-mentioned coal mine safety production management method for comprehensive disaster prevention and control, the mine can first be divided into multiple local assessment areas according to the geological structure and mining layout of the mine. This step provides a basis for a comprehensive understanding of the safety situation in the mine, and can more accurately assess the disaster risk of different areas, so as to formulate appropriate disaster prevention and control measures. Based on each local assessment area, the system can obtain mining environment data and miner status data in real time through sensors, etc., and track and analyze the mine environment and miner status. These data provide an important basis for subsequent disaster risk assessments.

[0115] Secondly, the system can input mining environment data and miner status data into the local disaster risk assessment model to obtain the disaster risk assessment results of each local assessment area. The disaster risk assessment results not only include the types of disasters that may occur in different areas, but also clarify the risk level and disaster characteristics, which helps mine managers to have an in-depth understanding of the safety status of each area and provide scientific data support for the formulation of targeted preventive measures. Finally, based on the local disaster risk assessment results, mine system data and external environment data, the system can further conduct a global disaster risk assessment, and finally obtain the overall disaster risk status of the mine and the current disaster prevention and control priority and other global disaster risk assessment results. This result can help mine managers fully understand the overall safety of the mine, and determine the optimal disaster prevention and control strategy based on the assessment results to ensure the safety of mine production and the lives of miners.

[0116] Compared with traditional disaster prevention and control methods, the above method can not only monitor the safety status of the mine in real time through multi-dimensional data collection and comprehensive analysis, but also reasonably allocate resources through global assessment results to ensure accurate and efficient disaster prevention and control. In addition, this method significantly improves the scientificity and systematicity of coal mine disaster risk prevention and control by combining the dual guarantees of local and global assessments, providing a more intelligent management method for mine safety production.

[0117] Furthermore, based on the geological structure and mining layout of the mine, the mining area is divided into several local assessment areas, including:

[0118] Obtaining mine geological structure data and mining layout data. Mine geological structure data includes the mine's geological layers, vein distribution and fault structure. Mining layout data includes the location of each working face of the mine, mining methods and mining progress;

[0119] Extract features from the mine geological structure data and mining layout data to obtain feature vectors;

[0120] Cluster analysis of feature vectors was performed based on the DBSCAN algorithm to obtain the preliminary clustering structure of different areas in the mining area;

[0121] Determine the number of clusters based on the preliminary cluster structure;

[0122] Based on the K-means algorithm, the preliminary clustering structure is optimized according to the number of clusters and eigenvectors to obtain multiple local evaluation areas.

[0123] Furthermore, the local disaster risk assessment model is obtained through the following steps:

[0124] Construct a disaster risk assessment model based on the support vector machine algorithm;

[0125] The disaster risk assessment model is trained according to the historical working condition data of different local assessment areas, and the kernel function parameters and penalty coefficient of the disaster risk assessment model are adjusted through k-fold cross validation until the kernel function parameters and penalty coefficient meet the target conditions to obtain the local disaster risk assessment model.

[0126] Furthermore, based on the local disaster risk assessment results, mine system data and external environment data, a global disaster risk assessment is conducted, including:

[0127] Based on the analytic hierarchy process, a judgment matrix is ​​constructed by combining the local disaster risk assessment results, mine system data and external environment data;

[0128] According to the judgment matrix, the weights of the evaluation indicators are calculated based on the eigenvector method to obtain weighted evaluation indicators. The evaluation indicators include various disaster risk indicators in the local disaster risk assessment results, ventilation system stability indicators in the mine system data, rationality indicators of mining and excavation succession plans, drainage system capacity indicators, and meteorological impact indicators in the external environment data.

[0129] Based on the fuzzy comprehensive evaluation method, according to the weighted evaluation indicators, the evaluation factor set is obtained and the evaluation level set is determined;

[0130] Construct a fuzzy relationship matrix, which is used to reflect the degree to which each evaluation indicator belongs to each evaluation level;

[0131] Based on the weighted evaluation index and the fuzzy relationship matrix, a fuzzy synthesis operation is performed to obtain an evaluation fuzzy vector;

[0132] The evaluation fuzzy vector is calculated based on the maximum membership principle to obtain the global disaster risk assessment result.

