基于使用行为的电动汽车驾驶员里程焦虑模型

doi:10.3969/j.issn.1674-8484.2021.02.011

汽车安全与节能学报 ›› 2021, Vol. 12 ›› Issue (2): 226-231.DOI: 10.3969/j.issn.1674-8484.2021.02.011

基于使用行为的电动汽车驾驶员里程焦虑模型

李宗华(), 翟钧, 王贤军, 马明泽, 刁冠通

重庆长安新能源汽车科技有限公司,重庆 401133,中国

收稿日期:2020-12-23 出版日期:2021-06-30 发布日期:2021-06-30
作者简介:李宗华（1981—）,男(汉),重庆,高级工程师。 E-mail: lizh3@changan.com.cn
基金资助:
国家科技部重点项目(2018YFB0106104);重庆市科技局项目(cstc2019jscx-mbdxX0029)

Electric vehicle driver’s range anxiety model based on use behavior

LI Zonghua(), ZHAI Jun, WANG Xianjun, MA Mingze, DIAO Guantong

Chongqing Changan New Energy Automobile Technology Co. LTD , Chongiqng 401133, China

Received:2020-12-23 Online:2021-06-30 Published:2021-06-30

摘要/Abstract

摘要：

研究了纯电动汽车用户里程焦虑对用户使用行为的影响。提出了一种基于车联网大数据用户使用行为的里程焦虑程度判定模型。运用Kernal K-means聚类算法,分析了用户的里程焦虑差异在充电频次、起止充电状态（SOC）、极限使用行为等工况的不同表现,采用逻辑回归算法,建立里程焦虑分类识别模型;通过评分卡方法,把逻辑回归模型输出的焦虑概率转换成里程焦虑等级;采用调查问卷方式,对模型准确性与普遍性进行了实例验证。结果表明：所建立的模型预测准确率为95.6%,能够有效判定用户的里程焦虑程度。若与其它分析维度整合,该方法可对电动汽车用户进行大数据画像分析。

关键词: 电动汽车(EV), 驾驶员里程焦虑, 大数据分析, 使用行为, 充电状态（SOC）, 聚类算法

Abstract:

A judgment model of range anxiety degree was proposed based on user behavior of big data of Internet of Vehicles to investigate the influence of range anxiety on user behavior of pure Electric Vehicle (EV). Kernal K-means clustering algorithm was used to analyze the different performance of users’ range anxiety differences in charging frequency, start-stop state of charging (SOC), extremely use behavior, etc. Logical regression algorithm was used to establish the classification and recognition model of range anxiety. The probability of anxiety output by logistic regression model was converted into range anxiety grade by scoring card method. The accuracy and universality of the model were verified via questionnaire. The results show that the prediction accuracy of the model is 95.6%. Therefore, this model can effectively determine the extent of users’ range anxiety, and can be used for big data portrait analysis of EV users if integrated with other analytical dimensions.

Key words: electric vehicle (EV), driver’s range anxiety, big data analysis, use behavior, state of charge (SOC), clustering algorithm

中图分类号:

U461.91

李宗华, 翟钧, 王贤军, 马明泽, 刁冠通. 基于使用行为的电动汽车驾驶员里程焦虑模型[J]. 汽车安全与节能学报, 2021, 12(2): 226-231.

LI Zonghua, ZHAI Jun, WANG Xianjun, MA Mingze, DIAO Guantong. Electric vehicle driver’s range anxiety model based on use behavior[J]. Journal of Automotive Safety and Energy, 2021, 12(2): 226-231.

图/表 11

图1 在不同里程内的用户充电分布

图2 充电起止SOC时用户分布分析

图3 每次充电行驶的里程的用户分布

图4 极限充放电行为占比的用户分布

图5 焦虑聚类分析

Info值	预测能力
≤0.03	无
0.03~0.10	低
0.10~0.30	中
0.03~0.50	高
≥0.5	极高

表1 5值预测能力

图6 逻辑回归模型识别的ROC曲线和AUC值

等级	人数	占比/%
A	9 486	18.74
B	16 608	32.81
C	12 378	24.45
D	5 044	9.96
E	7 110	14.04
总计	50 626	100.00

表2 平台用户里程焦虑等级分布

图7 A等级焦虑群体用户画像

图8 某用户画像

等级	模型判定人数	问卷数据人数	差异数
A	55	52	3
B	87	91	4
C	64	62	2
D	24	26	2
E	42	41	1
合计	272	272	12

