Coal mine underground safety comprehensive management method and system

Abstract

The invention relates to a coal mine underground safety comprehensive management method, system and device and a medium. The method comprises the following steps: establishing a coal mine underground risk factor set and a corresponding risk assessment index set; acquiring monitoring data of each element in the risk assessment index set to form a risk assessment index monitoring data set; based on a hierarchy analysis method and a fuzzy comprehensive evaluation method, first and second overall risk evaluation results are obtained according to the monitoring data set, and then the first and second overall risk evaluation results are synthesized to obtain a comprehensive risk evaluation result; and finally generating a response strategy according to the comprehensive risk evaluation result. Therefore, comprehensive and scientific assessment of the safety condition of the underground coal mine is realized, targeted prevention measure guidance is provided for managers, the safety management level of the underground coal mine is effectively improved, and the possibility of safety accidents is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of coal mine safety management, and particularly relates to a comprehensive underground coal mine safety management method and system. Background Art

[0002] As an important way to obtain energy, coal mining has long faced a severe safety situation in underground operations. Disasters such as gas outbursts, water inrush accidents, roof collapses, and dust explosions occur frequently, causing huge losses to miners' lives and enterprise property, highlighting the crucial position and arduousness of safety management.

[0003] Some existing safety management technologies are relatively weak in data processing and analysis capabilities. Although various monitoring devices are installed in some coal mines, the data generated by these devices are mostly in a scattered state, without forming an organic whole, lacking an integration and in-depth analysis mechanism, and unable to comprehensively reflect the underground safety situation.

[0004] In addition, with the deepening of coal mining and the increasing complexity of mining technologies, new safety challenges such as roadway deformation caused by deep ground pressure changes and abnormal gas outbursts under complex geological conditions continuously emerge, and traditional management technologies are difficult to cope with these dynamically changing risk factors. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a comprehensive underground coal mine safety management method, system, computer device, and its storage medium that can comprehensively, accurately, and dynamically evaluate the safety risks of underground coal mines and generate response strategies.

[0006] In the first aspect, the present application provides a comprehensive underground coal mine safety management method, including:

[0007] Establish a set of risk factors F = {F 1 , F 2 ,..., F n} and the corresponding set of risk assessment indicators wherein the set of risk assessment indicators corresponding to the risk factor F i is n is the number of elements in the set of risk factors F, m i is the number of risk assessment indicators corresponding to the risk factor F i , and i = 1, 2,..., n;

[0008] Obtain the monitoring data of each element in the set of risk assessment indicators i corresponding to each risk factor F to obtain the set of risk assessment indicator monitoring data i corresponding to each risk factor F Thus, the set of risk factors F = {F1 , F 2 ,..., F n} corresponding risk assessment index monitoring data set

[0009] Based on the analytic hierarchy process, according to the risk assessment index monitoring data set X, the first overall risk evaluation result is obtained;

[0010] Based on the fuzzy comprehensive evaluation method, according to the risk assessment index monitoring data set X, the second overall risk evaluation result is obtained;

[0011] According to the first overall risk evaluation result and the second overall risk evaluation result, the comprehensive risk evaluation result is obtained;

[0012] According to the comprehensive risk evaluation result, a response strategy is obtained; the response strategy is used to instruct the coal mine shaft management personnel to implement preventive measures corresponding to the comprehensive risk evaluation result.

[0013] On the second aspect, the present application also provides a comprehensive underground coal mine safety management system, including:

[0014] A risk evaluation system establishment module, used to establish a set of coal mine underground risk factors F = {F 1 , F 2 ,..., F n} and the corresponding risk assessment index set Among them, the risk factor F i The corresponding risk assessment index set is n is the number of elements in the risk factor set F, and m i Is the number of risk assessment indexes corresponding to the risk factor F i , i = 1, 2,..., n;

[0015] A data acquisition module, used to obtain the monitoring data of each element in the corresponding risk assessment index set i Of each risk factor F To obtain the risk assessment index monitoring data set corresponding to each risk factor F i} corresponding risk assessment index monitoring data set Thus, the risk factor set F = {F 1 , F 2 ,..., F n} corresponding risk assessment index monitoring data set

[0016] An analytic hierarchy process module, used to obtain the first overall risk evaluation result based on the analytic hierarchy process and according to the risk assessment index monitoring data set X;

[0017] The fuzzy comprehensive evaluation module is used to obtain the second overall risk evaluation result based on the fuzzy comprehensive evaluation method and according to the monitoring data set X of the risk assessment indicators.

[0018] The comprehensive risk evaluation module is used to obtain the comprehensive risk evaluation result according to the first overall risk evaluation result and the second overall risk evaluation result.

[0019] The response strategy generation module is used to obtain the response strategy according to the comprehensive risk evaluation result; the response strategy is used to instruct the coal mine well managers to implement preventive measures corresponding to the comprehensive risk evaluation result.

[0020] In a third aspect, the present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a comprehensive safety management method for coal mine underground as described in the first aspect.

[0021] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a comprehensive safety management method for coal mine underground as described in the first aspect.

[0022] The above-mentioned comprehensive safety management method, system, computer device and storage medium for coal mine underground establish a set of risk factors and their corresponding risk assessment indicators for coal mine underground; obtain the monitoring data of each element in the risk assessment indicator set to form a monitoring data set of risk assessment indicators; respectively obtain the first and second overall risk evaluation results based on the analytic hierarchy process and the fuzzy comprehensive evaluation method according to the monitoring data set, and then synthesize the two to obtain the comprehensive risk evaluation result; finally, generate a response strategy according to the comprehensive risk evaluation result. Thereby realizing a comprehensive and scientific assessment of the safety status of coal mine underground, providing targeted preventive measure guidance for managers, effectively improving the safety management level of coal mine underground, and reducing the possibility of safety accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0024] Figure 1 It is a schematic flow chart of a comprehensive safety management method for coal mine underground provided by the present invention;

[0025] Figure 2Schematic diagram of the structure of a comprehensive underground coal mine safety management system provided by the present invention. Detailed implementation manners

[0026] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to 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.

[0027] Referring to Figure 1 , which shows a flowchart of a comprehensive underground coal mine safety management method provided by the present application. The method includes the following steps:

[0028] S101. Establish a set of risk factors F = {F 1 , F 2 ,..., F n} and the corresponding set of risk assessment indicators Among them, the set of risk assessment indicators corresponding to the risk factor F i is n is the number of elements in the set of risk factors F, and m i is the number of risk assessment indicators corresponding to the risk factor F i , and i = 1, 2,..., n.

[0029] Specifically, in the complex environment of underground coal mines, there are many factors that may affect safe production. These factors are sorted and classified to determine the set of risk factors F = {F 1 , F 2 ,..., F n}.

[0030] For example, F 1 can represent the risk factor of gas concentration, and F 2 can represent the risk factor of roof stability, etc. For each risk factor F i , there is a corresponding set of risk assessment indicators Taking the risk factor F 1 of gas concentration as an example, its assessment indicators may include gas emission rate (I 11 ), gas concentration change rate (I 12 ), etc. Here, m 1 represents the number of assessment indicators corresponding to the risk factor of gas concentration.

[0031] In this way, all types of risks and their specific assessment dimensions in underground coal mines are comprehensively covered, establishing an assessment system for subsequent risk assessment.

