Coal mine accident reason analysis importance sorting method and system

Abstract

The invention provides a coal mine accident reason analysis importance sorting method and system, and belongs to the technical field of computers. The method comprises the following steps: calculating an influence value of each network node in a coal mine accident cause network model under different preset centrality indexes; based on the influence value of each accident cause node under each preset centrality index and the weight corresponding to each preset centrality index, determining comprehensive influence data of each accident cause node; comparing the comprehensive influence data of each accident cause node with the influence value of each accident cause node under each preset centrality index, determining a plurality of accident core cause nodes and accident cause nodes correspondingly associated with each accident core cause node, sorting the importance degrees of each accident cause node, and determining the importance degree of each accident cause node; and obtaining an importance sorting result of the accident cause nodes of the target coal mine accident. The coal mine accident cause importance ranking can be quantified and accurately identified, so that the accident prevention key point can be determined.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and particularly to a method for ranking the importance of coal mine accident cause analysis, a system for ranking the importance of coal mine accident cause analysis, a machine-readable storage medium, and an electronic device. Background Art

[0002] Analyzing accident causes and summarizing rules from past accidents are important means to prevent coal mine accidents. In recent years, the governance effect of coal mine accidents has rebounded, and major and extremely serious accidents have recurred. The current form of coal mine accident prevention is still severe. There is no once-and-for-all solution for coal mine accident prevention. Instead, it is more necessary to accumulate experience in dealing with high-consequence and low-probability events with a high-probability thinking. Only by being vigilant at all times and deeply studying the accident occurrence rules can we prevent the rebound of accident prevention effects. This makes it particularly crucial to conduct in-depth analysis of accident causes and find the core accident causes, which helps to clarify accident prevention measures, prevent the recurrence of similar accidents, ensure a rapid response in case of emergencies, and thus minimize the losses caused by accidents to the greatest extent.

[0003] The current existing technologies have studied accident causes. For the related research on coal mine accident cause analysis, it is more concentrated in aspects such as accident cause analysis and safety risk assessment. However, the means for analyzing and finding key accident causes usually mainly rely on the cause frequency statistical analysis based on accident causation models, lacking in-depth cause quantification analysis methods. Coal mine accidents occur within a complex social-technical system, which includes multiple aspects such as personnel, machinery, processes, and management.

[0004] Therefore, how to quantitatively and accurately identify the importance ranking of coal mine accident causes to determine the key points of accident prevention is an urgent problem to be solved currently. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a method and system for ranking the importance of coal mine accident cause analysis to at least solve the above problem of how to quantitatively and accurately identify the importance ranking of coal mine accident causes.

[0006] To achieve the above purpose, the first aspect of the present invention provides a method for ranking the importance of coal mine accident cause analysis, including:

[0007] Based on the coal mine accident cause network model of the target coal mine accident, calculate the influence values of each network node in the coal mine accident cause network model under different preset centrality indicators; wherein, the network nodes include accident cause nodes;

[0008] Based on the influence values of each accident cause node under each preset centrality indicator and the weights corresponding to each preset centrality indicator determined in advance, determine the comprehensive influence data of each accident cause node;

[0009] According to the coal mine accident cause network model of the target coal mine accident, compare the comprehensive influence data of each accident cause node with the influence values of each accident cause node under each preset centrality index, so as to determine multiple accident core cause nodes among the accident cause nodes and the accident cause nodes associated with each accident core cause node, determine the importance degree of each accident cause node, and sort the importance degrees of each accident cause node to obtain the importance ranking result of the accident cause nodes of the target coal mine accident.

[0010] Optionally, the determination of multiple accident core cause nodes among the accident cause nodes, the accident cause nodes associated with each accident core cause node, and the importance degree of each accident cause node includes:

[0011] Determine the accident cause nodes with comprehensive influence data greater than the preset value as accident core cause nodes, and determine the accident cause nodes with comprehensive influence data not greater than the preset value as accident cause nodes to be determined;

[0012] According to the coal mine accident cause network model and the influence values of the accident cause nodes to be determined under each preset centrality index, determine the accident cause nodes to be determined that connect different types of accident cause nodes as accident core cause nodes;

[0013] According to the coal mine accident cause network model, determine the network topology diagram of each accident core cause node;

[0014] According to the network topology diagram of each accident core cause node, the comprehensive influence data, and the influence values under each preset centrality index, determine the importance degree of each accident core cause node and the accident cause nodes whose association degree with each accident core cause node reaches the preset degree; among them, the comprehensive influence data of the accident core cause node is proportional to the importance degree of the accident core cause node.

[0015] Optionally, the rules for sorting the importance degrees of each accident cause node include:

[0016] According to the comprehensive influence data of each accident cause node and the influence values of each accident cause node under each preset centrality index, sort the importance degrees of the accident cause nodes corresponding to each accident core cause node in turn to obtain the importance ranking result of the accident cause nodes corresponding to each accident core cause node;

[0017] Based on the importance degrees of each accident core cause node, sort the importance ranking results of the accident cause nodes corresponding to each accident core cause node in descending order of importance degree to obtain the importance ranking result of the accident cause nodes of the target coal mine accident.

[0018] Optionally, the above preset centrality indicators include node degree centrality indicator, betweenness centrality indicator, and eigenvector centrality indicator;

[0019] The determination rules for the comprehensive influence data of accident cause nodes include:

[0020] Based on the influence values of each network node under each preset centrality indicator, use the entropy weight method to calculate the weights corresponding to each preset centrality indicator;

[0021] Based on the weights corresponding to each preset centrality indicator, use the weighted sum method to construct a ranking model for the importance of coal mine accident factors; among them, the ranking model for the importance of coal mine accident factors is F-Score i represents the comprehensive influence data of the i-th accident cause node, w 1 represents the weight of the node degree centrality indicator, w 2 represents the weight of the betweenness centrality indicator, w 3 represents the weight of the eigenvector centrality indicator, DC i represents the influence value of the i-th accident cause node under the node degree centrality indicator, BC i represents the influence value of the i-th accident cause node under the betweenness centrality indicator, EC i represents the influence value of the i-th accident cause node under the eigenvector centrality indicator, max(DC k ) represents the maximum influence value under the node degree centrality indicator, max(BC k ) represents the maximum influence value under the betweenness centrality indicator, max(EC k ) represents the maximum influence value under the eigenvector centrality indicator;

[0022] Based on the ranking model for the importance of coal mine accident factors and the influence values of each network node under each preset centrality indicator, calculate the comprehensive influence data of each accident cause node.

