基于模糊贝叶斯网络的高速公路营运客车运行风险评估  

Risk Assessment of Freeway Operating Buses Based on Fuzzy Bayesian Network

作　　者：程国柱 米亚宁 别一鸣[2] CHENG Guozhu;MI Yaning;BIE Yiming(School of Civil Engineering and Transportation,Northeast Forestry University,Harbin 150040,China;School of Traffic and Transportation,Jilin University,Changchun 130022,China)

机构地区：[1]东北林业大学土木与交通学院,黑龙江哈尔滨150040 [2]吉林大学交通学院,吉林长春130022

出　　处：《大连交通大学学报》2024年第4期33-40,共8页Journal of Dalian Jiaotong University

基　　金：吉林省科技发展计划项目(20210203214SF)。

摘　　要：为评估高速公路营运客车运行风险,运用模糊贝叶斯网络,提出了一种基于GPS数据的高速公路营运客车运行风险评估方法。确定高速公路营运客车运行两大类风险因素及具体表征风险评估指标,利用GeNIe软件构建高速公路营运客车运行风险的贝叶斯网络拓扑结构。建立安全、较安全、较危险和危险4个等级的评价集,采用降半梯形分布函数计算隶属度并构建隶属度矩阵,确定了隶属度到概率的转换公式,最后使用GeNIe软件对高速公路营运客车运行风险结果进行推理计算,并依据最大隶属原则确定其风险等级。结果表明,该评估模型实现了高速公路营运客车运行风险量化分级评价,识别了安全性较差路段,并以G12珲乌高速吉林至长春龙嘉机场段为实例,验证了该评估方法的有效性。In order to evaluate the operation risk of freeway operating buses,a method based on GPS data is proposed by using fuzzy Bayesian network.Two types of risk factors and specific risk assessment indexes were determined,and the Bayesian network topology of the risk was constructed by using GeNIe software.The evaluation set of four levels of safe,relatively safe,dangerous and relatively dangerous was established,membership degree was calculated,membership degree matrix was constructed by using the reduced half ladder distribution function,and the transformation formula from membership degree to probability was determined.Finally,the operation risk results of freeway operating buses were calculated by using GeNIe software,and the risk level was determined according to the principle of maximum membership.The results show that the evaluation model can realize the quantitative,grade evaluation of the operation risk of operating buses on freeways and identify the sections with poor safety.The example of G12 Hui Wu Freeway section from Jilin to Changchun Longjia Airport verifies the effectiveness of the evaluation method.

关 键 词：交通工程 运行风险评估 模糊贝叶斯网络 高速公路 营运客车 

分 类 号：U492.8[交通运输工程—交通运输规划与管理]