[0032] S102. Obtain each risk factor F iThe corresponding set of risk assessment indicators For the monitoring data of each element within, each risk factor F is obtained i The corresponding set of monitoring data of risk assessment indicators Thus, the set of risk factors F = {F 1 , F 2 ,..., F n} corresponding to the set of monitoring data of risk assessment indicators

[0033] Specifically, for each risk factor F i The corresponding set of risk assessment indicators The corresponding monitoring data can be obtained through various sensors and monitoring devices installed underground in the coal mine

[0034] For example, for the gas emission volume (I 11 ), the data is continuously monitored and recorded by a gas sensor; for the roof displacement (assuming it is an evaluation indicator I 2 of the roof stability risk factor F 21 ), a displacement sensor is used for monitoring

[0035] By collecting these monitoring data, the set of monitoring data of risk assessment indicators corresponding to each risk factor F i is obtained

[0036] Finally, the set of monitoring data of risk assessment indicators corresponding to the entire set of risk factors F is formed

[0037] S103. Based on the analytic hierarchy process, according to the set of monitoring data of risk assessment indicators X, the first overall risk evaluation result is obtained

[0038] Specifically, the analytic hierarchy process (AHP) is a method that decomposes complex problems into multiple levels and factors and determines the relative importance weights of each factor through pairwise comparisons. First, construct a hierarchical structure model for the risk assessment in the underground coal mine, set the target layer as the overall risk assessment in the underground coal mine, the criterion layer as each risk factor F i , and the index layer as the risk assessment indicators I corresponding to each risk factor ij . Then, pairwise comparisons of the factors at each level can be made according to the experience of experts in the field of coal mine safety to construct a judgment matrix. For example, for risk factors F 1 and F 2, experts judge their relative importance to the overall risk based on experience and expertise, forming the elements in the judgment matrix. By calculating the eigenvector and the maximum eigenvalue of the judgment matrix and conducting a consistency test, the rationality of the judgment is ensured. Finally, based on the weights of each risk factor and its evaluation indicators and combined with the data in the monitoring data set X, weighted calculation is performed to obtain the first overall risk evaluation result. This result reflects the comprehensive assessment of the risks underground in coal mines based on the analytic hierarchy process.

[0039] S104. Based on the fuzzy comprehensive evaluation method and according to the monitoring data set X of risk assessment indicators, the second overall risk evaluation result is obtained.

[0040] Specifically, the fuzzy comprehensive evaluation method is applicable to dealing with problems with fuzziness and uncertainty and also plays an important role in the risk assessment of underground coal mines. First, determine the factor set of risk evaluation, that is, the risk factor set F = {F 1 , F 2 ,..., F n}, and the corresponding evaluation set, which can be set as different levels such as low risk, medium risk, high risk, etc. Then, based on expert experience or historical data, establish the fuzzy relationship matrix R between each risk factor F i and the evaluation set. For example, for the risk factor F 1 , determine its membership degrees belonging to different levels such as low risk, medium risk, high risk, etc. according to its monitoring data , forming a row of the fuzzy relationship matrix R. Next, determine the weight vector of each risk factor, which can be obtained through the previous analytic hierarchy process or other methods. Finally, perform a fuzzy composition operation on the weight vector and the fuzzy relationship matrix to obtain the second overall risk evaluation result. This result comprehensively evaluates the risks underground in coal mines from a fuzzy perspective.

[0041] S105. Obtain the comprehensive risk evaluation result based on the first overall risk evaluation result and the second overall risk evaluation result.

[0042] Specifically, since the first overall risk evaluation result and the second overall risk evaluation result evaluate the risks underground in coal mines from different methods and perspectives, in order to more comprehensively and accurately reflect the actual risk situation, the two can be combined. Methods such as the weighted average method and the analytic hierarchy process can be used to fuse these two results to obtain the final comprehensive risk evaluation result. This result combines the advantages of the two methods and can more accurately describe the risk status underground in coal mines.

[0043] S106. Obtain the response strategy according to the comprehensive risk evaluation result; the response strategy is used to instruct the coal mine managers to implement preventive measures corresponding to the comprehensive risk evaluation result.

[0044] Specifically, according to the obtained comprehensive risk assessment results, corresponding response strategies are formulated. If the comprehensive risk assessment result is at a low risk level, the response strategies may include continuing to maintain the existing safety monitoring and management measures, regularly performing equipment maintenance and inspections, etc.; if it is at a medium risk level, it may be necessary to increase the monitoring frequency of certain key risk factors, organize relevant personnel for risk investigation and potential hazard control training, etc.; if it is at a high risk level, immediate emergency measures need to be taken, such as stopping some operating areas, evacuating relevant personnel, organizing experts for on-site assessment and formulating special control plans, etc. In this way, the management personnel in the coal mine shaft can take targeted preventive measures according to different risk situations, effectively ensuring the safe production in the coal mine shaft.

[0045] The above-mentioned comprehensive safety management method for coal mine shafts includes establishing a set of risk factors in the coal mine shaft and its corresponding set of risk assessment indicators; obtaining the monitoring data of each element in the set of risk assessment indicators to form a set of risk assessment indicator monitoring data; respectively based on the analytic hierarchy process and the fuzzy comprehensive evaluation method, obtaining the first and second overall risk assessment results according to the set of monitoring data, and then synthesizing the two to obtain the comprehensive risk assessment result; finally generating a response strategy according to the comprehensive risk assessment result. Thereby achieving a comprehensive and scientific assessment of the safety status in the coal mine shaft, providing targeted preventive measure guidance for management personnel, effectively improving the safety management level in the coal mine shaft, and reducing the possibility of safety accidents.

[0046] In an optional embodiment, based on the analytic hierarchy process, according to the set of risk assessment indicator monitoring data X, obtaining the risk factor risk assessment result and the first overall risk assessment result includes the following steps:

[0047] S1: According to the set of risk factors F and the set of risk assessment indicators I, establish a hierarchical structure model, and the hierarchical structure model includes an objective layer, a criterion layer, and an index layer;

[0048] Among them, the objective layer corresponds to the overall safety risk in the coal mine shaft; there are n criteria in the criterion layer, and the i-th criterion corresponds to the risk factor F i ; the index layer has m i indicators for the i-th criterion, and the set of indicators corresponding to the i-th criterion in the index layer is

[0049] S2: Based on the historical accident data and the geological structure data in the coal mine shaft, obtain the importance degree of each element in the set of risk factors F to the overall safety in the coal mine shaft and the importance degree of each element in the corresponding set of risk assessment indicators i of the risk factor F to the risk factor F i ;

[0050] S3: In the criterion layer, based on the importance of each element in the risk factor set F to the overall safety of the underground coal mine, pairwise comparison of each element in the risk factor set F is carried out to obtain the risk factor comparison result; based on the risk factor comparison result, the judgment matrix A is obtained;

[0051] where A is an n×n matrix, and the elements of A are a ij , where i and j respectively represent the serial numbers of different risk factors in the criterion layer, and a ij represents the importance of F i relative to F j , a ij > 0, and a ii = 1;

[0052] S4: In the index layer, for each criterion i, based on the importance of each element in the index set to the risk factor F i , pairwise comparison of each element in the index set is carried out to obtain the index comparison result; based on the index comparison result, the judgment matrix B is obtained;

[0053] where A i is an m i ×m i matrix, and the elements of A i are where h and k respectively represent the serial numbers of different risk factor indicators in criterion i, represents the importance of I ik relative to I ih , and

[0054] S5: Calculate the maximum eigenvalue λ of the judgment matrix A in the criterion layer and the corresponding eigenvector ω = (ω 1 , ω 2 ,..., ω n ); normalize the eigenvector ω to obtain the weight vector ω′ = (ω′ 1 , ω′ 2 ,..., ω′ n );

[0055] where ω i represents the importance of the risk factor F i to the overall safety of the underground coal mine; ω′ i is the influence weight of the risk factor F i on the overall safety of the underground coal mine;

[0056] S6: For the index layer, calculate the judgment matrix A corresponding to each criterion i i for the maximum eigenvalue λ i and the corresponding eigenvector Normalize the eigenvector to obtain the weight vector

[0057] where represents the risk assessment index I ik for the risk factor F i influence importance; is the risk assessment index I ik for the risk factor F i influence weight;

[0058] S7: Judge whether the judgment matrix A and the judgment matrix A i have acceptable consistency, including:

[0059] Calculate the consistency index of the criterion layer and the consistency index of the index layer for each criterion i

[0060] If , confirm that the judgment matrix A has acceptable consistency; if , confirm that the judgment matrix A i has acceptable consistency; where RI is the preset random consistency index of the n-order matrix, and RI i is the preset random consistency index of the m i order matrix;

[0061] S8: When it is confirmed that both the judgment matrix A and the judgment matrix A i have acceptable consistency, at the index layer, calculate the risk score R of each risk factor F i according to the following formula i :

[0062]

[0063] where is the preset monitoring data threshold of the risk assessment index I ik ;

[0064] At the criterion layer, calculate the overall risk score M of the underground coal mine according to the following formula:

[0065]

[0066] S9: Take the overall risk score M as the first overall risk evaluation result.

