CN-121998423-A - Urban rail transit construction safety coupling risk factor identification method and system

Abstract

The invention provides an urban rail transit construction safety coupling risk factor identification method and system, which belong to the technical field of building construction safety risk identification, wherein five risk factor sets including personnel, equipment, materials, management and environment are constructed based on building construction history accident data, quantitative processing is carried out on accident reasons and result losses, a risk factor-accident result data matrix is established, an improved Apriori association rule mining algorithm of accident result weights is introduced, the coupling relation among the risk factors is identified through weighted support degree, weighted confidence degree and weighted lifting degree, the association rule obtained through mining is mapped into a complex network, and the importance of node degree and proximity centrality measurement risk factors in the network is utilized to realize identification and sequencing of the construction safety coupling risk factors. The invention simultaneously considers the occurrence frequency of risk factors and the severity of accident results, identifies key coupling risk and junction risk factors, and provides scientific basis for construction safety risk management and decision.

Inventors

• MA JIANGPING
• LI XUDONG
• LI XIAOYUN
• WANG JIANQIAO
• LI CHONG
• Gao Fanqian
• SUN ZUO
• PU ZHIZHOU
• WANG YANHUI
• SHI XIAOBO
• SU WEI
• DU XIAOWEI
• WANG DAWEI
• SUN BOJIE
• Bu Weicheng
• GU XIULI

Assignees

• 张家口通泰大数据信息服务有限公司
• 北京交通大学

Dates

Publication Date

20260508

Application Date

20260126

Claims (10)

1. 1. The city track traffic construction-oriented safety coupling risk factor identification method is characterized by comprising the following steps of: The method comprises the steps of constructing a risk factor set and an accident data set, wherein, based on building construction safety related specifications, standards and accident reports, a risk factor set covering five types of risk factors including personnel, equipment, materials, management and environment is established, a construction accident report is acquired, accident cause and accident result information is extracted to form an accident sample data set comprising the risk factors and the accident result; introducing accident consequence weights on the basis of an Apriori algorithm, calculating weighted support, weighted confidence and weighted lifting degree, and mining the coupling relation among risk factors; the association rules are mapped into nodes and edges in the complex network, the nodes represent risk factors or a combination of the risk factors, the edge weights represent weighted confidence degrees, and the hub nodes and key coupling risk factors in the complex network are determined based on the node degrees and the proximity centrality.
2. 2. The urban rail transit construction safety coupling risk factor identification method according to claim 1 is characterized in that an Apriori algorithm considering the severity of accident results is used for mining association relations among different risk factors and coupling risk factors, and the weighted support degree and the weighted confidence degree are defined as follows: ; ; ; Wherein, the Is a risk factor Is a weighted support of (1); Is the first The weight value of the individual risk factors, Is the first The number of injuries reported by the accident where the individual risk factors are located, Is the first The number of deaths reported from the incident in which the individual risk factors are located, Is the first The economic loss reported by the accident where the individual risk factors are located, Respectively setting weight values for experts; as a matrix of risk factors, Represent the first And reporting the accident.
3. 3. The urban rail transit construction safety coupling risk factor identification method according to claim 1, wherein a complex network is constructed according to an association rule mining result, specifically, each association rule is regarded as an edge in the complex network, the front item and the rear item of the association rule are respectively regarded as the initial node and the target node of the network, the weight value of the edge is the weighted confidence of the association rule, and the like, so that a complex network taking the risk factor as the node is constructed.
4. 4. The urban rail transit construction safety coupling risk factor identification method according to claim 1, wherein the degree of a node is defined as the number of edges directly connected to the node. The higher the degree, the greater the importance of the node in the network, the following calculation method is adopted: ; ; Wherein, the Is a node Is used for the degree of (a), Is the set of all the nodes in the network, Is an element in the adjacency matrix.
5. 5. The urban rail transit construction safety coupling risk factor identification method according to claim 1, wherein the proximity centrality quantifies the overall accessibility of a node in a network by measuring the reciprocal of the average shortest path length from the node to all other nodes, the node with high proximity centrality is relatively close to other nodes in the network, high-efficiency interaction can be realized through fewer intermediate steps, the proximity centrality represents the potential efficiency of the node in the information diffusion, influence propagation or risk transfer process in a complex network, and the node with higher proximity centrality can reach other nodes more quickly, so that the key role in the global connectivity and function integration of the network is played: Is a node Is a measure of proximity centrality of (a). Is a slave node To the node Is provided for the shortest path length of (a).
6. 6. The urban rail transit construction safety coupling risk factor identification method according to claim 2, wherein, ; Is a risk factor Is expressed by the weighted confidence of the risk factor Resulting in risk factors The association rule may be generated by comparing the confidence level to a defined threshold size; ; Is a risk factor In the sense of measuring risk factors And risk factors Independence of (1) if the degree of elevation is A strong association rule is generally considered correct if the value of (2) is greater than 1.
7. 7. The utility model provides an urban rail transit construction safety coupling risk factor identification system which characterized in that includes: The system comprises a construction module, a risk factor matrix, a quantitative weighting module, a control module and a control module, wherein the construction module is used for constructing a risk factor set and an accident data set, wherein the risk factor set covering five risk factors of personnel, equipment, materials, management and environment is established based on building construction safety related norms, standards and accident reports; the computing module is used for introducing accident consequence weights on the basis of an Apriori algorithm, computing weighted support degree, weighted confidence degree and weighted lifting degree, and mining the coupling relation among risk factors; The determining module is provided with nodes and edges which map the association rules into the complex network, wherein the nodes represent risk factors or the combination of the risk factors, the edge weights represent weighted confidence degrees, and the hub nodes and key coupling risk factors in the complex network are determined based on the node degrees and the proximity centrality.
8. 8. A non-transitory computer readable storage medium for storing computer instructions which, when executed by a processor, implement the urban rail transit construction-oriented security coupling risk factor identification method of any of claims 1-6.
9. 9. A computer device comprising a memory and a processor, the processor and the memory in communication with each other, the memory storing program instructions executable by the processor, the processor invoking the program instructions to perform the urban rail transit construction safety coupling risk factor identification method of any of claims 1-6.
10. 10. An electronic device comprising a processor, a memory, and a computer program, wherein the processor is coupled to the memory, the computer program is stored in the memory, and when the electronic device is operated, the processor executes the computer program stored in the memory to cause the electronic device to execute instructions for implementing the urban rail transit construction safety coupling risk factor identification method according to any of claims 1-6.