[0133] Furthermore, the method also includes:

[0134] According to the physical connection and mutual influence degree between different local assessment areas, a regional connection matrix is ​​established;

[0135] Based on the propagation characteristics of different disaster types in different environments, determine the disaster propagation coefficient of each local assessment area;

[0136] Based on the results of the global disaster risk assessment, the disaster risk level and disaster characteristics of each local assessment area are obtained;

[0137] The disaster spread results are obtained based on the regional correlation matrix, disaster propagation coefficient, disaster risk level and disaster characteristics, and the disaster spread results include the disaster spread probability.

[0138] Indicatively, the calculation formula for the probability of disaster spread is:

[0139]

[0140] Among them, P spread (i,j,t) represents the probability of disaster spreading from area i to area j at time t, λ is the attenuation factor of the propagation rate, which represents the reaction speed of disaster spread, A ij is the correlation between region i and region j, P k[i,j] is the propagation rate of disaster type k from region j to region i, R j (τ) represents the disaster risk value of region j at time τ.

[0141] Furthermore, the method also includes:

[0142] Based on the results of local disaster risk assessment and global disaster risk assessment, warning levels are set, including blue warning, yellow warning, orange warning and red warning;

[0143] Real-time monitoring of mining environment data and miner status data. When the mining environment data and miner status data meet the preset conditions, the warning level is adjusted to obtain an updated warning level.

[0144] According to the updated warning level, warning information is sent to managers at different levels through a multi-channel communication system.

[0145] In an exemplary embodiment, the present invention further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a coal mine safety production management system for comprehensive disaster prevention and control of the present application are implemented. A multi-core processor is preferably used to improve the parallel processing capability of the system. Memory: Provides sufficient temporary storage space to support the operation of the program and the processing of data. The memory capacity should be large enough to accommodate a large amount of supply information and computing tasks.

[0146] In one embodiment, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of a coal mine safety production management system for comprehensive disaster prevention and control in the present application are implemented. The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a solid-state drive (SSD), or an optical disk, etc. Among them, the random access memory may include a resistive random access memory (ReRAM) and a dynamic random access memory (DRAM).

[0147] The above-mentioned embodiments only express several implementation methods of the embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the embodiments of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the embodiments of the present application, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A coal mine safety production management system for comprehensive disaster prevention and control, characterized in that: The system comprises: The regional division module is used to divide the mining area into multiple local assessment areas according to the geological structure and mining layout of the mine; A data acquisition module, for acquiring mining environment data and miner status data based on the local assessment area, wherein the mining environment data includes gas concentration, carbon monoxide concentration, temperature, humidity, roof pressure and water level, and the miner status data includes miner behavior data and miner physiological data; A local disaster assessment module, used for inputting the mining environment data and the miner status data into a local disaster risk assessment model to obtain a local disaster risk assessment result, wherein the local disaster risk assessment result includes the disaster type, risk level and disaster characteristics corresponding to each local assessment area; The global disaster assessment module is used to conduct a global disaster risk assessment based on the local disaster risk assessment results, mine system data and external environment data to obtain a global disaster risk assessment result, which includes the overall disaster risk status of the mine and the current disaster prevention and control priority.

2. The coal mine production safety management system according to claim 1, characterized in that: The global disaster assessment module includes: AHP subunits are used to: Based on the analytic hierarchy process, a judgment matrix is ​​constructed by combining the local disaster risk assessment results, the mine system data and the external environment data; According to the judgment matrix, the weights of the evaluation indicators are calculated based on the eigenvector method to obtain weighted evaluation indicators, wherein the evaluation indicators include various disaster risk indicators in the local disaster risk assessment results, ventilation system stability indicators in the mine system data, rationality indicators of mining and excavation succession plans, drainage system capacity indicators, and meteorological impact indicators in the external environment data; Fuzzy comprehensive analysis subunit, used for: Based on the fuzzy comprehensive evaluation method, according to the weighted evaluation index, an evaluation factor set is obtained and a set evaluation level set is determined; Constructing a fuzzy relationship matrix, wherein the fuzzy relationship matrix is ​​used to reflect the degree to which each of the evaluation indicators belongs to each evaluation level; Performing a fuzzy synthesis operation based on the weighted evaluation index and the fuzzy relationship matrix to obtain an evaluation fuzzy vector; The evaluation fuzzy vector is calculated based on the maximum membership principle to obtain the global disaster risk assessment result.