[0067] Specifically, for step S1:

[0068] The safety risks in underground coal mines are a complex system. To clearly analyze the relationships between various factors, a hierarchical structure model is constructed. The goal layer is clearly defined as the overall safety risk in underground coal mines, which is the object we ultimately want to evaluate. The criterion layer consists of n risk factors F in the risk factor set F i . Each risk factor represents an important aspect affecting the safety of underground coal mines, such as gas risk, water hazard risk, roof risk, etc. The index layer is further refined. For each criterion (risk factor F i ), there are m i specific risk assessment indicators I ik . Taking the gas risk factor as an example, its index layer may include indicators such as gas concentration, gas emission volume, gas emission rate, etc. Through such a hierarchical structure, the complex safety risk problem in underground coal mines is decomposed into an ordered hierarchical system.

[0069] For step S2:

[0070] To accurately evaluate the relative importance of each risk factor and its indicators, historical accident data and geological structure data of underground coal mines can be used. Historical accident data records various safety accidents that have occurred in the past. By analyzing information such as the occurrence frequency of different risk factors, the severity of accidents, and the correlation with each risk factor in these accidents, the importance degree of each element in the risk factor set F to the overall safety of underground coal mines can be inferred. For example, if gas explosion accidents occurred frequently and caused huge losses in the past, then the importance degree of the gas risk factor in the overall safety is relatively high. At the same time, combined with the geological structure data of underground coal mines, such as the occurrence conditions of coal seams and the complexity of geological structures, analyze the influence of these factors on each risk assessment indicator. For the gas risk factor, in areas with complex geological structures, gas is more likely to accumulate, making indicators such as gas emission volume and gas concentration changes more critical to the gas risk. By comprehensively analyzing these data, determine the importance degree of each element in the risk assessment indicator set corresponding to the risk factor F i to the risk factor F i .

[0071] For step S3:

[0072] In the criterion layer, to quantify the relative importance between various risk factors, pairwise comparisons are required. Experts in the field of coal mine safety, experienced technical personnel, etc. can be invited to make pairwise comparisons of each element in the risk factor set F according to their professional knowledge and practical experience. For example, for the gas risk factor F 1 and the water hazard risk factor F 2, experts can compare in terms of the likelihood of these two risks occurring underground in this coal mine, the degree of harm that may be caused if they occur, etc., and determine F 1 Relative to F 2 The importance of, denoted as a 12 . In this way, the judgment matrix A is constructed, which is an n×n matrix. Among them, the element a ij Indicates F i Relative to F j The importance of, and satisfies a ij > 0, This reflects the relativity and symmetry of the comparison. At the same time, a ii = 1, indicating that the importance of comparing oneself with oneself is 1.

[0073] For step S4:

[0074] For each criterion (risk factor F i ), a similar pairwise comparison operation also needs to be carried out at the index layer. Based on the influence importance degree of each element in the previously determined index set on the risk factor F i , relevant professionals can conduct pairwise comparisons of each element in the index set. For example, for the gas concentration index I 1 and the gas emission index I 11 of the gas risk factor F 12 , compare them according to their importance in reflecting gas risk, and determine I 11 Relative to I 12 The importance of, denoted as And so on, construct the judgment matrix A i for each criterion i, which is an m i ×m i matrix. Among them, the element Indicates I ik Relative to I ih The importance of, also satisfies And

[0075] For step S5:

[0076] For the judgment matrix A of the criterion layer, by calculating its maximum eigenvalue λ and the corresponding eigenvector ω = (ω 1 , ω 2 ,..., ω n ) to determine the importance ranking of each risk factor. The method of calculating the eigenvector can adopt numerical calculation methods such as the power method and the sum method. After obtaining the eigenvector, in order to make it satisfy the definition of weight, that is, the sum of each weight is 1, it is necessary to normalize the eigenvector ω. Through the formula The calculated weight vector ω′ = (ω′ 1 , ω′ 2 ,..., ω′ n ). Among them, ω i represents the importance degree of the risk factor F i to the overall safety of the coal mine underground, while ω′ i is the influence weight of the risk factor F i on the overall safety of the coal mine underground, and

[0077] For step S6:

[0078] For the index layer, for the judgment matrix A of each criterion i i , calculate its maximum eigenvalue λ i and the corresponding eigenvector Then, adopt a normalization processing method similar to that of the criterion layer to process the eigenvector . Through the formula , calculate the weight vector Among them, represents the importance degree of the risk assessment index I ik to the risk factor F i , is the influence weight of the risk assessment index I ik on the risk factor F i , and

[0079] For step S7:

[0080] To ensure the rationality and reliability of the judgment matrix, consistency check is required. Calculate the consistency index of the criterion layer and the consistency index of the index layer for each criterion i. The consistency index here reflects the degree of inconsistency of the judgment matrix. Then, compare the calculated consistency index with the preset random consistency index. For the criterion layer, if , confirm that the judgment matrix A has acceptable consistency; for the index layer, if , confirm that the judgment matrix A i has acceptable consistency. Among them, RI is the preset random consistency index of the n-order matrix, and RI i is the preset random consistency index of the m i -order matrix. These random consistency indexes can be reference values obtained based on experimental data and experience summary, and are used to measure whether the consistency of the judgment matrix is within a reasonable range.

[0081] For step S8:

[0082] When it is confirmed that both the judgment matrix A and the judgment matrix A i have acceptable consistency, calculate the risk score R i of each risk factor F i at the index layer. Use the formula where is the preset monitoring data threshold of the risk assessment index I ik . The meaning of this formula is that first, calculate the relative deviation of the actual monitoring data x ik of each risk assessment index from the threshold , take its positive value (implemented through the max function), then multiply it by the influence weight i of this index on the risk factor F . Finally, sum up all the indexes to obtain the risk score of the risk factor F i . At the criterion layer, calculate the overall risk score M of the underground coal mine according to the formula , that is, multiply the risk score of each risk factor by its weight in the overall safety, and then sum up to obtain the overall risk score.

[0083] For step S9:

[0084] Take the calculated overall risk score M as the first overall risk evaluation result based on the analytic hierarchy process. This result comprehensively reflects the influence of each risk factor and its indexes in the underground coal mine. By comparing with the preset risk level standard, it can be judged at what level the overall safety risk in the underground coal mine is.

[0085] In an alternative embodiment, based on historical accident data and geological structure data of the underground coal mine, obtain the importance degree of the influence of each element in the risk factor set F on the overall safety of the underground coal mine and the importance degree of the influence of each element in the risk assessment index set i corresponding to the risk factor F on the risk factor F i , including the following steps:

[0086] According to historical accident data, calculate the importance degree D i of the influence of the elements in the risk factor set F on the overall safety in historical accidents and the importance degree i of the influence of the elements in the risk assessment index set corresponding to the risk factor F i on the risk factor F

[0087] Input the geological structure data of the underground coal mine into the trained risk analysis model to obtain the predicted importance degree L i of the influence of the elements in the risk factor set F on the overall safety and the risk factor F iThe corresponding set of risk assessment indicators The elements in i The predicted impact importance on the risk factor F

[0088] Determine the impact importance C of each element in the risk factor set F on the overall safety underground in coal mines according to the following formula i And the risk factor F i The corresponding set of risk assessment indicators The impact importance of each element in i on the risk factor F

[0089] C i =δ 1 ·D i +δ 2 ·L i ;

[0090]

[0091] Among them, δ 1 is the weight coefficient of D i , δ 2 is the weight coefficient of L i , and moreover, δ 1 +δ 2 =1; ε 1 is 's weight coefficient, ε 2 is 's weight coefficient, and moreover, ε 1 +ε 2 =1.

[0092] Specifically, the calculation based on historical accident data:

[0093] First of all, deeply analyze the historical accident data. This data can be the specific situations of various safety accidents that occurred underground in coal mines in the past, covering information such as the types of accidents, the time nodes of occurrence, the specific locations, the scale of casualties and property losses caused, and the actual states of each risk factor at the moment of the accident.

[0094] For each element F in the risk factor set F i , count the frequency of its occurrence in historical accidents and analyze the associated impact on the severity of the accident each time it occurs. For example, if gas explosion accidents frequently appear in past records and each time they cause significant casualties and huge property losses, then the impact weight of the gas risk factor (assumed to be F 1 ) in these accidents will increase significantly. With the help of professional statistical analysis methods and specific analysis models, accurately calculate each risk factor Fi Importance degree D of the impact on overall safety in historical accidents i .

