驾驶风格K-means聚类与识别方法研究  

Research on Methods of K-means Clustering and Recognition for Driving Style

作　　者：李经纬 赵治国[1] 沈沛鸿 郭秋伊 Li Jingwei;Zhao Zhiguo;Shen Peihong;Guo Qiuyi(Clean Energy Automotive Engineering Center,Tongji University,Shanghai 201804)

机构地区：[1]同济大学新能源汽车工程中心,上海201804

出　　处：《汽车技术》2018年第12期8-12,共5页Automobile Technology

基　　金：国家自然科学基金项目(51275355)

摘　　要：驾驶风格用来表征驾驶员在实车运行环境中对车辆操作的行为特征,对于混合动力汽车能量经济性有较大影响,为提高驾驶风格识别方法在不同车型上的通用性与适应性,提出了基于K-means聚类的驾驶风格识别方法。针对采集的不同驾驶员所驾驶的商用车和乘用车的行驶数据,利用该识别方法分别进行了驾驶风格的识别,结果表明,将驾驶风格聚为3类具有较好的分类效果,并且该方法对商用车和乘用车均具有较好的识别效果。The driving style reflects the behavior characteristic of the driver operating the vehicle in real driving environment,which has huge impact on the energy economy of hybrid electric vehicles.To improve the versatility and applicability of driving style recognition method on different vehicle models,a driving style recognition method based on Kmeans clustering was proposed.With driving data of commercial vehicles and passenger cars operated by different drivers,this method was used to recognize driving style.The results show that the driving styles classified into three categories have good classification effect,and this method has good recognition effect on both commercial vehicles and passenger cars.

关 键 词：驾驶员 驾驶风格 K-MEANS聚类 识别 HEV 

分 类 号：U461[机械工程—车辆工程] TP391.6[交通运输工程—载运工具运用工程]