主办:陕西省汽车工程学会
ISSN 1671-7988  CN 61-1394/TH
创刊:1976年

汽车实用技术 ›› 2022, Vol. 47 ›› Issue (13): 15-20.DOI: 10.16638/j.cnki.1671-7988.2022.013.005

• 智能网联汽车 • 上一篇    

基于车联网数据的电动汽车驾驶评价应用

李宗华 1,翟 钧 1,王贤军 1,吴 炬 1,贺小栩 1,黄 晶 2   

  1. 1.重庆长安新能源汽车科技有限公司;2.重庆长安汽车股份有限公司
  • 出版日期:2022-07-15 发布日期:2022-07-15
  • 通讯作者: 李宗华
  • 作者简介:李宗华(1981-),男,硕士,高级工程师,研究方向为车联网大数据,E-mail:354153626@qq.com。
  • 基金资助:
    国家科技部重点项目(2018YFB0106104);重庆市科技局项目(cstc2019jscx-mbdxX0029)。

Application on Driving Evaluation of Electric Vehicles Based on Internet of Vehicles Data

LI Zonghua1 , ZHAI Jun1, WANG Xianjun1, WU Ju1 , HE Xiaoxv 1 , HUANG Jing2   

  1. 1.Chongqing Changan New Energy Automobile Technology Company Limited; 2.Chongqing Changan Automobile Company Limited
  • Online:2022-07-15 Published:2022-07-15
  • Contact: LI Zonghua

摘要: 新能源汽车相对于传统燃油车,在运行过程中采集了大量的行驶数据。通过对数据的 挖掘与分析,可以为用户的驾驶习惯和新能源汽车的研发提供参考。论文提出一种基于车联 网大数据的驾驶行为评价模型,旨在研究电动汽车用户的驾驶行为。首先分别从驾驶习惯、 安全系数、能量消耗维度进行分析和研究,然后构建并提取不同维度的特征变量,通过逻辑 回归分类模型和评分卡方法,分别输出驾驶习惯分数、安全性分数、能量消耗分数。最后进 行了实例应用验证,结果表明,所采用的的方法能有效评价用户实际的驾驶行为。

关键词: 电动汽车;车联网数据;大数据分析;驾驶评价;逻辑回归

Abstract: Compared with traditional fuel vehicles, new energy vehicles collect a large number of driving data during operation. Through data mining and analysis, it can provide reference for users' driving habits and the research and development of new energy vehicles. In this paper, a driving behavior evaluation model based on big data of Internet of vehicles is proposed to study the driving behavior of electric vehicle users. Firstly, the driving habit, safety factor and energy consumption are analyzed and studied respectively, and then the characteristic variables of different dimensions are constructed and extracted. Through the logistic regression classification model and scorecard method, the driving habit score, safety score and energy consumption score are output respectively. Finally, an example is applied to verify the results. The results show that the method used in this paper can effectively evaluate the actual driving behavior of users.

Key words: Electric vehicle; Internet of vehicles data; Big data analysis; Driving evaluation; Logistic regression