[0095] Meanwhile, for risk factor F i The corresponding set of risk assessment indicators For each element I ik in it, analyze the abnormal fluctuation condition of this indicator and its close connection with the accident severity in the accident scenario involving risk factor F i . For example, in accident cases related to gas risk, the sharp rise of the gas concentration indicator (assumed to be I 11 ) is often directly related to the outbreak of the accident. Through in-depth mining and analysis of these data, calculate the importance degree of each indicator I ik on risk factor F i

[0096] Application of risk analysis model based on geological structure data:

[0097] The geological structure data in the coal mine underground contains multi-dimensional key information such as the thickness change of coal seams, inclination angle, distribution trend of faults, hardness coefficient of rocks, etc. These factors have an important impact on risk factors and their assessment indicators that cannot be ignored.

[0098] First, construct and train a risk analysis model. This model can be a complex system constructed based on machine learning or deep learning algorithms, capable of capturing the potential correlation laws between geological structures and risk factors.

[0099] From the perspective of machine learning, the risk analysis model can adopt a decision tree model. The decision tree learns from a large number of sample data with geological structure characteristics and corresponding risk results to construct a tree-like structure. For example, use geological structure data such as coal seam thickness, number of faults, and rock hardness as the node branching conditions of the tree. If the coal seam thickness is less than a certain threshold, it may continue to judge other factors such as the number of faults along a certain branch. Eventually, the end nodes of each branch correspond to the prediction results of the importance degree of different risk factors on overall safety.

[0100] ​From the perspective of deep learning, a risk analysis model can utilize a neural network model, such as a multi-layer perceptron (MLP). First, the geological structure data is standardized and used as the data for the input layer, and complex non-linear transformations are performed by the neurons in the hidden layer. The number of neurons and the number of layers in the hidden layer can be adjusted according to the complexity of the actual data and the training effect of the model. Through the backpropagation training of a large number of sample data, the connection weights between neurons are continuously adjusted, enabling the model to accurately output the predicted value of the importance of the risk factors to the overall safety based on the input geological structure data.

[0101] Input the geological structure data of the current coal mine underground into this risk analysis model, and the model will predict the importance level L of each risk factor F i to the overall safety. i . For example, if the geological structure data shows that there is a complex fault structure in a specific area, the model is very likely to determine that the importance level L of the roof stability risk factor (assumed to be F 2 ) in this area is at a relatively high level. 2

[0102] Similarly, for each element I in the set of risk assessment indicators corresponding to the risk factor F i , the model will also predict its importance level to the risk factor F ik . For example, for the water hazard risk factor (assumed to be F i ), if the geological structure data indicates that the distance between the aquifer and the coal seam in this area is extremely small, the model will probably predict that the importance level L of the water level change index (assumed to be I 3 ) to the water hazard risk factor F 31 3 is relatively large. 31 31

[0103] Comprehensively determine the importance level:

[0104] To obtain a more accurate, comprehensive and practical importance level of risk factors and their assessment indicators, a weighted summation method can be used to fuse the results obtained based on historical accident data and geological structure data.

[0105] For each element F in the set of risk factors F i , according to the formula C i = δ 1 · D i + δ 2 · L i to calculate its importance level C i to the overall safety of the coal mine underground. Among them, the weight coefficients δ 1 and δ2 It can be reasonably determined according to the relative importance of the influence of risk factors on historical accident data and geological structure data, representing the relative importance weights of historical accident data and geological structure data respectively when determining the degree of influence importance, and satisfying δ 1 +δ 2 = 1. In the actual application process, if we determine based on past experience and the actual situation of the current coal mine that historical accident data plays a more crucial role in the risk assessment process, then we can appropriately increase the value of δ 1 ; conversely, if it is considered that the reference value of geological structure data is more prominent, then the value of δ 2 can be correspondingly increased.

[0106] For each element I i in the risk assessment index set corresponding to the risk factor F ik , according to the formula determine its degree of influence importance on the risk factor F i Here, the weight coefficients ε and ε 1 and ε 2 can also be reasonably determined according to the relative importance of the influence of historical accident data and geological structure data on the index, and satisfy ε 1 +ε 2 = 1.

[0107] In an alternative embodiment, based on the fuzzy comprehensive evaluation method, according to the risk evaluation results of risk factors, a second overall risk evaluation result is obtained, including the following steps:

[0108] Take the risk factor set F = {F 1 , F 2 ,..., F n} as the evaluation factor set U = {u 1 , u 2 ,..., u n}; where, F i corresponds to u i ;

[0109] Set the evaluation grade set V = {v 1 , v 2 ,..., v T}, T is the number of elements in the evaluation grade set V, and v 1 to v T represent different risk levels;

[0110] According to the risk assessment index monitoring data set X, use the following formula to calculate the state value E i of the evaluation factor u i :

[0111]

[0112] According to the status value E i , the evaluation factor u is obtained i subordinate to the risk level v t to the degree r it ; where, t = 1, 2,..., T;

[0113] According to the evaluation factor u i subordinate to the risk level v t to the degree r it , construct the fuzzy relation matrix R = (r it );

[0114] Take the weight vector ω′ = (ω′ 1 , ω′ 2 ,..., ω′ n ) as the weight vector W = (w 1 , w 2 ,..., w n ) corresponding to the evaluation factor set U, where, w i is the weight of the evaluation factor u i , w i = ω′ i ;

[0115] According to the fuzzy relation matrix R and the weight vector W, calculate the fuzzy comprehensive evaluation result vector B; where, B = W·R, B = (b 1 , b 2 ,..., b T ), b t represents the comprehensive possibility degree that the evaluation result is the risk level v t ;

[0116] Take the fuzzy comprehensive evaluation result vector B as the second overall risk evaluation result.

[0117] Specifically, determine the evaluation factor set and the evaluation grade set:

[0118] First, directly set the risk factor set F = {F 1 , F 2 ,..., F n} in the coal mine underground as the evaluation factor set U = {u 1 , u 2 ,..., u n}, where F i and u i are in one-to-one correspondence, that is, each risk factor becomes an evaluation factor.

[0119] Next, the evaluation level set V = {v 1 ,v 2 ,...,v T}, where T represents the number of evaluation levels. These evaluation levels represent different degrees of risk, such as low risk, medium risk, high risk, etc. The specific level division and definition can be determined in combination with the safety standards and actual experience of coal mines.

[0120] Calculate the status value of the evaluation factor:

[0121] Based on the risk assessment indicator monitoring data set X obtained previously, use the formula ω′ ik To calculate each evaluation factor u i The state value E i Here x ik Is a risk factor F i Corresponding risk assessment indicator I ik Monitoring data, ω′ ik Is the indicator for risk factor F i The impact weight of each risk factor is obtained by summing the monitoring data of all evaluation indicators contained in each risk factor and multiplying their corresponding weights. This status value comprehensively reflects the overall situation of the risk factor under the current monitoring data.

[0122] Determine the membership degree and construct the fuzzy relationship matrix:

[0123] According to the calculated state value E i , through a specific membership function or rules based on historical data and expert experience, to determine the evaluation factor u i Belongs to risk level v t The degree of it , where t=1,2,...,T. For example, if the state value E i When it is in a certain value range, it is considered to belong to the low risk level v 1 The degree of belonging to other risk levels is relatively low. In this way, for each evaluation factor u i , we can get its membership vector (r i1 ,r i2 ,…,r iT ).

[0124] The membership vectors of all evaluation factors are combined to construct the fuzzy relationship matrix R = (r it)。Each row of this matrix represents the membership of an evaluation factor to different risk levels, and each column represents the membership of different evaluation factors to the same risk level. It comprehensively reflects the fuzzy relationship between the evaluation factor set and the evaluation level set.

[0125] Determine the weight vector and perform fuzzy composition operation:

[0126] Take the weight vector ω′ = (ω′ 1 , ω′ 2 ,..., ω′ n ) obtained by methods such as the analytic hierarchy process before as the weight vector W = (w 1 , w 2 ,..., w n ) corresponding to the evaluation factor set U, where w i = ω′ i , that is, the weight of each evaluation factor remains unchanged.

