基于驾驶行为的纯电动汽车剩余续驶里程预测

doi:10.3901/JME.2025.04.262

机械工程学报 ›› 2025, Vol. 61 ›› Issue (4): 262-272.doi: 10.3901/JME.2025.04.262

• 运载工程 • 上一篇

扫码分享

基于驾驶行为的纯电动汽车剩余续驶里程预测

李骏¹, 李继秋¹, 孙亚诚¹, 单丰武^2,3, 曾建邦^1,3

1. 华东交通大学机电与车辆工程学院南昌 330013;
2. 同济大学汽车学院上海 201804;
3. 江西江铃集团新能源汽车有限公司南昌 330013

收稿日期:2024-05-26 修回日期:2024-10-07 发布日期:2025-04-14
作者简介:李骏，男，1969年出生，博士，教授。主要研究方向为新能源汽车、汽车安全与检测。E-mail：65770426@qq.com
李继秋，男，1999年出生。主要研究方向为新能源汽车大数据技术。E-mail：2020038080200016@ecjtu.edu.cn
曾建邦(通信作者)，男，1981年出生，博士，副教授。主要研究方向为新能源汽车大数据技术。E-mail：jbzeng68@sina.com
基金资助:
国家自然科学基金(51206171)、载运工具与装备教育部重点实验室基金(KLCE2021-08)、江西省自然科学基金(20192BAB206033)和江西省创新创业大学生训练计划省级重点(202110404029)资助项目。

Prediction of Remaining Mileage of Electric Vehicle Based on Driving Behavior

LI Jun¹, LI Jiqiu¹, SUN Yacheng¹, SHAN Fengwu^2,3, ZENG Jianbang^1,3

1. School of Electromechanical and Vehicle Engineering, East China Jiaotong University, Nanchang 330013;
2. School of Automobile Studies, Tongji University, Shanghai 201804;
3. New Energy Vehicle Corporation, Jiangxi Jiangling Motors Group, Nanchang 330013

Received:2024-05-26 Revised:2024-10-07 Published:2025-04-14

摘要/Abstract

摘要： 针对目前纯电动汽车在实际行驶过程中仪表显示剩余续驶里程预测不准这一难题，提出一种基于驾驶行为的纯电动汽车剩余续驶里程预测方法。首先，对车辆行驶数据进行片段切分并进行数据维度扩充，利用最大信息系数法提取与纯电动汽车平均百公里能耗相关的驾驶行为特征参量；然后，针对行驶片段数据探讨特征参量选取方式对K-Means聚类结果的影响，并将驾驶行为分类标签、电池荷电状态(State of charge, SOC)、行驶工况、温度等参数作为预测输入，使用BP和长短时间记忆(Long short-term memory, LSTM)网络模型分别对纯电动汽车行驶过程中剩余续驶里程进行预测，发现相比未考虑驾驶行为，考虑驾驶行为时模型预测结果与真实值之间的误差更小，且相比BP神经网络模型，LSTM网络模型预测结果与真实值之间的误差更小；最后，结合纯电动汽车实际行驶过程中的行驶数据对预测结果进行验证，发现原车剩余续驶里程预测准确度确定系数由0.853 9提高至0.982 2。所取得研究成果对提高纯电动汽车实际行驶过程中的剩余续驶里程预测准确度，减轻驾驶员里程焦虑具有重要的意义。

关键词: 纯电动汽车, 剩余续驶里程预测, 驾驶行为, 最大信息系数法, K-Means聚类算法

Abstract: Aiming at the problem of inaccurate prediction of remaining driving range of electric vehicle in actual driving process, a prediction method of remaining driving range of electric vehicle based on driving behavior is proposed. Firstly, segment the vehicle driving data and expand the data dimensions, and extract the driving behavior characteristic parameters related to the average energy consumption of 100 km of electric vehicles using the maximum information coefficient method; Then, based on the driving segment data, the influence of the selection method of characteristic parameters on the K-Means clustering results is discussed. With the driving behavior classification label, SOC, driving conditions, temperature and other parameters as the prediction input, BP and LSTM network models are used to predict the remaining driving range of the electric vehicle during driving. It is found that the error between the model prediction results and the real value is smaller when driving behavior is considered than when driving behavior is not considered, Compared with the BP neural network model, the error between the predicted results of LSTM network model and the true value is smaller; Finally, the prediction results are verified with the actual driving data of the electric vehicle, and it is found that the determination coefficient of the prediction accuracy of the remaining driving range of the original vehicle is increased from 0.853 9 to 0.982 2. The research results obtained in this study are of great significance to improve the prediction accuracy of the remaining driving range in the actual driving process of electric vehicles and reduce the driver's mileage anxiety.

