基于因子回归分析和分层雷达图法的电动汽车运行状态评估  

Electric vehicle operational status evaluation based on factor regression analysis and layered radar map method

作　　者：蒲松林[1] 周念成[2] 郭胤[1] 王强钢[2] 张静 李题印 

机构地区：[1]国网四川省电力公司遂宁供电公司,四川遂宁629000 [2]重庆大学输配电装备及系统安全与新技术国家重点实验室,重庆400044 [3]国网浙江杭州市余杭区供电公司,浙江杭州311100

出　　处：《电力自动化设备》2015年第6期44-51,共8页Electric Power Automation Equipment

基　　金：输配电装备及系统安全与新技术国家重点实验室自主研究项目(2007DA10512711209);国家自然科学基金资助项目(51277184)~~

摘　　要：为优化电动汽车的检修策略,有必要利用监测数据对其运行状态进行综合评估。选取蓄电池、电机传动和充放电过程的26个特征量作为电动汽车运行状态指标,利用因子分析法提取指标的公共因子,利用公共因子间的独立性对电动汽车状态指标进行分类;再结合逐步回归分析对各个分类的指标进行筛选,删除对评估结果影响小的指标,由此建立电动汽车运行状态综合评估指标体系。将针对电动汽车评估的层次递阶结构,采用分层雷达图法对电动汽车运行状态进行综合评估。根据某电动公交车充电站的监测数据进行计算,结果表明所提方法能够反映电动汽车各组成部分及整体运行状态,所提出的评估模型和方法是正确和有效的。In order to optimize the maintenance strategy of EV（Electric Vehicle）,its monitoring data are used to comprehensively evaluate its operating status. 26 eigenvalues of battery,motor transmission and charge/discharge process are selected as the EV operating status indexes and the factor analysis is applied to extract their common factors. The independency of common factors is used to classify the EV status indexes and the stepwise regression analysis is applied to screen out the indexes with little contribution to the evaluation results. A comprehensive evaluation index system of EV operating status is thus established. According to its hierarchical structure,the layered radar map is applied to comprehensively evaluate the operating status of EV. The monitoring data of an EV charging station are used and the calculative results show that,the operating status of an EV or its component can be properly reflected,proving the proposed method is correct and effective.

关 键 词：电动汽车 状态评估 指标选择 特征量 因子分析 雷达图 

分 类 号：TM61[电气工程—电力系统及自动化] U469.72[机械工程—车辆工程]