[0023] Optionally, the construction rules of the above coal mine accident cause network model include:

[0024] Based on the historical coal mine accident data of the target coal mine accident, construct a coal mine accident cause network model according to the network modeling rules;

[0025] Among them, the coal mine accident cause network model includes an individual action layer, an individual ability layer, a management system layer, and a safety culture layer. The network nodes in the coal mine accident cause network model represent accident causes, and the directed line segments between the network nodes represent the causal relationships between the network nodes.

[0026] Optionally, after obtaining the importance ranking result of the accident cause nodes of the target coal mine accident, the method further includes:

[0027] Simulate the connectivity of the coal mine accident cause network model after removing the accident core cause nodes to obtain a simulation result;

[0028] Based on the simulation result, use a preset attack strategy to verify the efficiency of cutting off the accident risk propagation path of a plurality of predetermined accident prevention strategies, and obtain an efficiency verification result corresponding to each accident prevention strategy; wherein, each accident prevention strategy corresponds to a preset centrality index or a comprehensive index combining all preset centrality indexes;

[0029] Based on the efficiency verification results corresponding to each accident prevention strategy, determine the optimal accident prevention strategy.

[0030] Optionally, the above preset attack strategy includes a deliberate attack strategy and a random attack strategy, and the efficiency verification result includes the network connectivity efficiency of the coal mine accident cause network model after the attack and the network global efficiency of the coal mine accident cause network model after the attack;

[0031] The above use of a preset attack strategy to verify the efficiency of cutting off the accident risk propagation path of a plurality of predetermined accident prevention strategies and obtain an efficiency verification result corresponding to each accident prevention strategy includes:

[0032] After deliberately attacking the coal mine accident cause network model using the deliberate attack strategy, calculate the network connectivity efficiency of the coal mine accident cause network model after the attack and the network global efficiency of the coal mine accident cause network model after the attack;

[0033] After randomly attacking the coal mine accident cause network model using the random attack strategy, calculate the network connectivity efficiency of the coal mine accident cause network model after the attack and the network global efficiency of the coal mine accident cause network model after the attack;

[0034] Among them, the calculation formula for the network connectivity efficiency is:

[0035]

[0036] S is the network connectivity efficiency, N GCC is the number of network nodes in the largest connected component in the coal mine accident cause network model, N total is the total number of network nodes in the coal mine accident cause network model;

[0037] The calculation formula for the network global efficiency is:

[0038]

[0039] Egl0ba is the global network efficiency, and N is the total number of network nodes in the coal mine accident cause network model. is the shortest path length between network node i and network node j.

[0040] The second aspect of the present invention provides a coal mine accident cause analysis importance ranking system, including:

[0041] An influence value calculation module, configured to calculate the influence values of each network node in the coal mine accident cause network model under different preset centrality indexes based on the coal mine accident cause network model of the target coal mine accident; wherein, the network nodes include accident cause nodes.

[0042] A comprehensive influence data determination module, configured to determine the comprehensive influence data of each accident cause node based on the influence values of each accident cause node under each preset centrality index and the weights corresponding to each preset centrality index determined in advance.

[0043] An importance ranking module, configured to compare the comprehensive influence data of each accident cause node and the influence values of each accident cause node under each preset centrality index according to the coal mine accident cause network model of the target coal mine accident, so as to determine multiple accident core cause nodes among the accident cause nodes and the accident cause nodes associated with each accident core cause node, and determine the importance degree of each accident cause node, and rank the importance degrees of each accident cause node to obtain the importance ranking result of the accident cause nodes of the target coal mine accident.

[0044] The third aspect of the present invention provides a machine-readable storage medium, on which instructions are stored, and when the instructions are executed by a processor, the processor is configured to execute the above-mentioned coal mine accident cause analysis importance ranking method.

[0045] The fourth aspect of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned coal mine accident cause analysis importance ranking method is implemented.

[0046] Through the above technical solution, a method and system for ranking the importance of coal mine accident causes are provided. Based on the coal mine accident cause network model of the target coal mine accident, after comprehensively considering multiple preset centrality indicators, the influence values of each network node in the coal mine accident cause network model under different preset centrality indicators are calculated. According to the influence values of each accident cause node under each preset centrality indicator and the weights corresponding to each preset centrality indicator, the comprehensive influence data of each accident cause node is calculated to measure the influence of each accident cause node in different aspects of the coal mine accident cause network model. According to the coal mine accident cause network model of the target coal mine accident, by comparing the comprehensive influence data of each accident cause node with the influence values of each accident cause node under each preset centrality indicator, multiple accident core cause nodes in the accident cause nodes and the accident cause nodes associated with each accident core cause node are determined, and the importance degree of each accident cause node is determined, and the importance degrees of each accident cause node are ranked to obtain the importance ranking result of the accident cause nodes of the target coal mine accident. Thus, the purpose of quantitatively and accurately identifying the importance ranking of coal mine accident causes is achieved, which is conducive to determining the key points of accident prevention.

[0047] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent specific embodiment part. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings are used to provide a further understanding of the embodiments of the present invention, and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation to the embodiments of the present invention. In the drawings:

[0049] Figure 1 is a flowchart of a method for ranking the importance of coal mine accident causes provided by an embodiment of the present invention;

[0050] Figure 2 is a schematic diagram of the sub-network transmission process of the accident core cause nodes of F-Score provided by an embodiment of the present invention;

[0051] Figure 3 is a schematic diagram of the robustness analysis of the gas explosion accident cause network provided by an embodiment of the present invention;

[0052] Figure 4 is a block diagram of a system for ranking the importance of coal mine accident causes provided by an embodiment of the present invention;

[0053] Figure 5 is a schematic diagram of the structure of an electronic device provided by a preferred embodiment of the present invention.

