基于AHP-Apriori改进算法的山区公路运营风险辨识  

Risk Identification of Operation on Mountainous Roads Based on Improved AHP-Apriori Algorithm

作　　者：柳本民[1] 邓润竹 LIU Benmin;DENG Runzhu(Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Tongji University,Shanghai 201804,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

出　　处：《交通与运输》2022年第3期27-31,共5页Traffic & Transportation

摘　　要：山区公路地理位置特殊,管理难度较大。应用数据挖掘技术对已有山区公路事故数据进行关联规则挖掘,分析其影响,对集中管理资源提升公路运营安全具有重大意义。针对事故影响因素种类繁多、影响程度难以界定等问题,建立采用层次分析法加权的改进Apriori算法,对山区公路事故关联规则进行研究,优化该算法的基本思想和流程。选取某山区二级公路2011—2017年的事故数据进行详细分析,并基于Python语言实现改进算法,输出一般到重大事故等级与车辆类型、碰撞方向和天气之间的关联规则结果,为山区公路事故危害等级划分、风险辨识、优化管理资源配置等提供重要的参考依据。Mountainous roads are geographically unique and difficult to manage.Therefore,applying data mining techniques to existing mountainous road accident data for association rule mining and analysis of its impact is of great significance to centralize management resources to improve road operation safety.To address the problems of a wide variety of accident influencing factors and the difficulty of defining the degree of influence,an improved Apriori algorithm using hierarchical analysis weighting is established.The accident data of a mountainous secondary road from 2011 to 2017 are selected for detailed analysis and improved algorithms are implemented based on Python language to output the results of association rules between general to major accident levels and vehicle type,collision direction,and weather,which provide an important reference basis for accident hazard classification,risk identification and optimal management resource allocation of mountainous roads.

关 键 词：山区公路 风险辨识 加权关联规则 APRIORI算法 交通事故等级 

分 类 号：U491[交通运输工程—交通运输规划与管理]