Key words: electric vehicle, remaining driving mileage, driving behavior, maximum information coefficient algorithm, K-Means cluster algorithm

中图分类号:

U463

李骏, 李继秋, 孙亚诚, 单丰武, 曾建邦. 基于驾驶行为的纯电动汽车剩余续驶里程预测[J]. 机械工程学报, 2025, 61(4): 262-272.

LI Jun, LI Jiqiu, SUN Yacheng, SHAN Fengwu, ZENG Jianbang. Prediction of Remaining Mileage of Electric Vehicle Based on Driving Behavior[J]. Journal of Mechanical Engineering, 2025, 61(4): 262-272.

参考文献

[1] 邓忠伟，肖伟，李阳，等. 宏观时间尺度下的电动汽车循环里程预测[J]. 机械工程学报，2021，57(24):250-258. DENG Zhongwei，XIAO Wei，LI Yang，et al. Cycle mileage prediction of electric vehicle over macro timescale[J]. Journal of Mechanical Engineering，2021，57(24):250-258.
[2] 尹安东，赵韩，周斌，等. 基于行驶工况识别的纯电动汽车续驶里程估算[J]. 汽车工程，2014，36(11):1310-1315. YIN Andong，ZHAO Han，ZHOU Bin，et al. Driving range estimation for battery electric vehicles based on driving cycle identification[J]. Automotive Engineering，2014，36(11):1310-1315.
[3] 田慧欣，李晓宇，刘芳. 基于地图信息和循环SVR模型的纯电动汽车续驶里程预测[J]. 汽车工程，2020，42(9):1174-1182. TIAN Huixin，LI Xiaoyu，LIU Fang. Prediction of continued driving range of battery electric vehicle based on map information and cyclic svr model[J]. Automotive Engineering，2020，42(9):1174-1182.
[4] BI J，WANG Y，SAI Q，et al. Estimating remaining driving range of battery electric vehicles based on real-world data:A case study of Beijing，China[J]. Energy，2019，169(15):833-843.
[5] 李晓宇，陈炫锴，李嘉栩，等. 基于机器学习的电动汽车续航里程预测[J]. 电器与能效管理技术，2021(10):78-82，91. LI Xiaoyu，LI Xuankai，LI Jiaxu，et al. Driving range prediction of electric vehicles based on machine learning[J]. Electrical & Energy Management Technology，2021(10):78-82，91.
[6] 魏恒，何超，李加强，等. 基于实际行驶工况的纯电动汽车续驶里程在线估算方法研究[J]. 公路交通科技，2020，37(12):149-158. WEI Heng，HE Chao，LI Jiaqiang，et al. Study on method for online estimating driving range of battery electric vehicle based on actual driving cycle[J]. Journal of Highway and Transportation Research and Development，2020，37(12):149-158.
[7] BINGHAM C. Power/energy storage technologies and energy management[C]. The 3rd International Symposium on Adranced Engine Control Tecnology，2010.
[8] LARUSDOTTIR E B，ULFARSSON G F. Effect of driving behavior and vehicle characteristics on energy consumption of road vehicles running on alternative energy sources[J]. International Journal of Sustainable Transportation，2015，9(8):592-601.
[9] 佘承其，张照生，刘鹏，等. 大数据分析技术在新能源汽车行业的应用综述—基于新能源汽车运行大数据[J]. 机械工程学报，2019，55(20):3-16. SHE Chengqi，ZHANG Zhaosheng，LIU Peng，et al. Overview of the application of big data analysis technology in new energy vehicle industry:Based on operating big data of new energy vehicle[J]. Journal of Mechanical Engineering，2019，55(20):3-16.
[10] 喻文健. 数值分析与算法[M]. 北京:清华大学出版社，2012. YU Wenjian. Numerical analysis and algorithms[M]. Beijing:Tsinghua University Press，2012.
[11] 侯德藻，刘刚，李克强，等. 新型汽车主动避撞安全距离模型[J]. 汽车工程，2005，27(2):186-190. HOU Dezao，LIU Gang，LI Keqiang，et al. A new safety distance model for vehicle collision avoidance[J]. Automotive Engineering，2005，27(2):186-190
[12] RESHEF D N，RESHEF Y A，FINUCANE H K，et al. Detecting novel associations in large data sets[J]. Science，2011，334(6062):1518-1524.
[13] NIE F，XUE J，WU D，et al. Coordinate descent method for k-means[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，2021，44(5):2371-2385.
[14] ROUSSEEUW P J. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis[J]. Journal of Computational and Applied Mathematics，1987，20:53-65.
[15] 李萌，李洋，纪少波，等. 纯电动共享汽车驾驶行为对能耗的影响[J]. 吉林大学学报(工学版)，2022，52(4):754-763. LI Meng，LI Yang，JI Shaobo，et al. Influence of driving behavior on energy consumption of electric shared vehicles[J]. Journal of Jilin University(Engineering and Technology Edition)，2022，52(4):754-763.
[16] 刘阳，郜志英，周晓敏，等. 工业数据驱动下薄板冷轧颤振的LSTM智能预报[J]. 机械工程学报，2020，56(11):121-131. LIU Yang，GAO Zhiying，ZHOU Xiaomin，et al. Industrial data-driven intelligent forecast for chatter of cold rolling of thin strip with lstm recurrent neural network[J]. Journal of Mechanical Engineering，2020，56(11):121-131.
[17] 肖曦，田培根，于璐，等. 动力电池梯次利用储能系统电热安全研究现状及展望[J]. 电气工程学报，2022, 17(1):206-224. XIAO Xi，TIAN Peigen，YU Lu，et al. Status and prospect of safety studies of cascade power battery energy storage system[J]. Journal of Electrical Engineering，2022，17(1):206-224.
[18] 于仲安，陈可怡，张军令，等. 动力电池散热技术研究进展[J]. 电气工程学报，2022，17(4):145-162. YU Zhongan, CHEN Keyi, ZHANG Junling, et al. Research progress of power battery cooling technology[J]. Journal of Electrical Engineering，2022, 17(4):145-162.
[19] 夏光，张洋，魏振亚，等. 驾驶员驾驶习惯识别与车辆自动变速换档修正[J]. 机械工程学报，2020，56(20):120-133. XIA Guang，ZHANG Yang，WEI Zhengya，et al. Driving habit recognition and shifting correction control of vehicle automatic transmission[J]. Journal of Mechanical Engineering，2020，56(20):120-133.
[20] 刘松华，张军英，许进，等. Kernel-KNN: 基于信息能度量的核k-最近邻算法[J]. 自动化学报，2010(12):681-688. LIU Songhua，ZHANG Junying，XU Jin，et al. Kernel-knn:A new KNN algorithm based on informational energy metric[J]. Acta Automatica Sinica，2010(12):681-688.