[0127] According to the fuzzy relation matrix R and the weight vector W, perform fuzzy composition operation to obtain the fuzzy comprehensive evaluation result vector B. The calculation formula is B = W·R, where B = (b 1 , b 2 ,..., b T ). When calculating specifically, b t represents the comprehensive possibility degree that the evaluation result is the risk level v t . Through this operation, the weight of each evaluation factor and their membership to different risk levels are comprehensively considered, and a vector reflecting the possibility distribution of the overall risk at different levels is obtained, which is used as the second overall risk evaluation result based on the fuzzy comprehensive evaluation method. This result can provide a comprehensive assessment of the safety risk in the coal mine underground from a fuzzy perspective.

[0128] In an optional embodiment, according to the state value E i , obtain the degree r i to which the evaluation factor u t belongs to the risk level v it , including the following steps:

[0129] According to the historical state value data of the evaluation factor u i under the risk level v t , calculate the historical state value mean μ i and the historical state value standard deviation σ t of the evaluation factor u it under the risk level v it ;

[0130] According to the historical state value mean μit and the standard deviation σ of historical status values it , construct the risk level v t 's normal distribution membership function, the risk level v t 's normal distribution membership function is expressed as:

[0131]

[0132] Take the status value E i as the independent variable x and input it into the normal distribution membership function f t (x), to obtain f t (E i ), and take f t (E i ) as r it .

[0133] Specifically, calculate the statistics of historical status values:

[0134] Collect and organize the evaluation factor u i 's historical status value data under the risk level v t . These data are sourced from the status value records of this risk factor in the coal mine underground at corresponding risk levels at different time points in the past, forming a data set.

[0135] Through statistical analysis of this data set, calculate the mean μ i of the historical status values of the evaluation factor u t under the risk level v it . The calculation method of the mean is to add up all historical status values and then divide by the number of data points, which reflects the average status level of this evaluation factor at this risk level.

[0136] Meanwhile, calculate the standard deviation σ it of historical status values. The standard deviation measures the degree of dispersion of the data and can reflect the fluctuation of historical status values around the mean. The larger the standard deviation, the stronger the discreteness of the data and the more unstable the change of the status values of this evaluation factor at this risk level.

[0137] Construct the normal distribution membership function:

[0138] Based on the calculated mean μ it of historical status values and the standard deviation σ it of historical status values, construct the normal distribution membership function f t (x) of the risk level. The normal distribution is a common probability distribution model, and in this case, it can well describe the distribution law of the status values of the evaluation factor at the risk level.

[0139] Its expression is The graph of this function is a bell curve, with the mean μ it as the axis of symmetry, and the standard deviation σ it determining the "fatness" of the curve. When x (i.e., the state value) is close to the mean, the function value is large, indicating a high probability that this state value belongs to this risk level; when x is far from the mean, the function value gradually decreases, indicating a reduced probability that this state value belongs to this risk level.

[0140] Calculate the membership degree:

[0141] Substitute the state value E i of the currently calculated evaluation factor u i as the independent variable x into the normal distribution membership function f t (x), and obtain f t (E i ). This value of f t (E i ) is the degree r i to which the evaluation factor u t belongs to the risk level v it .

[0142] In an alternative embodiment, according to the first overall risk assessment result and the second overall risk assessment result, obtain the comprehensive risk assessment result, including the following steps:

[0143] Calculate the comprehensive risk score S of the underground coal mine according to the following formula:

[0144]

[0145] where α is the weight coefficient of the analytic hierarchy process in the comprehensive risk assessment, (1 - α) is the weight coefficient of the fuzzy comprehensive evaluation method in the comprehensive risk assessment, and β t is the risk score corresponding to the risk level v t ;

[0146] Compare the comprehensive risk score S with the pre-set comprehensive risk score threshold S th to obtain the safety risk level of the underground coal mine;

[0147] Take the safety risk level as the comprehensive risk assessment result.

[0148] Specifically, both the analytic hierarchy process and the fuzzy comprehensive evaluation method play important roles, and weight coefficients need to be set for them respectively. Here, α is the weight coefficient of the analytic hierarchy process in the comprehensive risk assessment, which reflects the relative importance of the first overall risk assessment result obtained based on the analytic hierarchy process in the final comprehensive result; while (1 - α) is the weight coefficient of the fuzzy comprehensive evaluation method in the comprehensive risk assessment, reflecting the proportion of the importance of the fuzzy comprehensive evaluation result.

[0149] In the formula where M is the first overall risk assessment result calculated previously by the analytic hierarchy process, that is, the overall risk score in the coal mine underground. b t is an element in the fuzzy comprehensive evaluation result vector B, representing the comprehensive possibility degree of the evaluation result being the risk level v t . β t is the risk score corresponding to the risk level v t , which can be preset according to the experience and standards of coal mine safety management. Different risk levels correspond to different score values, which are used to quantify the influence degree of each risk level on the comprehensive risk.

[0150] By multiplying the first overall risk assessment result M by its weight coefficient α, and multiplying the possibility degree b t of each risk level in the fuzzy comprehensive evaluation result by its corresponding risk score β t and summing them up and then multiplying by the weight coefficient (1 - α), the two are added together to obtain the comprehensive risk score S of the coal mine underground. This score comprehensively considers the results of the two evaluation methods and can more comprehensively reflect the actual risk situation in the coal mine underground.

[0151] Next, compare the calculated comprehensive risk score S with the preset comprehensive risk score threshold S th . These thresholds can be comprehensively determined according to the safety specifications of the coal mine, historical risk data, and industry standards, etc., dividing the range of the comprehensive risk score into different intervals, and each interval corresponds to a specific safety risk level.

[0152] Finally, determine the determined safety risk level as the comprehensive risk assessment result. This result can intuitively inform the coal mine management personnel of the current safety risk degree in the coal mine underground, so that they can timely take corresponding preventive measures and management strategies to ensure the safe operation of coal mine production.

[0153] In an alternative embodiment, the method for determining the weight coefficient α includes the following steps:

[0154] Obtain the risk assessment related data of the coal mine underground in the past time period. The risk assessment related data includes: the risk factor risk assessment result data X 1 obtained by the analytic hierarchy process, the risk level membership degree data X 2 obtained by the fuzzy comprehensive evaluation method, and the quantitative coding data Y reflecting the actual safety situation;

[0155] Construct a multiple linear regression model Y = γ 0 + γ 1 X 1 + γ 2 X2 + ∈, where Y is the dependent variable, X 1 and X 2 are independent variables, γ 0 is the intercept term, γ 1 and γ 2 are regression coefficients, and ∈ is the random error term;

[0156] Using the data related to risk assessment, parameter estimation of the multiple linear regression model is carried out through statistical analysis software to obtain the estimated values of the regression coefficients γ 1 and γ 2 ;

[0157] According to the estimated values of the regression coefficients γ 1 and γ 2 , the weight coefficient α is determined using the following formula:

[0158]

[0159] Specifically, collect the data related to risk assessment in the past period in the coal mine underground, including the risk evaluation result data X 1 obtained through the analytic hierarchy process, which details the risk assessment values calculated based on the hierarchical structure and the weights of each factor, reflecting the quantitative assessment of the risks in the coal mine underground from the perspective of the analytic hierarchy process. At the same time, collect the risk level membership degree data X 2 obtained through the fuzzy comprehensive evaluation method, which shows the membership degree of each risk factor under different risk levels, presenting the distribution of risks from a fuzzy perspective. In addition, obtain the quantitative coding data Y reflecting the actual safety status, which can be obtained by quantifying and coding according to the actual situation such as whether a safety accident occurs in the coal mine underground, the severity of the accident, the frequency and scope of equipment failures, etc., and is used to measure the real safety level in the coal mine underground.

[0160] Based on the collected data, construct a multiple linear regression model Y = γ 0 + γ 1 X 1 + γ 2 X 2 + ∈. In this model, Y is the dependent variable, representing the actual safety status; X 1 and X 2 are independent variables, which are the risk evaluation result data of the analytic hierarchy process and the risk level membership degree data of the fuzzy comprehensive evaluation method respectively. γ 0 is the intercept term, which plays a role in adjusting the overall level in the model; γ 1 and γ 2are regression coefficients, which will respectively reflect the influence degrees of and on ; ∈ is the random error term, which is used to consider the influence of other factors not explained in the model to ensure the rationality of the model.