[0054] DESCRIPTION OF THE REFERENCE NUMERALS

[0055] 10 - Electronic device, 100 - Processor, 101 - Memory, 102 - Computer program. Detailed implementation manners

[0056] The following will describe in detail the specific implementation manners of the present invention in conjunction with the accompanying drawings. It should be understood that the specific implementation manners described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0057] Figure 1 It is a flowchart of a method for ranking the importance of analyzing the causes of coal mine accidents provided by an embodiment of the present invention. As Figure 1 shown, an embodiment of the present invention provides a method for ranking the importance of analyzing the causes of coal mine accidents, including:

[0058] S110: Based on the coal mine accident cause network model of the target coal mine accident, calculate the influence values of each network node in the coal mine accident cause network model under different preset centrality indicators; wherein, the network nodes include accident cause nodes;

[0059] In some embodiments of this embodiment, the above preset centrality indicators include node degree centrality indicator, betweenness centrality indicator, and eigenvector centrality indicator.

[0060] It should be noted that the centrality of a network refers to a measure of the importance or influence of nodes in a complex network. It measures the relative importance of nodes in the network through different mathematical indicators. The network centrality can be calculated through a variety of indicators, mainly including the following: Node degree centrality: Measures the number of edges directly connected to a node in the network, reflecting the activity and influence of the node. Closeness centrality: Calculates the average distance from a node to all other nodes in the network. The smaller the distance, the closer the node is to other nodes. Betweenness centrality: Measures its importance by calculating the number of shortest paths passing through a node, reflecting the control ability of the node in information transmission. Eigenvector centrality: Considers the importance of node neighbors. The importance of a node depends not only on the number of nodes directly connected to it, but also on the importance of these neighbors. DomiRank centrality: A new measurement method that combines local and structural-level information to evaluate the impact of a node on the stability and functionality of the entire network.

[0061] Specifically, this method is based on the coal mine accident cause network model of the target coal mine accident, and uses node degree centrality (DC), betweenness centrality (BC), and eigenvector centrality (EC) to calculate the influence values of different network nodes.

[0062] S120: Determine the comprehensive influence data of each accident cause node based on the influence values of each accident cause node under each preset centrality index and the weights corresponding to each preset centrality index determined in advance.

[0063] In some implementation manners of this embodiment, the determination rule of the comprehensive influence data of the accident cause node includes: calculating the weights corresponding to each preset centrality index by using the entropy weight method based on the influence values of each network node under each preset centrality index; constructing an importance ranking model of coal mine accident factors in a weighted sum manner based on the weights corresponding to each preset centrality index; where the importance ranking model of coal mine accident factors is F-Score i represents the comprehensive influence data of the i-th accident cause node, w 1 represents the weight of the node degree centrality index, w 2 represents the weight of the betweenness centrality index, w 3 represents the weight of the eigenvector centrality index, DC i represents the influence value of the i-th accident cause node under the node degree centrality index, BC i represents the influence value of the i-th accident cause node under the betweenness centrality index, EC i represents the influence value of the i-th accident cause node under the eigenvector centrality index, max(DC k ) represents the maximum influence value under the node degree centrality index, max(BC k ) represents the maximum influence value under the betweenness centrality index, max(EC k ) represents the maximum influence value under the eigenvector centrality index; calculate the comprehensive influence data of each accident cause node based on the importance ranking model of coal mine accident factors and the influence values of each network node under each preset centrality index.

[0064] Specifically, the entropy weight method (it should be noted that the core idea of the entropy weight method is to use information entropy to measure the information volume and dispersion degree of each evaluation index. The smaller the information entropy, the greater the variability of the index, the more information it provides, and thus the greater its weight) is used to calculate the weights corresponding to each preset centrality index (including the node degree centrality index, the betweenness centrality index, and the eigenvector centrality index). The weighted sum of the three indexes of the node degree centrality index, the betweenness centrality index, and the eigenvector centrality index is used to construct a method for ranking the importance of coal mine accident factors based on F-Score to measure the influence of each accident cause node in different aspects of the coal mine accident cause network model. In order to obtain the comprehensive measure of each accident cause node, this method uses the entropy weight method to calculate the weights of each preset centrality index. The weights of the node degree centrality index, the betweenness centrality index, and the eigenvector centrality index are respectively expressed as w 1 、w 2 、w 3 . Specifically, the greater the dispersion degree of the preset centrality index, the greater its entropy, and the greater the influence of the index on the response variable (i.e., the weight). From this point of view, the influence of the accident cause node can be expressed by F-Score as

[0065] S130: According to the coal mine accident cause network model of the target coal mine accident, compare the comprehensive influence data of each accident cause node and the influence values of each accident cause node under each preset centrality index to determine multiple accident core cause nodes among the accident cause nodes and the accident cause nodes associated with each accident core cause node, and determine the importance degree of each accident cause node, and rank the importance degrees of each accident cause node to obtain the importance ranking result of the accident cause nodes of the target coal mine accident.

[0066] Specifically, based on the coal mine accident cause network model of the target coal mine accident, after comprehensively considering multiple preset centrality indicators, the influence values of each network node in the coal mine accident cause network model under different preset centrality indicators are calculated. According to the influence values of each accident cause node under each preset centrality indicator and the weights corresponding to each preset centrality indicator, the comprehensive influence data of each accident cause node is calculated to measure the influence of each accident cause node in different aspects of the coal mine accident cause network model. According to the coal mine accident cause network model of the target coal mine accident, by comparing the comprehensive influence data of each accident cause node with the influence values of each accident cause node under each preset centrality indicator, multiple accident core cause nodes in the accident cause nodes and the accident cause nodes associated with each accident core cause node are determined, and the importance degree of each accident cause node is determined, and the importance degrees of each accident cause node are sorted to obtain the importance ranking result of the accident cause nodes of the target coal mine accident. Thus, the purpose of quantifiable and accurate identification of the importance ranking of coal mine accident causes is achieved, which is beneficial to determining the key points of accident prevention.

