基于贝叶斯网络的罐式汽车运输风险分析  

Risk Analysis of Tank Vehicle Transportation Based on Bayesian Network

作　　者：陈琳[1] 谢学飞[1] 

机构地区：[1]长安大学

出　　处：《汽车工程师》2016年第2期44-46,58,共4页Automotive Engineer

基　　金：国家"八六三"子项目;重型商用车底盘(2014A0310154)

摘　　要：罐式汽车是液体和气体危险货物道路运输的主要承载工具,危险货物一旦发生泄漏,将对周围环境以及居民的生命财产安全造成严重影响。为了找到引起事故发生的最可能因素,文章采用贝叶斯网络对可能导致事故发生的所有因素进行分析,建立故障树模型,然后将其转化为贝叶斯网络;由886起罐式汽车公路运输危险货物事故统计结果得到贝叶斯网络中的先验概率,根据故障树与贝叶斯网络的转换关系得到条件概率,据此计算事故发生概率并找到导致事故发生的最可能因素,进而在运输过程中加以防范,减少事故的发生。计算分析结果表明,该方法可以提高故障分析的有效性,且具有一定的理论性和实际应用价值。Tank vehicles are major tools for carrying liquids,gases and other dangerous goods by road transportation. Once the leakage occurred, it would have a serious impact on the environment, the lives and property of the residents. In order to analyze the accident and find the most likely cause of the accident, using Bayesian network to analyze the factors that likely cause the accident, building a fault tree and making a fault tree mapping into Bayesian network. The prior probability of Bayesian network was obtained from accident statistical results of tank vehicle on the road transportation of dangerous goods, and the conditional probability was got from the conversion of the fault tree and Bayesian network. Bayesian network was used to calculate the probability of the accident and determine which factors are most likely to cause the accident, finally take some measures to prevent and reduce accident. The computing analysis showed that the combination of fault tree to Bayesian network can improve the efficiency of the fault analysis. The tank vehicle transportation risk analysis has certain rationality theory and practical application value.

关 键 词：罐式汽车 危险货物 故障树 贝叶斯网络 事故分析 

分 类 号：U492.8[交通运输工程—交通运输规划与管理]