[0161] Using the collected data related to risk assessment, parameter estimation is carried out on the constructed multiple linear regression model with the help of professional statistical analysis software. The statistical analysis software will use methods such as the least squares method, and through the analysis and calculation of the data, find the regression coefficients γ that minimize the sum of squared errors between the predicted values and the actual values of the model. 1 and γ 2 estimation values. This process needs to be carried out based on a large number of data samples to ensure that the estimation values have high reliability and accuracy and can truly reflect the relationship between the independent variable and the dependent variable.

[0162] After obtaining the estimation values of the regression coefficients γ 1 and γ 2 , according to the formula determine the weight coefficient α. The absolute value is adopted here to ensure that the calculation of the weight coefficient is not affected by the positive or negative signs of the regression coefficients, and only focuses on the relative magnitude of their influence on the dependent variable. The calculated through this formula can reasonably allocate the weights of the analytic hierarchy process and the fuzzy comprehensive evaluation method in the comprehensive risk assessment, making the final comprehensive risk assessment result more accurately reflect the actual risk situation underground in coal mines.

[0163] The above-mentioned comprehensive management method for underground coal mine safety, by establishing a set of risk factors and the corresponding set of risk assessment indicators underground in coal mines, and obtaining monitoring data; based on the analytic hierarchy process, according to the set of monitoring data of risk assessment indicators, by establishing a hierarchical structure model, combining historical accident data and geological structure data to determine the importance degree of influence of each element and construct a judgment matrix, and obtaining the risk assessment result of risk factors and the first overall risk assessment result after calculation and consistency test; based on the fuzzy comprehensive evaluation method, taking the set of risk factors as the evaluation factor set, setting the evaluation grade set, calculating the state values of evaluation factors, determining the degree of belonging to each risk grade and constructing a fuzzy relation matrix, and combining the weight vector to calculate the fuzzy comprehensive evaluation result vector as the second overall risk assessment result; fusing the first and second overall risk assessment results according to a specific formula to obtain the comprehensive risk assessment result, and determining the fusion weight coefficient through a multiple linear regression model; generating response strategies based on the comprehensive risk assessment result. Thus, a comprehensive and accurate quantitative assessment of underground coal mine safety risks is realized, providing a scientific basis for coal mine safety management, effectively improving the level of underground coal mine safety management, reducing the accident rate, and ensuring the safe and stable operation of coal mine production.

[0164] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this document, the execution of these steps has no strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0165] Based on the same inventive concept, an embodiment of the present application also provides a system for implementing the above-mentioned comprehensive safety management method for coal mines underground. The implementation solutions provided by this system to solve problems are similar to the implementation solutions recorded in the above method. Therefore, the specific limitations in one or more embodiments of the following comprehensive safety management system for coal mines underground can refer to the limitations on a comprehensive safety management method for coal mines in the above text, and will not be repeated here.

[0166] In an exemplary embodiment, as Figure 2 shown, a comprehensive safety management system 20 for coal mines underground is provided, including:

[0167] A risk assessment system establishment module 21, configured to establish a set of risk factors F = {F 1 , F 2 ,..., F n} for coal mines underground and a corresponding set of risk assessment indicators wherein, the set of risk assessment indicators corresponding to the risk factor F i is n is the number of elements in the set of risk factors F, and m i is the number of risk assessment indicators corresponding to the risk factor F i , and i = 1, 2,..., n.

[0168] A data acquisition module 22, configured to acquire the monitoring data of each element in the set of risk assessment indicators i corresponding to each risk factor F to obtain the set of risk assessment indicator monitoring data corresponding to each risk factor F i and thus obtain the set of risk assessment indicator monitoring data corresponding to the set of risk factors F = {F , F 1 ,..., F 2 ,..., F n}

[0169] The hierarchical analysis module 23 is used to obtain the first overall risk evaluation result based on the hierarchical analysis method and according to the risk assessment index monitoring data set X.

[0170] The fuzzy comprehensive evaluation module 24 is used to obtain the second overall risk evaluation result based on the fuzzy comprehensive evaluation method and according to the risk assessment index monitoring data set X.

[0171] The comprehensive risk evaluation module 25 is used to obtain the comprehensive risk evaluation result according to the first overall risk evaluation result and the second overall risk evaluation result.

[0172] The response strategy generation module 26 is used to obtain the response strategy according to the comprehensive risk evaluation result; the response strategy is used to instruct the coal mine shaft management personnel to implement the preventive measures corresponding to the comprehensive risk evaluation result.

[0173] Optionally, the hierarchical analysis module 23 includes:

[0174] The hierarchical structure model construction unit 231 is used to establish a hierarchical structure model according to the risk factor set F and the risk assessment index set I. The hierarchical structure model includes an objective layer, a criterion layer, and an index layer; among them, the objective layer corresponds to the overall safety risk in the coal mine; there are n criteria in the criterion layer, and the i-th criterion corresponds to the risk factor F i ; for the i-th criterion in the index layer, there are m i indicators, and the index set corresponding to the i-th criterion in the index layer is

[0175] The influence importance acquisition unit 232 is used to obtain the influence importance of each element in the risk factor set F on the overall safety in the coal mine and the risk assessment index set i corresponding to the risk factor F for each element in the risk factor F i on the risk factor F.

[0176] The criterion layer judgment matrix construction unit 233 is used to compare each element in the risk factor set F pairwise in the criterion layer based on the influence importance of each element in the risk factor set F on the overall safety in the coal mine, and obtain the risk factor comparison result; obtain the judgment matrix A based on the risk factor comparison result; where A is an n×n matrix, and the elements of A are a ij , i and j respectively represent the serial numbers of different risk factors in the criterion layer, and a ij represents the importance of F i relative to F j , and a ii= 1.

[0177] The index layer judgment matrix construction unit 234 is used to, in the index layer, for each criterion i, based on the importance of the elements in the index set to the risk factor F i , pairwise compare the elements in the index set to obtain the index comparison result; obtain the judgment matrix B based on the index comparison result; where A i is an m i × m i matrix, and the elements of A i are where h and k represent the serial numbers of different risk factor indicators in criterion i, represents the importance of I ik relative to I ih . And

[0178] The criterion layer weight vector calculation unit 235 is used to calculate the maximum eigenvalue λ of the judgment matrix A of the criterion layer and the corresponding eigenvector ω = (ω 1 , ω 2 ,..., ω n ); normalize the eigenvector ω to obtain the weight vector ω' = (ω' 1 , ω' 2 ,..., ω' n ); where ω i represents the importance of the risk factor F i to the overall safety of the coal mine underground; ω' i is the influence weight of the risk factor F i on the overall safety of the coal mine underground.

[0179] The index layer weight vector calculation unit 236 is used to: for the index layer, calculate the maximum eigenvalue λ i of the judgment matrix A i corresponding to each criterion i and the corresponding eigenvector normalize the eigenvector to obtain the weight vector where represents the importance of the risk assessment index I ik to the risk factor F i ; is the influence weight of the risk assessment index I ik on the risk factor F i .

[0180] An acceptable consistency judgment unit 237, which is used to judge whether the judgment matrix A and the judgment matrix A i have acceptable consistency, including:

[0181] Calculating the consistency index of the criterion layer and the consistency index of the index layer for each criterion i

[0182] If , it is confirmed that the judgment matrix A has acceptable consistency; if , it is confirmed that the judgment matrix A i has acceptable consistency; where RI is the preset random consistency index of the n-order matrix, and RI i is the preset random consistency index of the m i -order matrix.

[0183] An overall risk score calculation unit 238, which is used to perform the following operations when it is confirmed that both the judgment matrix A and the judgment matrix A i have acceptable consistency:

[0184] At the index layer, calculate the risk score R of each risk factor F i according to the following formula: i :

[0185]

[0186] where, is the monitoring data threshold of the preset risk assessment index I ik ;

[0187] At the criterion layer, calculate the overall risk score M of the underground coal mine according to the following formula:

[0188]

[0189] A first overall risk evaluation result determination unit 239, which is used to use the overall risk score M as the first overall risk evaluation result.