Description

Urban rail transit construction safety coupling risk factor identification method and system Technical Field The invention relates to the technical field of building construction safety risk identification, in particular to a method and a system for identifying coupling risk factors for urban rail transit construction safety. Background Urban rail transit construction safety remains a critical challenge for industry worldwide. Despite significant advances in security management systems, accidents continue to occur and often not due to a single cause, but rather from complex couplings and interactions between multiple risk factors. Traditional risk analysis relies primarily on statistical methods and expert judgment to identify individual factors such as human error, equipment failure, or environmental conditions. However, these methods often have difficulty revealing potential associations between these factors and risk propagation paths. To address this limitation, data driven technology is increasingly gaining importance. Association rule mining, and in particular Apriori algorithms, have been effectively applied to mining frequent patterns in accident data. Meanwhile, complex network theory is also a powerful tool for describing system interaction relations and identifying key nodes in multiple security fields. In recent years, some studies have begun to attempt to integrate these two approaches. For example, students use association rules to mine generation rules and build networks to visualize risk factor relationships in occupational safety and tunnel construction safety, and research uses weighted network analysis methods to prioritize construction project risks. Despite the above advances, there is still a significant research gap. Firstly, most of applications based on association rule mining in the existing security field still depend on the traditional frequency class index (support degree and confidence degree), and the key dimension of the severity of the accident result is ignored. Second, although existing network models are built, the methodology of systematically mapping association rules into weighted directed complex networks for analysis of construction risk factor coupling relationships is still imperfect. There are few studies combining association rule mining introducing accident severity weight with analysis methods based on network topology centrality to quantitatively identify and rank single and coupled risk factors. Disclosure of Invention The invention aims to provide a method and a system for identifying security coupling risk factors for urban rail transit construction, which aim to solve at least one technical problem in the background technology. In order to achieve the above purpose, the present invention adopts the following technical scheme: in a first aspect, the invention provides a method for identifying security coupling risk factors for urban rail transit construction, which comprises the following steps: The method comprises the steps of constructing a risk factor set and an accident data set, wherein, based on building construction safety related specifications, standards and accident reports, a risk factor set covering five types of risk factors including personnel, equipment, materials, management and environment is established, a construction accident report is acquired, accident cause and accident result information is extracted to form an accident sample data set comprising the risk factors and the accident result; introducing accident consequence weights on the basis of an Apriori algorithm, calculating weighted support, weighted confidence and weighted lifting degree, and mining the coupling relation among risk factors; the association rules are mapped into nodes and edges in the complex network, the nodes represent risk factors or a combination of the risk factors, the edge weights represent weighted confidence degrees, and the hub nodes and key coupling risk factors in the complex network are determined based on the node degrees and the proximity centrality. As a further limitation of the first aspect of the invention, an Apriori algorithm taking the severity of the accident result into consideration is used for mining the association relation among different risk factors and coupling risk factors, and the weighted support degree and the weighted confidence degree are defined as follows: ; ; ; Wherein, the Is a risk factorIs a weighted support of (1); Is the first The weight value of the individual risk factors,Is the firstThe number of injuries reported by the accident where the individual risk factors are located,Is the firstThe number of deaths reported from the incident in which the individual risk factors are located,Is the firstThe economic loss reported by the accident where the individual risk factors are located,Respectively setting weight values for experts; as a matrix of risk factors, Represent the firstAnd reporting the accident. As a further