| 基于改进贝叶斯网络模型的高速公路交通设施风险评估 |
| |
| 引用本文： | 张道玉,胡晓伟.基于改进贝叶斯网络模型的高速公路交通设施风险评估[J].交通信息与安全,2016,34(5):102-107. |
| |
| 作者姓名： | 张道玉 胡晓伟 |
| |
| 作者单位： | 哈尔滨工业大学交通科学与工程学院 哈尔滨 150090 |
| |
| 基金项目： | 吉林省交通运输厅科技项目 |
| |
| 摘 要： | 交通设施对高速公路交通安全起着关键作用,对交通设施进行风险评估是预防交通事故的有效方法之一.为实现对高速公路交通设施风险的评估,分析了交通设施对交通安全的影响机理.通过因子分析法提取了各作用节点和作用网络,根据网络中各节点之间的关系,结合条件概率知识对贝叶斯公式进行了变形与推导,舍去无关变量和无影响常量,构建基于改进贝叶斯网络的高速公路交通设施风险评估模型.用高速公路历史事故数据对模型概率参数进行标定和校准之后,可将高速公路交通设施现状调查结果带入模型进行风险评估.模型计算得到的 值越小,高速公路交通设施风险越大.采用珲乌高速公路实地调查数据,带入模型分析发现,值小于0.5时,事故数相对较高,设施风险较大;值大于0.5时,设施风险较小.
|
| 关 键 词： | 交通安全 高速公路 交通设施 风险评估 贝叶斯网络模型 |
Risk Assessment of Traffic Facility on Freeway Based on a Modified Bayesian Network Model |
| |
| Abstract: | Traffic facilities play an important role in traffic safety.Assessing the risk of facilities on freeways is one of the effective methods to prevent traffic accidents.In order to evaluate the risk, this study analyzes the effects of facilities on freeway safety.The nodes and network are extracted by factor analysis.According to the relationship of nodes in a network, combined with probability theory (such as the conditional probability), this paper modifies the Bayesian formula after rounding off unrelated variables and no-effect constants, and establishes a modified Bayesian model for assessing facilities on freeways.With the traffic data of freeways and the result of a survey, the risk of facilities can be assessed.The results computed by the modified model show that the smaller the value, the higher the risk of freeway facilities.Using the data of Huiwu freeway to verify this proposed model, it shows that when the value is smaller than 0.5, the number of crashes is relatively larger, correspondingly, the risk of facilities is higher;otherwise, the risk of facilities is lower. |
| |
| Keywords: | |
|
| 点击此处可从《交通信息与安全》浏览原始摘要信息 |
|
点击此处可从《交通信息与安全》下载全文 |
|
