多因素动态瞬变下高速公路交通安全风险预测  

Prediction of Highway Traffic Safety Risk Under the Dynamic Transient Characteristics of Multi-factors

作　　者：崔航 涂辉招[1] 王晓峰[2] 吴兵[1] CUI Hang;TU Huizhao;WANG Xiaofeng;WU Bing(Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Tongji University,Shanghai 201804,China;Research Institute of Shanghai Meteorological Science,Shanghai 200030,China)

机构地区：[1]同济大学道路与交通工程教育部重点实验室,上海201804 [2]上海市气象科学研究所,上海200030

出　　处：《交通与运输》2019年第5期23-27,共5页Traffic & Transportation

基　　金：上海市科委重点计划(17DZ1205302)。

摘　　要：我国高速公路在交通流、不良天气、大车混入率等多因素随机动态瞬变影响下,交通安全风险隐患大。如何表征多因素动态瞬变性对交通安全风险的影响、预测短时间内风险变化,是有效采取风险预警管控措施的关键。利用BP神经网络,考虑多因素影响,提出了基于"建议车速-预期车速"模型的交通安全风险预测方法,并通过案例分析验证了预测方法的可靠性与适用性,研究结果为有效遏制高速公路事故提供技术支撑。Under the influence of random,dynamic and transient characteristics of multi-factors such as traffic flow,adverse weather conditions and large vehicle composition,traffic safety risks on Chinese highways are serious.How to characterize the impacts of multi-factor dynamic transients on traffic safety risks and to predict safety risk changes in a short period of time is the key issue for effective risk control measures.Considering the effects of multi-factors,a traffic safety risk prediction method based on"dynamic speed-limit&expected speed"is proposed by using BP neural network.Meanwhile,the reliability and applicability of the prediction method is verified by empirical case studies.Research results can provide technical support for effectively preventing highway accidents.

关 键 词：交通安全 风险预测 多因素动态瞬变 建议车速-预期车速 BP神经网络 

分 类 号：U491[交通运输工程—交通运输规划与管理]