聚类分析法在城市公交行驶工况开发中的应用  

Application of Cluster to Development of City Bus Driving Cycle

作　　者：董恩源[1] 颜文胜[1] 申江卫[1] 李江波[1] 

机构地区：[1]昆明理工大学交通工程学院,云南昆明650224

出　　处：《昆明理工大学学报（自然科学版）》2013年第5期41-44,51,共5页Journal of Kunming University of Science and Technology(Natural Science)

基　　金：国家863高技术研究发展计划(2009AA11A114);昆明市重大科技计划项目(10G030002)

摘　　要：针对昆明市161路混合动力公交客车实际行车数据,使用K-Means聚类分析法对运动学片段进行了分类,并构建了161路的行驶工况.研究表明:K-Means聚类分析法获得的两类运动学片段特征明显,分别反映了较为通畅和十分拥堵的交通状况;构建的行驶工况可以代表161路的实际行驶工况,具有怠速时间长、平均车速低、加减速所占比例高和车辆启停频繁的特点.Aiming at the practical driving data of 161 hybrid city bus in Kunming, the kinematic sequences are classified and its driving cycle is built by k-Means cluster methodology. It is shown clearly through the study that the characteristics of two groups of kinematic sequences obtained by classification are very distinctively, and the traffic conditions of congested road and unobstructed road are reflected by these two groups respectively. With its several characteristics, such as long idling time, low average speed, high proportion of acceleration and deceler- ation, and frequently start-stop, the driving cycle built by k-Means cluster methodology is able to represent the actual driving cycle of the bus.

关 键 词：行驶工况 K—Means聚类分析法 混合动力 公交客车 

分 类 号：U46[机械工程—车辆工程]