表3 2种方式判定结果对比

参考文献 13

[1]	China Association of Automobile Manufacturers. Summary of production and marketing of automobile industry in December 2020[EB/OL]. (2021-01-13). http://www.caam.org.cn/chn/4/cate_30/con_5232919.html. (in Chinese)
[2]	肖向良, 毛盈方, 黄奕浩. 基于统计分析的城市道路驾驶行为特性研究[J]. 科技信息, 2014(5):104-105.
	XIAO Xiangliang, MAO Yingfang, HUANG Yihao. Research on driving behavior characteristics of urban road based on statistical analysis[J]. Sci Tech Info, 2014(05):104-105. (in Chinese)
[3]	Rauh N, Franke T, Krems J F. Understanding the impact of electric vehicle driving experience on range anxiety[J]. Human Factors, 2015,57(1):177-187. doi: 10.1177/0018720814546372 URL
[4]	谢驰, 白婷, 王同根. 里程焦虑下的电动汽车交通网络均衡[J]. 中国科技论文, 2017,12(19):2161-2165, 2171.
	XIE Chi, BAI Ting, WANG Tonggen. Equilibrium of electric vehicle transportation network under mileage anxiety[J]. Chin Sci Papers, 2017,12(19):2 161-2165, 2171. (in Chinese)
[5]	王涛. 考虑里程焦虑的电动汽车充电站选址模型[D]. 大连: 大连理工大学, 2016.
	WANG Tao. Location model of electric vehicle charging station considering mileage anxiety[D]. Dalian:Dalian University of Technology, 2016. (in Chinese)
[6]	Dhillon I S, Guan Y, Kulis B. Kernel k-means: Spectral clustering and normalized cuts[C]// Proc tenth ACM SIGKDD Int’l Conf’ Knowledge Discovery and Data Mining. 2004: 551-556.
[7]	Zaki M J, Meira Jr W, Meira W. Data Mining and Analysis: Fundamental Concepts and Algorithms [M]. Cambridge: Cambridge University Press, 2014: 147-148.
[8]	Joanes D N. Reject inference applied to logistic regression for credit scoring[J]. IMA J Manag Math, 1993,5(1):35-43. doi: 10.1093/imaman/5.1.35 URL
[9]	Gestel T V, Baesens B, Garcia J, et al. A support vector machine approach to credit scoring[J]. Bank- en Financiewezen, 2003,2:73-82.
[10]	West D. Neural network credit scoring models[J]. Computers Oper Res, 2000,27(11-12):1131-1152. doi: 10.1016/S0305-0548(99)00149-5 URL
[11]	Henley W E. Construction of a k-nearest neighbour credit-scoring system[J]. IMA J Manag Math, 1997,8(4):305-321. doi: 10.1093/imaman/8.4.305 URL
[12]	ZOU Xiaonan, HU Yong, TIAN Zhewen, et al. Logistic Regression Model Optimization and Case Analysis[C]// 2019 IEEE 7th Int’l Conf Computer Sci Network Tech (ICCSNT), IEEE, 2019: 135-139.
[13]	Sperandei S. Understanding logistic regression analysis[J]. Biochemia Medica, 2014,24(1):12-18.

基于使用行为的电动汽车驾驶员里程焦虑模型

Electric vehicle driver’s range anxiety model based on use behavior

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 13

相关文章 11

编辑推荐

Metrics

本文评价

期刊信息

在线期刊

作者中心

审稿中心

联系我们

[1]	董振鹏, 祖炳锋, 周建伟, 徐佳晨. 基于交通信息的电动汽车制动策略及仿真[J]. 汽车安全与节能学报, 2021, 12(1): 35-42.
[2]	谢辉, 张宁. 基于参数自适应的电动汽车整车质量辨识算法[J]. 汽车安全与节能学报, 2019, 10(2): 219-225.
[3]	许万，周大永. 三元锂离子动力电池挤压损伤容限的试验研究[J]. JASE, 2019, 10(1): 106-111.
[4]	方健，史国宏. 电动汽车全新架构前期开发中的多学科集成优化设计[J]. JASE, 2019, 10(1): 112-118.
[5]	宋雯，张欣*，田毅，席利贺. 基于运行工况识别及充电管理的E-REV 智能控制策略[J]. JASE, 2016, 07(02): 224-229.
[6]	张俊智，吕辰，李禹橦. 电动汽车混合驱动与混合制动系统——现状及展望[J]. 汽车安全与节能学报, 2014, 5(03): 209-223.
[7]	[ 德国] 亨宁·瓦伦托维兹. 汽车工程的创新——展望未来（英文）[J]. 汽车安全与节能学报, 2013, 4(2): 95-108.
[8]	袁昊, 王丽芳, 王立业. 基于液体冷却和加热的电动汽车热管理系统[J]. 汽车安全与节能学报, 2012, 3(4): 371-380.
[9]	朴昌浩, 覃丹丹, 段志辉, 陈平, 刘冬群. 电动汽车动力电池的生态系统——性能、成本及市场[J]. 汽车安全与节能学报, 2011, 2(3): 192-197.
[10]	王颖男, Uwe SCHAEFER. Adaptive Control of IPMSM Considering Parameter Variation for Electric Vehicle[J]. 汽车安全与节能学报, 2011, 2(3): 237-245.
[11]	陈清泉. 电动汽车、混合动力汽车和燃料电池汽车的发展前景(英文)[J]. 汽车安全与节能学报, 2011, 2(1): 12-24.