[0067] In some implementation manners of this embodiment, the determination of multiple accident core cause nodes in the accident cause nodes, the accident cause nodes associated with each accident core cause node, and the importance degree of each accident cause node includes:

[0068] Determine the accident cause nodes with comprehensive influence data greater than the preset value as accident core cause nodes, and determine the accident cause nodes with comprehensive influence data not greater than the preset value as accident cause nodes to be determined;

[0069] Please refer to Table 1, which shows the numerical values of the centrality indicators of accident causes. Compare the proposed method of ranking the importance of coal mine accident factors based on F-Score with the numerical values of the centrality indicators of accident causes for three methods: degree centrality (DC), betweenness centrality (BC), and eigenvector centrality (EC). According to the centrality measure index F-Score, the ranking of the influence of the core nodes in the gas explosion accident network is shown in Table 2, which is the topological parameters of the core nodes in the gas explosion accident cause network. Table 2 shows the top seventeen nodes with the highest F-Score (the nodes are network nodes), and the average F-Score between the nodes is 0.0538. Six accident core nodes in the gas explosion accident cause network are obtained with F-Score = 0.2 as the boundary. This also means that some factors in the accident occupy most of the connectivity of the accident network. In addition, different from the way of simply judging hub nodes based on betweenness centrality, according to the F-Score of different nodes, nodes with relatively small total degree values in the accident network may also become core nodes, because they are bridge nodes connecting different associated groups. For example, although the total degree values (i.e., comprehensive influence data) of IA61 and IA41 are relatively small, they radiate other surrounding cause factors as the central points in the accident cause network. Topological indicators of the core nodes in the gas explosion accident network.

[0070] Table 1 Numerical values of the centrality indicators of accident causes

[0071]

[0072] Table 2 Topological parameters of the core nodes in the gas explosion accident cause network

[0073]

[0074]

[0075] According to the coal mine accident cause network model and the influence numerical values of the accident cause nodes to be determined under each preset centrality indicator, the accident cause nodes to be determined that connect different types of accident cause nodes are used as accident core cause nodes;

[0076] Exemplarily, although the total degree values (i.e., comprehensive influence data) of IA61 and IA41 are relatively small, they radiate other surrounding cause factors as the central points in the accident cause network.

[0077] According to the coal mine accident cause network model, determine the network topology diagram of each accident core cause node;

[0078] Based on the network topology diagrams of the core cause nodes of each accident, the comprehensive influence data, and the influence values under each preset centrality index, determine the importance degree of each accident core cause node and the accident cause nodes whose association degree with each accident core cause node reaches the preset degree; among them, the comprehensive influence data of the accident core cause node is proportional to the importance degree of the accident core cause node.

[0079] Specifically, after determining the accident core cause nodes of the coal mine accident cause network model, the control of the accident core cause nodes is an important means to reduce the accident path length and lower the network security risk transmission efficiency. Please refer to Figure 2 , Figure 2 is a schematic diagram of the sub-network transmission process of the accident core cause nodes of F-Score provided by an embodiment of the present invention, Figure 2 which shows the sub-network transmission process of the 4 core nodes with the largest F-Score. The size of the nodes in each sub-network represents the influence of the corresponding type of accident cause according to the value of F-Score, and the thickness of the directed curve represents the number of times it appears in the accident. Among them, the F-Score of the SP02 (indicating illegal production by continuing to violate the production suspension order) node is the largest, which is 0.7329. Illegal production is the most important factor leading to the occurrence of gas explosion accidents. The nodes strongly affected by it also include IA24 (indicating mining instead of tunneling), IA67 (indicating mining beyond the boundary), IA69 (indicating overproduction), IA73 (indicating unauthorized resumption of work during production suspension), and IA76 (indicating unauthorized modification of the production system), etc.

[0080] In some embodiments of this embodiment, the rules for ranking the importance degrees of the accident cause nodes include: according to the comprehensive influence data of each accident cause node and the influence values of each accident cause node under each preset centrality index, rank the importance degrees of the accident cause nodes corresponding to each accident core cause node in turn to obtain the importance ranking results of the accident cause nodes corresponding to each accident core cause node; based on the importance degrees of each accident core cause node, sort the importance ranking results of the accident cause nodes corresponding to each accident core cause node in descending order of importance degree to obtain the importance ranking results of the accident cause nodes of the target coal mine accident. Thus, for each accident core cause node, after ranking the importance degrees of the accident cause nodes corresponding to each accident core cause node, and then integrating the importance ranking results of the accident cause nodes corresponding to all accident core cause nodes, the importance ranking results of the accident cause nodes of the target coal mine accident can be obtained.

[0081] In some embodiments of this embodiment, the construction rules of the above coal mine accident cause network model include: based on the historical coal mine accident data of the target coal mine accident, constructing a coal mine accident cause network model according to the network modeling rules; wherein, the coal mine accident cause network model includes an individual action layer, an individual ability layer, a management system layer, and a safety culture layer, the network nodes in the coal mine accident cause network model represent accident causes, and the directed line segments between the network nodes represent the causal relationships between the network nodes.

[0082] Specifically, taking the coal mine gas explosion accident as a specific implementation case, obtaining and using the historical coal mine accident data of the target coal mine accident (the target coal mine accident can be a coal mine gas explosion accident) to construct a corresponding coal mine accident cause network model based on the network modeling rules (such as the coal mine gas explosion accident cause network corresponding to the coal mine gas explosion accident), the coal mine accident cause network model includes an individual action layer, an individual ability layer, a management system layer, and a safety culture layer, the network nodes represent accident causes, and the directed line segments represent causal relationships.

[0083] In some embodiments of this embodiment, after obtaining the importance ranking result of the accident cause nodes of the target coal mine accident, the method further includes: simulating the connectivity of the coal mine accident cause network model after removing the accident core cause nodes to obtain a simulation result; based on the simulation result, using a preset attack strategy to verify the efficiency of cutting off the accident risk propagation path of a plurality of predetermined accident prevention strategies to obtain an efficiency verification result corresponding to each accident prevention strategy; wherein, each accident prevention strategy corresponds to a preset centrality index or a comprehensive index combining all preset centrality indexes; based on the efficiency verification results corresponding to each accident prevention strategy, determining the optimal accident prevention strategy.

[0084] Among them, each accident prevention strategy corresponds to three accident prevention strategies: degree centrality (DC), betweenness centrality (BC), and F-Score index-based.