[0190] Optionally, the influence importance acquisition unit 232 includes:

[0191] A first influence importance acquisition subunit 2321, which is used to calculate the influence importance D of the elements in the risk factor set F on the overall safety in historical accidents according to historical accident data i and the influence importance of the elements in the corresponding risk assessment index set i of the risk factor F on the risk factor F i

[0192] ​The second importance degree acquisition subunit 2322 is configured to input the underground coal mine geological structure data into the trained risk analysis model, and obtain the predicted influence importance degree L of the elements in the risk factor set F on the overall safety. i And the risk factor F i The corresponding risk assessment index set The predicted influence importance degree of the elements in i on the risk factor F

[0193] The comprehensive influence importance degree calculation subunit 2323 is configured to determine the influence importance degree C of each element in the risk factor set F on the overall safety of the underground coal mine according to the following formula i And the risk factor F i The corresponding risk assessment index set The influence importance degree of each element in i on the risk factor F

[0194] C i =δ 1 ·D i +δ 2 ·L i ;

[0195]

[0196] Wherein, δ 1 is the weight coefficient of D i , δ 2 is the weight coefficient of L i , and δ 1 +δ 2 =1; ε 1 is 's weight coefficient, ε 2 is 's weight coefficient, and ε 1 +ε 2 =1.

[0197] Optionally, the fuzzy comprehensive evaluation module 24 includes:

[0198] The evaluation factor set setting unit 241 is configured to use the risk factor set F = {F 1 , F 2 ,..., F n} as the evaluation factor set U = {u 1 , u 2 ,..., u n}; wherein, F i corresponds to u i .

[0199] The evaluation level set setting unit 242 is used to set the evaluation level set V = {v 1 ,v 2 ,...,v T}, T is the number of elements in the evaluation level set V, v 1 to v T Represents different risk levels.

[0200] The evaluation factor state value calculation unit 243 is used to calculate the evaluation factor u according to the risk assessment indicator monitoring data set X using the following formula: i The state value E i :

[0201]

[0202] The membership degree calculation unit 244 is used to calculate the membership degree according to the state value E i , get the evaluation factor u i Belongs to risk level v t The degree of it ; where t=1,2,...,T.

[0203] The fuzzy relationship matrix construction unit 245 is used to i Belongs to risk level v t The degree of it , construct the fuzzy relationship matrix R = (r it ).

[0204] The evaluation factor weight vector acquisition unit 246 is used to convert the weight vector ω′=(ω′ 1 ,ω′ 2 ,...,ω′ n ) as the weight vector W corresponding to the evaluation factor set U = (w 1 ,w 2 ,...,w n ), where w i is the evaluation factor u i The weight, w i =ω′ i .

[0205] The fuzzy comprehensive evaluation result calculation unit 247 is used to calculate the fuzzy comprehensive evaluation result vector B according to the fuzzy relationship matrix R and the weight vector W; wherein B=W·R, B=(b 1 ,b 2 ,...,b T ), b t Indicates that the evaluation result is risk level v t The overall probability of

[0206] The second overall risk assessment result determination unit 248 is configured to use the fuzzy comprehensive evaluation result vector B as the second overall risk assessment result.

[0207] Optionally, the membership degree calculation unit 244 includes:

[0208] The membership function parameter calculation subunit 2441 is configured to calculate the mean value μ of the historical state values and the standard deviation σ of the historical state values of the evaluation factor u at the risk level v according to the historical state value data of the evaluation factor u at the risk level v. i at the risk level v t of the evaluation factor u i at the risk level v t of the evaluation factor u it and the standard deviation σ of the historical state values it .

[0209] The membership function construction subunit 2442 is configured to construct a normal distribution membership function of the risk level v according to the mean value μ of the historical state values and the standard deviation σ of the historical state values. The expression of the normal distribution membership function of the risk level v is: it and the standard deviation σ of the historical state values it to construct a normal distribution membership function of the risk level v t of the risk level v t The expression of the normal distribution membership function of the risk level v is:

[0210]

[0211] The membership degree determination subunit 2443 is configured to use the state value E i as the independent variable x and input it into the normal distribution membership function f t (x) to obtain f t (E i ) and use f t (E i ) as r it .

[0212] Optionally, the comprehensive risk assessment module 25 includes:

[0213] The comprehensive risk score calculation unit 251 is configured to calculate the comprehensive risk score S of the underground coal mine according to the following formula:

[0214]

[0215] where α is the weight coefficient of the analytic hierarchy process in the comprehensive risk assessment, (1 - α) is the weight coefficient of the fuzzy comprehensive evaluation method in the comprehensive risk assessment, and β t is the risk score corresponding to the risk level v t .

[0216] The risk level determination unit 252 is configured to compare the comprehensive risk score S with a preset comprehensive risk score threshold S th to obtain the safety risk level of the underground coal mine.

[0217] The comprehensive risk assessment result determination unit 253 is configured to use the safety risk level as the comprehensive risk assessment result.

[0218] Optionally, the comprehensive risk assessment module 25 further includes a comprehensive risk scoring weight coefficient obtaining unit 254, which is configured to perform the following operations:

[0219] Obtain risk assessment related data for the past period in the coal mine underground. The risk assessment related data includes: the risk assessment result data X of risk factors obtained by the analytic hierarchy process 1 , the risk level membership degree data X obtained by the fuzzy comprehensive evaluation method 2 , and the quantitative coding data Y reflecting the actual safety condition;

[0220] Construct a multiple linear regression model Y = γ 0 +γ 1 X 1 +γ 2 X 2 +∈, where Y is the dependent variable, X 1 and X 2 are independent variables, γ 0 is the intercept term, γ 1 and γ 2 are regression coefficients, and ∈ is the random error term;

[0221] Use the risk assessment related data to estimate the parameters of the multiple linear regression model through statistical analysis software, and obtain the estimated values of the regression coefficients γ 1 and γ 2 ;

[0222] According to the estimated values of the regression coefficients γ 1 and γ 2 , use the following formula to determine the weight coefficient α:

[0223]

[0224] An embodiment of the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps in the foregoing method embodiments are implemented.

[0225] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the foregoing method embodiments are implemented.

[0226] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial descriptions of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0227] The above embodiments only represent several implementation manners of the embodiments of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the embodiments of the application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the embodiments of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A comprehensive safety management method for underground coal mines, characterized in that: The method comprises: Establish the risk factor set F = {F1, F2, ..., F n } and the corresponding risk assessment indicator set Among them, risk factor F i The corresponding risk assessment indicator set is n is the number of elements in the risk factor set F, m i Risk factor F i The number of corresponding risk assessment indicators, i = 1, 2, ..., n; Obtain each of the risk factors F i Corresponding risk assessment indicator set The monitoring data of each element in the i Corresponding risk assessment indicator monitoring data set Thus, the risk factor set F = {F1, F2, ..., F n }Corresponding risk assessment indicator monitoring data set Based on the analytic hierarchy process, a first overall risk assessment result is obtained according to the risk assessment indicator monitoring data set X; Based on the fuzzy comprehensive evaluation method, according to the risk assessment indicator monitoring data set X, a second overall risk assessment result is obtained; Obtaining a comprehensive risk assessment result according to the first overall risk assessment result and the second overall risk assessment result; A response strategy is obtained according to the comprehensive risk assessment result; the response strategy is used to instruct coal mine management personnel to implement preventive measures corresponding to the comprehensive risk assessment result.

