基于贝叶斯网络的双车道公路风险性分析  

Analysis of Two-lane Highway Traffic Risk Based on Bayesian Network

作　　者：袁黎[1] 于俊俊 吴梦倩[1] 蔡明杰[1] 

机构地区：[1]河海大学土木与交通学院,江苏南京210098

出　　处：《公路工程》2016年第2期99-103,共5页Highway Engineering

基　　金：国家自然科学基金项目资助(51308192)

摘　　要：双车道公路是我国公路网的重要组成部分,对其进行风险性分析能有效降低交通事故风险。在分析道路风险产生因素的基础上,构建了双车道公路风险评估指标体系,根据贝叶斯网络理论构建贝叶斯网络拓扑结构,再结合大量事故数据,采用EM算法确定了节点的条件概率表,最终建立了基于贝叶斯网络的风险评估模型。通过对模型进行等级划分,证明了该风险评估方法的有效性。Two-lane highway is an important part of China＇s highway network. A risk assessment on the two-lane highway can effectively reduce risk. Based on the analysis of the factors of risk on the road,the author builds a two-lane highway risk assessment index system. Bayesian network theory is introduced on the risk assessment of two-lane highway. On this basis,a Bayesian network topology of two-lane highway is built,combining with a large number of accident data,the node＇s conditional probability tables are determined by using the EM algorithm. The eventual establishment of a risk assessment model is based on Bayesian network. Finally,the risk level of two-lanel highway was defined,which proves the effectiveness of the risk assessment methodology.

关 键 词：双车道公路 风险 贝叶斯网络 交通安全 

分 类 号：U491.4[交通运输工程—交通运输规划与管理]