[0085] Specifically, due to the complexity of the accident cause transmission process, when a certain safety measure fails or an unsafe action occurs, it may cause other accident cause nodes around this node to be at safety risk. Conduct a robustness analysis on the constructed coal mine accident cause network model, and reverse verify the efficiency of Scheme F-Score and other schemes for quickly cutting off the accident risk propagation path by simulating the connectivity of the coal mine accident cause network model after removing the accident core cause nodes. Use a preset attack strategy to verify the ability of the three accident prevention strategies of degree centrality (DC), betweenness centrality (BC), and F-Score index-based to eliminate safety risks, and determine the final accident prevention strategy based on the efficiency verification results.

[0086] In some embodiments of this embodiment, the above-mentioned preset attack strategies include deliberate attack strategies and random attack strategies, and the efficiency verification results include the network connectivity efficiency of the coal mine accident cause network model after the attack and the network global efficiency of the coal mine accident cause network model after the attack; the above-mentioned use of the preset attack strategies to verify the efficiency of cutting off the accident risk propagation path of a plurality of pre-determined accident prevention strategies, and obtaining the efficiency verification results corresponding to each accident prevention strategy, including: after using the deliberate attack strategy to conduct a deliberate attack on the coal mine accident cause network model, calculating the network connectivity efficiency of the coal mine accident cause network model after the attack and the network global efficiency of the coal mine accident cause network model after the attack; after using the random attack strategy to conduct a random attack on the coal mine accident cause network model, calculating the network connectivity efficiency of the coal mine accident cause network model after the attack and the network global efficiency of the coal mine accident cause network model after the attack; wherein, the calculation formula of the network connectivity efficiency is: S is the network connectivity efficiency, N GCC is the number of network nodes in the largest connected component in the coal mine accident cause network model, N total is the total number of network nodes in the coal mine accident cause network model; the calculation formula of the network global efficiency is: E globa is the network global efficiency, N is the total number of network nodes in the coal mine accident cause network model, is the shortest path length between network node i and network node j.

[0087] Specifically, the selection of the accident cause network attack strategy (i.e., the preset attack strategy) for this method is as follows: in this method, the deliberate attack strategy selects a specific target attack method based on node degree, and the selected deliberate attack strategy is a specific target attack method based on node degree, including degree centrality (DC), betweenness centrality (BC), and attacking the network nodes in the coal mine accident cause network model in the order of F-Score size. During the analysis process, the robustness of the coal mine accident cause network model will be determined by comparing the variation laws of the maximum connected subgraph efficiency and the global efficiency of the coal mine accident cause network model under the two strategies of the random attack strategy and the deliberate attack strategy. The relative sizes of S and E of the coal mine accident cause network model are the changes in the network connectivity efficiency and the network global efficiency of the coal mine accident cause network model after each attack. Among them, the network connectivity efficiency can be calculated by dividing the number of nodes in the largest connected component by the total number of network nodes. The formula can be expressed as: wherein, S is the connectivity efficiency of the network, N GCC is the number of nodes in the largest connected component, and N totalis the total number of nodes in the network. This ratio reflects the ability of the coal mine accident cause network model to maintain connectivity in the face of failures or attacks. If most nodes are within one connected component, it indicates that the network (i.e., the coal mine accident cause network model) has a high connectivity rate, meaning the network is more stable as a whole. Conversely, if the ratio is low, it means the network (i.e., the coal mine accident cause network model) is more sensitive to node failures and has poor connectivity and robustness. The global efficiency N globa is mathematically defined as the average of the reciprocals of the shortest path lengths between all possible node pairs in the network. For a given target network G, the formula for calculating the global efficiency is as follows: where N is the total number of nodes in the network, is the shortest path length between node i and node j. The global efficiency (E globa ) takes into account all node pairs and emphasizes the efficiency of the path by taking the reciprocal of the shortest path length, that is, the shorter the path, the higher the efficiency it contributes.

[0088] Please refer to Figure 3 , Figure 3 which is a schematic diagram of the robustness analysis of the gas explosion accident cause network provided by an embodiment of the present invention. The robustness of the example gas explosion accident cause network is analyzed. Among them, the analysis of the random attack strategy is as follows: For the first strategy of node failure, causal nodes are randomly attacked (i.e., relevant accident prevention measures are randomly selected to remove causal nodes). When nodes are randomly attacked, since the accident network exhibits scale-free characteristics, the vast majority of nodes have low degree values and few connections. At this time, low-degree nodes account for a large proportion of the nodes in the gas explosion accident cause network, and the probability that nodes with fewer connection edges are first attacked and disabled is relatively high. This also causes the connectivity rate S of the network to show a slow downward trend when the network is randomly attacked. Figure 3 (a) is a schematic diagram of the proportion change of the largest connected subgraph under different attack modes. As shown in Figure 3 (a), when 10% of the nodes are randomly attacked, the connectivity rate of the accident cause network is 81%. Since there are still multiple interdependent connections in the accident cause network at this time, the nodes in the causal path that are not attacked remain in the accident network. And the decrease in the connectivity rate S also approaches a linear decrease. This trend continues until the number of failed nodes in the network increases to 81%, and the network connectivity rate S drops to 10%. At this time, the interdependent edges between the networks decrease, and the causal nodes and accident nodes are almost completely disconnected. When 99% of the nodes are attacked, the accident cause network is completely destroyed, and the connectivity rate S value drops to 0. Figure 3(a) The continuous linear trend of network connectivity indicates that the accident-causing network has a high degree of robustness against random attacks. If safety managers unconsciously and randomly select accident prevention measures, the accident network may maintain a high degree of connectivity. That is, in the daily safety management of coal mines, randomly selected safety prevention measures have little effect on eliminating safety hazards. At this time, with a certain amount of safety investment, the effect of accident prevention is limited, especially in small and medium-sized coal mines with poor working environments and rough safety management. In addition, the analysis of the deliberate attack strategy is as follows: For the second strategy of node failure, the deliberate attack is achieved by eliminating nodes in a certain order. Commonly used attack methods include attacking in the decreasing order of the total degree value (DC) and betweenness centrality (BC). By comparing the F-Score proposed in this paper with the above two deliberate attack strategies, the robustness results of the accident network are analyzed. As Figure 3 (a) shows, overall, when applying the three deliberate attack strategies to remove nodes from the network, the gas explosion accident-causing network presents similar failure modes, that is, the connectivity rate S of the network decreases rapidly to varying degrees. From the overall decreasing trend of network connectivity, the attack strategy based on the decreasing order of F-Score performs significantly better than the above two other attack strategies. As more nodes are deliberately attacked, the connectivity value in the accident network begins to decline rapidly. It is worth noting that under the F-Score attack strategy, when the proportion of failed nodes rises to 22%, the connectivity of the gas explosion accident-causing network has decreased by 50%. This also verifies that in the process of safety management of coal mine gas explosion accidents, targeted safety prevention measures can minimize accident risks. When the node failure probability increases to 40%, the connectivity of the gas explosion accident-causing network is almost completely disconnected, and the network connectivity rate S value drops to 10%. At this time, under the two attack strategies based on the total degree value and betweenness centrality, there are still a large number of paths in the network, and the network connectivity rates S are 28% and 42% respectively, and the F-Score attack strategy is 17% lower than the other two methods. In addition, global efficiency is also a network characteristic metric used to evaluate the information transfer efficiency between nodes in the network. Figure 3 (b) is a schematic diagram of the change in global efficiency under different attack modes, as Figure 3 (b) shows, when the global efficiency of the accident network drops to 10%, at this time, the proportions of network nodes removed under the F-Score attack, DC attack, and random attack are 18%, 23%, and 41% respectively. This also shows that the F-Score is superior to the general topological structure analysis in analyzing the influence of network nodes and is more conducive to quickly obtaining the key points of accident prevention.