3. The coal mine production safety management system according to claim 1, characterized in that: The system further comprises a disaster spread assessment module, which is used to: Establishing a regional correlation matrix according to the physical correlation and mutual influence degree between different local assessment areas; Determining the disaster propagation coefficient of each local assessment area based on the propagation characteristics of different disaster types in different environments; According to the global disaster risk assessment result, obtaining the disaster risk level and the disaster characteristics of each local assessment area; A calculation is performed based on the regional association matrix, the disaster propagation coefficient, the disaster risk level and the disaster characteristics to obtain a disaster propagation result, wherein the disaster propagation result includes a disaster propagation probability.

4. The coal mine production safety management system according to claim 3, characterized in that: The calculation formula for the probability of disaster spread is: Among them, P spread (i,j,t) represents the probability of disaster spreading from area i to area j at time t, λ is the attenuation factor of the propagation rate, which represents the reaction speed of disaster spread, A ij is the correlation between region i and region j, P k[i,j] is the propagation rate of disaster type k from region j to region i, R j (τ) represents the disaster risk value of region j at time τ.

5. The coal mine production safety management system according to claim 1, characterized in that: The area division module comprises: A data processing subunit, for: Acquire the geological structure data and mining layout data of the mine, wherein the geological structure data of the mine includes the geological layers, vein distribution and fault structure of the mine, and the mining layout data includes the location, mining method and mining progress of each working face of the mine; Extracting features from the mine geological structure data and the mining layout data to obtain feature vectors; Cluster analysis subunit, used to: Performing cluster analysis on the feature vectors based on the DBSCAN algorithm to obtain a preliminary clustering structure of different areas in the mining area; Determining the number of clusters according to the preliminary cluster structure; Based on the K-means algorithm, the preliminary clustering structure is optimized according to the number of clusters and the feature vector to obtain a plurality of local evaluation areas.

6. The coal mine production safety management system according to claim 1, characterized in that: It also includes a hierarchical warning module for: Based on the local disaster risk assessment results and the global disaster risk assessment results, setting warning levels, the warning levels include blue warning, yellow warning, orange warning and red warning; The mining environment data and the miner status data are monitored in real time, and when the mining environment data and the miner status data meet preset conditions, the warning level is adjusted to obtain an updated warning level; According to the updated warning level, warning information is sent to managers at different levels through a multi-channel communication system.

7. The coal mine production safety management system according to claim 1, characterized in that: The local disaster risk assessment model is obtained through the following steps: Construct a disaster risk assessment model based on the support vector machine algorithm; The disaster risk assessment model is trained according to the historical operating data of different local assessment areas, and the kernel function parameters and penalty coefficient of the disaster risk assessment model are adjusted through k-fold cross validation until the kernel function parameters and the penalty coefficient meet the target conditions, thereby obtaining the local disaster risk assessment model.

8. A coal mine safety production management method for comprehensive disaster prevention and control, characterized in that: The method comprises: The mining area is divided into several local assessment areas according to the geological structure and mining layout of the mine; Based on the local assessment area, mining environment data and miner status data are obtained, wherein the mining environment data includes gas concentration, carbon monoxide concentration, temperature, humidity, roof pressure and water level, and the miner status data includes miner behavior data and miner physiological data; Inputting the mining environment data and the miner status data into a local disaster risk assessment model to obtain a local disaster risk assessment result, wherein the local disaster risk assessment result includes the disaster type, risk level and disaster characteristics corresponding to each local assessment area; Based on the local disaster risk assessment results, mine system data and external environment data, a global disaster risk assessment is performed to obtain a global disaster risk assessment result, which includes the overall disaster risk status of the mine and the current disaster prevention and control priorities.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the coal mine safety production management system described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the coal mine safety production management system described in any one of claims 1 to 7 are implemented.

Images