基于数据挖掘的高速公路货车交通事故影响因素关联分析研究  

Correlation Analysis of Influencing Factors of Truck Traffic Accidents on Expressways

作　　者：牛毅 李振明[2] 樊运晓[1] NIU Yi;LI Zhenming;FAN Yunxiao(School of Engineering & Technology,China University of Geosciences(Beijing),Beijing 100083,China;Department of Safety Science and Engineering,Zhejiang University of Technology,Hangzhou 310023,China)

机构地区：[1]中国地质大学(北京)工程技术学院,北京100083 [2]浙江工业大学安全科学与工程系,浙江杭州310023

出　　处：《安全与环境工程》2020年第4期180-188,共9页Safety and Environmental Engineering

基　　金：国家自然科学基金项目(51674224)。

摘　　要：为深入挖掘高速公路货车交通事故影响因素间的复杂关联关系,以2012—2017年浙江省辖区内高速公路37万起货车交通事故数据为样本数据,基于社会网络分析法、Apriori关联算法和可视化等数据挖掘技术,构建从宏观到具体的详细关联规则挖掘流程,实现对浙江省内高速公路货车交通事故发生时间、事故形态、事故地点(桩号)和事故原因等七类事故影响因素间关联关系的深层次分析。结果表明:高速公路货车交通事故的时空分布规律显著;不同路段在安全状况、事故原因和事故发生时间上的差异性很大;死亡事故多发于凌晨时段,且多由疲劳驾驶引发;高速交通数据采集系统需进一步完善。针对事故多发路段、疲劳驾驶、车辆安全监管等热点问题,结合高速公路一线交警及管理部门的实践经验和迫切需求,提出了具有针对性的事故预防及安全管理对策与建议措施。In order to deeply explore the complex association relationship between the influencing factors of truck accidents on expressways,this paper takes the data of 370 thousand truck traffic accidents on expressways in Zhejiang Province from 2012 to 2017 as samples.Using social network analysis,Apriori algorithm and visualization technology,the paper constructs a detailed association rules mining process from macro to specific,so as to realize the in-depth analysis of the association relationship among the seven types of factors influencing the truck traffic accidents on expressways,such as the accident occurrence time,accident pattern,accident location(stake number)and accident cause,etc.The results show that the spatial-temporal distribution of truck traffic accidents is significant;there are great differences in safety conditions,accident causes and accident occurrence time in different sections;fatalities often occur in the early hours of the morning,and most of them are caused by fatigue driving;the highway traffic accident data acquisition system should be further improved.In view of key issues such as accident blackspot,fatigue driving and vehicle safety supervision,the paper puts forward targeted suggestions and measures of accident prevetion and safety management based on the practical experience and urgent needs of expressway traffic police and management departments.

关 键 词：高速公路 货车交通事故 影响因素 数据挖掘 关联分析 Apriori关联算法 

分 类 号：X928[环境科学与工程—安全科学]