基于文本挖掘的城镇燃气事故致因及关联分析

Causes and correlation analysis of urban gas accidents based on text mining

为有效预防城镇燃气事故发生,采用文本挖掘与复杂网络理论相结合的方法,系统分析影响城镇燃气安全的事故致因及其关联性。首先运用文本挖掘技术,从2017—2021年间的1256份燃气事故案例中提取城镇燃气事故致因因素,采用Apriori算法挖掘城镇燃气事故致因的关联规则,共得到49条强关联规则;然后基于共现矩阵构建事故致因网络图,通过度中心性、紧密中心性、介数中心性分析,明确燃气事故的关键致因项和事故致因集合。研究结果表明:管道破损,阀门未关,设备老化,操作、使用不当和软管破损、脱落是城镇燃气事故关键致因因素,气体泄漏是燃气事故常见的事故类型,主要与管道破损、阀门未关等具有强关联性。

In order to effectively prevent the occurrence of urban gas accidents,the causes of accidents affecting urban gas safety and their relevance were systematically analyzed by using the research method of text mining and complex network theory.Firstly,text mining technology was used to extract the causative factors of urban gas accidents from 1256 gas accident cases from 2017 to 2021,and the Apriori algorithm was used to mine the association rules of urban gas accident causes,and 49 strong association rules were obtained.Then the accident cause network diagram was constructed based on the co-occurrence matrix,and the key causes and accident cause sets of gas accidents were identified through the analysis of degree centrality,compact centrality and intermediary centrality.The research results show that pipeline damage,valve opening,equipment aging,improper operation and use,hose damage and shedding are the key causes of urban gas accidents,and gas leakage is a common type of gas accident.It is mainly related to pipeline damage,valve failure and so on.