基于贝叶斯网络的城市地下燃气管网动态风险分析

Dynamic risk analysis of urban buried gas pipeline network based on Bayesian network

为研究城市燃气管网风险的动态性,针对传统风险分析方法的局限性,提出基于贝叶斯网络的燃气管网动态风险分析方法。构建燃气管网失效蝴蝶结模型并将其转化为贝叶斯网络模型;在事故发生状态下更新事件失效概率,识别出关键因素;根据异常事件数据和贝叶斯理论,对基本事件失效概率进行实时动态改变;随之更新管网失效及各后果发生的概率,从而实现管网的动态风险分析。研究结果表明:该方法克服了传统风险分析方法的不足,可动态反映燃气管网失效和事故后果发生概率随时间变化的特征,能够为城市地下燃气管网的风险分析与事故预防提供参考。

In order to study the dynamic characteristic of the risk of urban gas pipeline network,aiming at the limitation of traditional risk analysis methods,a dynamic risk analysis method of gas pipeline network based on the Bayesian network was proposed. A Bow-tie model on the failure of gas pipeline network was established and converted into the Bayesian network model,then the failure probabilities of events were updated in case of accident,and the key factors were identified. According to the data of abnormal events and the Bayesian theory,the real-time and dynamic change of the failure probabilities of basic events was carried out. Subsequently,the probabilities of pipeline network failure and each consequence were updated,thus the dynamic risk analysis of pipeline network was realized. The results showed that the method overcomes the shortcomings of traditional analysis methods,which can reflect the dynamic change characteristics of the probabilities of gas pipeline network failure and accident consequence with time,and provide reference for the risk analysis and accident prevention of urban buried gas pipeline network.