摘要
影响加油站安全的各因素间的作用关系难以定量描述。系统梳理了加油站事故案例并提取关键信息,深入挖掘危险因素间逻辑关系。基于Apriori算法对加油站危险因素关联规则进行了挖掘分析及定量研究。首先对71起加油站典型安全生产事故的属性结构进行分析并建立了人、物、管的元数据框架;其次采用Apriori算法从多维分析角度对加油站事故的危险因素进行了规则挖掘,并对危险因素关联作用规律进行了定量分析;最后根据关联规则挖掘及定量分析结果,从事故属性和事故致因间提取了不同属性与致因间的重要关联规则,挖掘出三个维度共32条强关联规则,直观地展现出加油站事故中各危险因素间的内在联系,克服了面对大量语义信息难以人为全面定量分析的难题。
There are many kinds of factors that affect the safety of gas stations,and it is difficult to describe the relationship between them quantitatively.It is necessary to systematize the cases of gas station accidents,extract the key information,and dig out the logic relationship among the risk factors.In this paper,based on Apriori algorithm to gas station risk factors association rules mining analysis and quantitative research.Based on the analysis of accident attribute structure,a metadata framework of human,material and management was established.Secondly,the Apriori algorithm is used to mine the risk factors of gas station accidents from the angle of multi-dimensional analysis,and the association RULES OF RISK factors are Quantitative analysis.Finally,according to the association rule mining and quantitative analysis results,the important association rules between different attributes and causes are extracted from the accident attributes and causes,and 32 strong association rules in three dimensions are discovered,which visually shows the internal relationship among the risk factors in gas station accidents,and overcomes the difficulties of artificial quantitative analysis in the face of a large amount of semantic information.
作者
康健
王庆梓
张继信
代濠源
KANG Jian;WANG Qingzi;ZHANG Jixin;Dai Haoyuan(Beijing Institute of Petrochemical Technology,Beijing 102617,China)
出处
《北京石油化工学院学报》
2023年第2期62-67,共6页
Journal of Beijing Institute of Petrochemical Technology
基金
国家自然科学基金青年基金(71901029)
北京市教委科技计划项目(KM202010017009)。