2. The method according to claim 1, characterized in that The hierarchical analysis method is based on the risk assessment indicator monitoring data set X to obtain the risk factor risk assessment result and the first overall risk assessment result, including: S1: establishing a hierarchical model according to the risk factor set F and the risk assessment indicator set I, wherein the hierarchical model includes a target layer, a criterion layer and an indicator layer; The target layer corresponds to the overall safety risk of the coal mine; the criterion layer has n criteria, and the i-th criterion corresponds to the risk factor F i ; The indicator layer has m for the i-th criterion i indicators, the indicator set corresponding to the i-th criterion in the indicator layer is S2: Based on the historical accident data and the geological structure data of the coal mine, the importance of each element in the risk factor set F on the overall safety of the coal mine and the risk factor F are obtained. i Corresponding risk assessment indicator set Effects of each element on risk factor F i The importance of the impact; S3: In the criterion layer, based on the importance of each element in the risk factor set F on the overall safety of the coal mine underground, each element in the risk factor set F is compared in pairs to obtain a risk factor comparison result; and a judgment matrix A is obtained based on the risk factor comparison result; Among them, A is an n×n matrix, and the elements of A are a ij , i and j represent the serial numbers of different risk factors in the criterion layer, a ij Indicates F i Relative to F j The importance of ij >0, And a ii =1; S4: In the indicator layer, for each criterion i, based on the indicator set Effects of each element on risk factor F i The importance of the impact on the indicator set Compare each element in pairwise to obtain an index comparison result; obtain a judgment matrix B based on the index comparison result; Among them, A i is m i ×m i Matrix, A i The elements of h and k represent the serial numbers of different risk factor indicators in criterion i, Indicates I ik Relative to I ih The importance of and S5: Calculate the maximum eigenvalue λ of the judgment matrix A of the criterion layer and the corresponding eigenvector ω=(ω1,ω2,...,ω n );Normalize the feature vector ω to obtain a weight vector ω′=(ω′1,ω′2,...,ω′ n ); Among them, ω i Representative risk factor F i The importance of the impact on the overall safety of the coal mine; ω′ i Risk factor F i The weight of the impact on the overall safety of the coal mine; S6: For the indicator layer, calculate the judgment matrix A corresponding to each criterion i i The maximum eigenvalue λ i and the corresponding eigenvector For the feature vector Normalize to get the weight vector in, Representative risk assessment index I ik Risk Factors i Impact importance; Risk Assessment Index I ik Risk Factors i The influence weight of i , S7: Determine the judgment matrix A and the judgment matrix A i Acceptable consistency, including: Calculate the consistency index of the criterion layer and the consistency index of the index layer for each criterion i like , confirm that the judgment matrix A has acceptable consistency; if When confirming the judgment matrix A i With acceptable consistency; RI is the preset n-order matrix random consistency index, RI i The preset m i Random consistency index of order matrix; S8: When the confirmation judgment matrix A and the confirmation judgment matrix A i When all have acceptable consistency, at the indicator level, each risk factor F is calculated according to the following formula i The risk score R i : in, The preset risk assessment indicator I ik Monitoring data thresholds; At the criterion level, the overall risk score M of the coal mine is calculated according to the following formula: S9: Using the overall risk score M as the first overall risk assessment result.

3. The method according to claim 2, characterized in that Based on the historical accident data and the geological structure data of the coal mine, the importance of each element in the risk factor set F on the overall safety of the coal mine and the risk factor F are obtained. i Corresponding risk assessment indicator set Effects of each element on risk factor F i The importance of the impact includes: According to the historical accident data, calculate the importance D of the elements in the risk factor set F on the overall safety in the historical accidents i and risk factors F i Corresponding risk assessment indicator set The elements in the risk factor F i The importance of the impact The underground geological structure data of the coal mine is input into the trained risk analysis model to obtain the predicted impact importance L of the elements in the risk factor set F on the overall safety. i and risk factors F i Corresponding risk assessment indicator set The elements in the risk factor F i The importance of the predicted impact Determine the importance of each element in the risk factor set F on the overall safety of the coal mine underground according to the following formula C i and risk factors F i Corresponding risk assessment indicator set Effects of each element on risk factor F i The importance of the impact C i =δ1·D i +δ2·L i ; Among them, δ1 is D i The weight coefficient of L i The weight coefficient, and δ1+δ2=1; ε1 is The weight coefficient of ’s weight coefficient, and ε1+ε2=1.

4. The method according to claim 2, characterized in that: The fuzzy comprehensive evaluation method is used to obtain a second overall risk assessment result according to the risk factor risk assessment result, including: The risk factor set F = {F1, F2, ..., F n } as the evaluation factor set U = {u1,u2,...,u n }; where F i with u i correspond; Set the evaluation level set V = {v1, v2, ..., v T }, T is the number of elements in the evaluation level set V, v1 to v T Represents different risk levels; According to the risk assessment indicator monitoring data set X, the evaluation factor u is calculated using the following formula i The state value E i : According to the state value E i , get the evaluation factor u i Belongs to risk level v t The degree of it ; Wherein, t=1,2,...,T; According to the evaluation factor u i Belongs to risk level v t The degree of it , construct the fuzzy relationship matrix R = (r it ); The weight vector ω′=(ω′1,ω′2,...,ω′ n ) as the weight vector W corresponding to the evaluation factor set U = (w1, w2, ..., w n ), where w i is the evaluation factor u i The weight, w i =ω′ i ; According to the fuzzy relationship matrix R and the weight vector W, a fuzzy comprehensive evaluation result vector B is calculated; wherein B=W·R, B=(b1, b2, ..., b T ), b t Indicates that the evaluation result is risk level v t The overall probability of The fuzzy comprehensive evaluation result vector B is used as the second overall risk evaluation result.

5. The method according to claim 4, characterized in that The state value E i , get the evaluation factor u i Belongs to risk level v t The degree of it ,include: According to the evaluation factor u i At risk level v t Under the historical state value data, calculate the evaluation factor u i At risk level v t The mean value of historical state value μ under it and the standard deviation of historical state values ​​σ it ; According to the historical state value mean μ it and the standard deviation of the historical state value σ it , construct the risk level v t The normal distribution membership function, the risk level v t The expression of the normal distribution membership function is: The state value E i As the independent variable x, input the normal distribution membership function f t (x), we get f t (E i ), and f t (E i ) as r it .

6. The method according to claim 4 or 5, characterized in that: The step of obtaining a comprehensive risk assessment result based on the first overall risk assessment result and the second overall risk assessment result includes: The comprehensive risk score S of the coal mine is calculated according to the following formula: Among them, α is the weight coefficient of the hierarchical analysis method in comprehensive risk assessment, (1-α) is the weight coefficient of the fuzzy comprehensive evaluation method in comprehensive risk assessment, and β t The risk level is v t The corresponding risk score; The comprehensive risk score S is compared with the pre-set comprehensive risk score threshold S th Compare and obtain the safety risk level of the coal mine; The safety risk level is used as the comprehensive risk assessment result.

7. The method according to claim 6, characterized in that The method for determining the weight coefficient α includes: Obtain risk assessment related data of the coal mine in the past period of time, wherein the risk assessment related data includes: risk factor risk assessment result data X1 obtained by the analytic hierarchy process, risk level membership data X2 obtained by the fuzzy comprehensive evaluation method, and quantitative coding data Y reflecting the actual safety status; Construct a multiple linear regression model Y = γ0 + γ1X1 + γ2X2 + ∈, where Y is the dependent variable, X1 and X2 are independent variables, γ0 is the intercept term, γ1 and γ2 are regression coefficients, and ∈ is the random error term; Using the risk assessment related data, the parameters of the multivariate linear regression model are estimated by statistical analysis software to obtain estimated values ​​of regression coefficients γ1 and γ2; According to the estimated values ​​of regression coefficients γ1 and γ2, the weight coefficient α is determined using the following formula:

8. A comprehensive safety management system for underground coal mines, characterized in that: The system comprises: The risk assessment system establishment module is used to establish the risk factor set F = {F1, F2, ..., F n } and the corresponding risk assessment indicator set Among them, risk factor F i The corresponding risk assessment indicator set is n is the number of elements in the risk factor set F, m i Risk factor F i The number of corresponding risk assessment indicators, i = 1, 2, ..., n; A data acquisition module is used to obtain each of the risk factors F i Corresponding risk assessment indicator set The monitoring data of each element in the i Corresponding risk assessment indicator monitoring data set Thus, the risk factor set F = {F1, F2, ..., F n }Corresponding risk assessment indicator monitoring data set A hierarchical analysis module, configured to obtain a first overall risk assessment result based on the risk assessment indicator monitoring data set X based on a hierarchical analysis method; A fuzzy comprehensive evaluation module, used to obtain a second overall risk evaluation result based on the risk assessment indicator monitoring data set X based on the fuzzy comprehensive evaluation method; A comprehensive risk assessment module, configured to obtain a comprehensive risk assessment result according to the first overall risk assessment result and the second overall risk assessment result; The response strategy generation module is used to obtain a response strategy based on the comprehensive risk assessment results; the response strategy is used to instruct coal mine management personnel to implement preventive measures corresponding to the comprehensive risk assessment results.

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 method according to any one of claims 1 to 7 is 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 method according to any one of claims 1 to 7 is implemented.

Images