[0089] In some embodiments of the present embodiment, the method further includes visualizing the key points of various accident causes using a display. Specifically, according to the selected application field and the output analysis indicators, the prevention sequence of accident causes and the core node network in different application scenarios are visually displayed, facilitating the rapid identification of the key points of accident prevention.

[0090] In the actual application process, based on the constructed coal mine accident cause network model of the target coal mine accident, after comprehensively considering three types of network centrality indicators (including node degree centrality indicator, betweenness centrality indicator, and eigenvector centrality indicator), the entropy weight method is used to calculate the weights of each centrality indicator, and the weighted sum of the three centrality indicators is used to construct a coal mine accident factor importance ranking method based on F-Score to measure the influence of each accident cause node in different aspects of the coal mine accident cause network model. By comparing the numerical values of different network node influence analysis methods (specific methods include node degree centrality (DC), betweenness centrality (BC), eigenvector centrality (EC), and F-Score-based), the core accident causes of coal mine accidents (i.e., the accident core cause nodes in the coal mine accident cause network model) and the optimal accident cause importance ranking method are determined, and the core nodes and the corresponding network topology diagrams in the demonstration cases are given. By simulating the connectivity of the coal mine accident cause network model after removing the accident core cause nodes, the efficiency of the F-Score scheme and other schemes for quickly cutting off the accident risk propagation path is verified in reverse. From the two attack strategies of the deliberate attack strategy and the random attack strategy, the ability of the degree centrality (DC), betweenness centrality (BC), and the accident prevention strategy based on the F-Score index to eliminate safety risks is verified, and then the final accident prevention strategy is determined. And the accident cause analysis results can be visually displayed. In summary, the method can be applied to the formulation of accident prevention measures in coal mine enterprises, helping to find the optimal measures to prevent accidents and prevent the occurrence of accidents. Thus, it helps the coal mine safety management department select the key risk factors that need to be removed, thereby formulating accident prevention strategies and preventing the occurrence of accidents.

[0091] In the above implementation process, after comprehensively considering three types of network centrality indicators (including node degree centrality indicator, betweenness centrality indicator, and eigenvector centrality indicator), the method uses the entropy weight method to calculate the weights of each centrality indicator, and proposes a method for ranking the importance of coal mine accident factors based on F-Score using the weighted sum of the three centrality indicators to measure the influence of each accident cause node in different aspects of the network. This method can also be used for reference in the analysis of accident causes of other similar types. By comparing the conventional network centrality analysis indicators (such as node degree centrality (DC), betweenness centrality (BC), and eigenvector centrality (EC)) with the F-Score-based network centrality indicator proposed by this method, an example template for finding the core accident causes of coal mine accidents and the optimal ranking of accident cause importance is given, providing a solution for comprehensively understanding the occurrence path and mechanism of coal mine accidents. This method can overcome the disadvantage of insufficient quantitative analysis of the original accident prevention strategy, and compared with the conventional network centrality indicator analysis method, the importance ranking method based on the F-Score index proposed by this method is 17% superior to the conventional analysis method in determining the importance of accident prevention. This method can help the coal mine safety department select key risk factors to be removed, so as to formulate accident prevention strategies and prevent the occurrence of accidents.

[0092] In some embodiments of this embodiment, a method for ranking the importance of coal mine accident cause analysis includes: based on conventional network centrality indicators, proposing a method for ranking the importance of accident causes based on the F-Score index. Taking the coal mine gas explosion accident as an example, different network centrality indicators are compared to determine the core accident causes of the coal mine gas explosion accident and the optimal ranking of accident cause importance. Based on the proposed centralized network centrality indicators, a robustness analysis is performed on the gas explosion accident cause network to determine the ability of different accident prevention strategies to eliminate safety risks.

[0093] Among them, the method for ranking the importance of accident causes based on the F-Score index includes: after comprehensively considering three types of network centrality indicators (including: node degree centrality (DC), betweenness centrality (BC), and eigenvector centrality (EC)), using the entropy weight method to calculate the weights of each centrality indicator, and proposing a method for ranking the importance of coal mine accident factors based on F-Score using the weighted sum of the three centrality indicators to measure the influence of each accident cause node in different aspects of the network.

[0094] Among them, determining the core accident causes of coal mine gas explosion accidents and the optimal importance ranking of accident causes includes: taking coal mine gas explosion accidents as an example, comparing the importance ranking method of coal mine accident factors based on F-Score with the numerical values of the centrality indicators of the accident cause network for the three methods of degree centrality (DC), betweenness centrality (BC), and eigenvector centrality (EC), and then giving the core accident causes and cause network diagrams of coal mine gas explosion accidents.

[0095] Among them, the accident prevention strategy includes: conducting a robustness analysis on the constructed gas explosion accident cause network model, and reversely verifying the efficiency of the F-Score scheme and other schemes for quickly cutting off the accident risk propagation path by simulating the connectivity of the cause network after removing nodes.

[0096] Figure 4 It is a block diagram of an importance ranking system for coal mine accident cause analysis provided by an embodiment of the present invention. As Figure 4 shown, the embodiment of the present invention provides an importance ranking system for coal mine accident cause analysis, including:

[0097] An influence value calculation module, configured to calculate the influence values of each network node in the coal mine accident cause network model under different preset centrality indicators based on the coal mine accident cause network model of the target coal mine accident; among them, the network nodes include accident cause nodes;

[0098] A comprehensive influence data determination module, configured to determine the comprehensive influence data of each accident cause node based on the influence values of each accident cause node under each preset centrality indicator and the weights corresponding to each preset centrality indicator determined in advance;

[0099] An importance ranking module, configured to compare the comprehensive influence data of each accident cause node and the influence values of each accident cause node under each preset centrality indicator according to the coal mine accident cause network model of the target coal mine accident, so as to determine multiple accident core cause nodes among the accident cause nodes and the accident cause nodes associated with each accident core cause node, and determine the importance degree of each accident cause node, and rank the importance degrees of each accident cause node to obtain the importance ranking result of the accident cause nodes of the target coal mine accident.

[0100] Specifically, based on the coal mine accident cause network model of the target coal mine accident, after comprehensively considering multiple preset centrality indicators, the influence values of each network node in the coal mine accident cause network model under different preset centrality indicators are calculated. According to the influence values of each accident cause node under each preset centrality indicator and the weights corresponding to each preset centrality indicator, the comprehensive influence data of each accident cause node is calculated to measure the influence of each accident cause node in different aspects of the coal mine accident cause network model. According to the coal mine accident cause network model of the target coal mine accident, by comparing the comprehensive influence data of each accident cause node with the influence values of each accident cause node under each preset centrality indicator, multiple accident core cause nodes in the accident cause nodes and the accident cause nodes associated with each accident core cause node are determined, and the importance degree of each accident cause node is determined, and the importance degrees of each accident cause node are sorted to obtain the importance ranking result of the accident cause nodes of the target coal mine accident. Thus, the purpose of quantifiable and accurate identification of the importance ranking of coal mine accident causes is achieved, which is beneficial to determining the key points of accident prevention.

[0101] An embodiment of the present invention also provides a machine-readable storage medium, on which instructions are stored, and when the instructions are executed by the processor 100, the processor 100 is configured to execute the above-mentioned importance ranking method for coal mine accident cause analysis.

[0102] The machine-readable storage medium includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0103] An embodiment of the present invention also provides an electronic device 10, which includes a memory 101, a processor 100, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the above-mentioned importance ranking method for analyzing the causes of coal mine accidents is implemented.

[0104] As Figure 5 shown is a schematic diagram of an electronic device provided by an embodiment of the present invention. As Figure 5 shown, the electronic device 10 of this embodiment includes: a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the steps in the above method embodiment are implemented. Alternatively, when the processor 100 executes the computer program 102, the functions of each module / unit in the above device embodiment are implemented.

[0105] Exemplarily, the computer program 102 can be divided into one or more modules / units. One or more modules / units are stored in the memory 101 and executed by the processor 100 to complete the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 102 in the electronic device 10. For example, the computer program 102 can be divided into an influence value calculation module, a comprehensive influence data determination module, and an importance ranking module.

[0106] The electronic device 10 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The electronic device 10 may include, but is not limited to, a processor 100 and a memory 101. Those skilled in the art can understand that Figure 5 this is only an example of the electronic device 10 and does not constitute a limitation on the electronic device 10. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, the electronic device may also include input / output devices, network access devices, a bus, etc.

[0107] The processor 100 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0108] The memory 101 may be an internal storage unit of the electronic device 10, such as the hard disk or memory of the electronic device 10. The memory 101 may also be an external storage device of the electronic device 10, such as a plug-in hard disk equipped on the electronic device 10, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 101 may also include both the internal storage unit and the external storage device of the electronic device 10. The memory 101 is used to store computer programs and other programs and data required by the electronic device 10. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0109] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example for illustration. In actual applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0110] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product 102. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product 102 implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0111] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products 102 according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor 100 of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor 100 of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0112] These computer program instructions can also be stored in a computer-readable memory 101 that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory 101 generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0113] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0114] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0115] The above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for ranking the importance of coal mine accident cause analysis, characterized in that: include: Based on the coal mine accident cause network model of the target coal mine accident, the influence value of each network node in the coal mine accident cause network model under different preset centrality indicators is calculated; wherein the network node includes the accident cause node; Based on the influence values ​​of each accident cause node under each preset centrality index and the pre-determined weights corresponding to each preset centrality index, the comprehensive influence data of each accident cause node is determined; According to the coal mine accident cause network model of the target coal mine accident, the comprehensive influence data of each accident cause node and the influence value of each accident cause node under each preset centrality index are compared to determine multiple accident core cause nodes in the accident cause node and the accident cause nodes corresponding to each accident core cause node, and the importance of each accident cause node is determined, and the importance of each accident cause node is ranked to obtain the importance ranking result of the accident cause node of the target coal mine accident.

2. The importance ranking method for coal mine accident cause analysis according to claim 1 is characterized in that: The determining of multiple accident core cause nodes in the accident cause node, the accident cause nodes corresponding to each accident core cause node, and the importance of each accident cause node includes: Determine the accident cause nodes whose comprehensive influence data is greater than the preset value as the accident core cause nodes, and the accident cause nodes whose comprehensive influence data is not greater than the preset value as the accident cause nodes to be determined; According to the network model of coal mine accident causes and the influence values ​​of the undetermined accident cause nodes under each preset centrality index, the undetermined accident cause nodes connecting different types of accident cause nodes are taken as the accident core cause nodes; According to the network model of coal mine accident causes, determine the network topology of the core cause nodes of each accident; According to the network topology diagram, comprehensive influence data and influence values ​​under each preset centrality index of each core cause node of the accident, the importance of each core cause node of the accident and the accident cause nodes whose correlation with each core cause node of the accident reaches the preset degree are determined; among which, the comprehensive influence data of the core cause node of the accident is proportional to the importance of the core cause node of the accident.

3. The importance ranking method for coal mine accident cause analysis according to claim 2 is characterized in that: The rules for ranking the importance of each accident cause node include: According to the comprehensive influence data of each accident cause node and the influence value of each accident cause node under each preset centrality index, the importance of the accident cause nodes corresponding to each accident core cause node is ranked in turn to obtain the accident cause node importance ranking result corresponding to each accident core cause node; Based on the importance of each core cause node of the accident, the importance ranking results of the accident cause nodes corresponding to each core cause node of the accident are comprehensively ranked in order from large to small, and the importance ranking results of the accident cause nodes of the target coal mine accident are obtained.

4. The importance ranking method for coal mine accident cause analysis according to claim 1 is characterized in that: The preset centrality indexes include node degree centrality index, betweenness centrality index and eigenvector centrality index; The determination rules of the comprehensive influence data of the accident cause node include: Based on the influence value of each network node under each preset centrality index, the entropy weight method is used to calculate the weight corresponding to each preset centrality index; Based on the weights corresponding to each preset centrality index, a coal mine accident factor importance ranking model is constructed using a weighted sum method; wherein, the coal mine accident factor importance ranking model is: F-Score i represents the comprehensive influence data of the i-th accident cause node, w1 represents the weight of the node degree centrality index, w2 represents the weight of the betweenness centrality index, w3 represents the weight of the eigenvector centrality index, DC i represents the influence value of the i-th accident cause node under the node degree centrality index, BC i represents the influence value of the i-th accident cause node under the betweenness centrality index, EC i represents the influence value of the i-th accident cause node under the eigenvector centrality index, max(DC k ) represents the maximum influence value under the node degree centrality index, max(BC k ) represents the maximum influence value under the betweenness centrality index, max(EC k ) represents the maximum influence value under the eigenvector centrality index; Based on the importance ranking model of coal mine accident factors and the influence value of each network node under each preset centrality index, the comprehensive influence data of each accident cause node is calculated.

5. The importance ranking method for coal mine accident cause analysis according to claim 1 is characterized in that: The construction rules of the coal mine accident cause network model include: Based on the historical coal mine accident data of the target coal mine accident, a network model of the cause of the coal mine accident is constructed according to the network modeling rules; Among them, the coal mine accident cause network model includes individual action layer, individual ability layer, management system layer and safety culture layer. The network nodes in the coal mine accident cause network model represent the cause of the accident, and the directed line segments between the network nodes represent the causal relationship between the network nodes.

6. The importance ranking method for coal mine accident cause analysis according to claim 1 is characterized in that: After obtaining the importance ranking result of the accident cause nodes of the target coal mine accident, the method further includes: The connectivity of the coal mine accident cause network model after removing the core cause node of the accident is simulated, and the simulation results are obtained; Based on the simulation results, the preset attack strategies are used to verify the efficiency of multiple predetermined accident prevention strategies in cutting off the accident risk propagation path, and the efficiency verification results corresponding to each accident prevention strategy are obtained; among which, each accident prevention strategy corresponds to a preset centrality index or a comprehensive index that integrates all preset centrality indexes; Based on the efficiency verification results corresponding to each accident prevention strategy, the optimal accident prevention strategy is determined.

7. The importance ranking method for coal mine accident cause analysis according to claim 6 is characterized in that: The preset attack strategy includes a deliberate attack strategy and a random attack strategy, and the efficiency verification result includes the network connectivity efficiency of the coal mine accident cause network model after the attack and the network global efficiency of the coal mine accident cause network model after the attack; The efficiency of cutting off the accident risk propagation path of the predetermined multiple accident prevention strategies is verified by using the preset attack strategy, and the efficiency verification results corresponding to each accident prevention strategy are obtained, including: After the coal mine accident cause network model is intentionally attacked using the intentional attack strategy, the network connectivity efficiency of the coal mine accident cause network model after the attack and the network global efficiency of the coal mine accident cause network model after the attack are calculated; After using the random attack strategy to randomly attack the coal mine accident cause network model, the network connectivity efficiency of the coal mine accident cause network model after the attack and the network global efficiency of the coal mine accident cause network model after the attack are calculated; The calculation formula of the network connectivity efficiency is: S is the network connectivity efficiency, N GCC is the number of network nodes in the largest connected component in the coal mine accident cause network model, N total is the total number of network nodes in the coal mine accident cause network model; The calculation formula of the network global efficiency is: E globa is the global efficiency of the network, N is the total number of network nodes in the coal mine accident cause network model, is the shortest path length between network node i and network node j.

8. A coal mine accident cause analysis importance ranking system, characterized in that: include: An influence value calculation module is used to calculate the influence value of each network node in the coal mine accident cause network model under different preset centrality indicators based on the coal mine accident cause network model of the target coal mine accident; wherein the network node includes the accident cause node; A comprehensive influence data determination module, used to determine the comprehensive influence data of each accident cause node based on the influence value of each accident cause node under each preset centrality index and the predetermined weight corresponding to each preset centrality index; The importance ranking module is used to compare the comprehensive influence data of each accident cause node and the influence value of each accident cause node under each preset centrality index according to the coal mine accident cause network model of the target coal mine accident, so as to determine multiple accident core cause nodes in the accident cause node and the accident cause nodes corresponding to each accident core cause node, determine the importance of each accident cause node, and rank the importance of each accident cause node to obtain the importance ranking result of the accident cause node of the target coal mine accident.

9. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the importance ranking method for analyzing the causes of coal mine accidents as described in any one of claims 1 to 7.

10. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for ranking the importance of coal mine accident cause analysis as described in any one of claims 1 to 7 is implemented.

Images