基于驾驶行为的纯电动汽车剩余续驶里程预测

Prediction of Remaining Mileage of Electric Vehicle Based on Driving Behavior

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 9

编辑推荐

Metrics

本文评价

[1]	汤勇, 赵威, 尹树彬, 袁雪鹏, 袁伟, 张仕伟. 基于相变传热的动力电池高效复合热控技术研究综述[J]. 机械工程学报, 2025, 61(4): 176-194.
[2]	关海杰, 王博洋, 龚建伟, 陈慧岩. 面向异构车辆的统一运动规划方法[J]. 机械工程学报, 2024, 60(18): 288-298.
[3]	张海伦, 许庆, 高博麟, 王建强, 李克强. 网联环境下驾驶人响应机制——一种交叉路口接近行为定性效应分析与定量驾驶模式提取案例[J]. 机械工程学报, 2024, 60(10): 22-47.
[4]	赵敬玉, 徐铖, 李晓宇. 基于实际行驶数据的电动汽车能耗分析与预测[J]. 机械工程学报, 2023, 59(10): 263-274.
[5]	李文博, 刘羽婧, 张峻铖, 肖华飞, 郭钢, 曹东璞. 驾驶员情绪-驾驶风险机理分析[J]. 机械工程学报, 2022, 58(22): 379-394.
[6]	谢林, 李红伟, 袁岳, 周海林. 基于K-Means聚类和改进多分类相关向量机的台区线损计算方法[J]. 电气工程学报, 2021, 16(1): 62-69.
[7]	胡东海, 严炎智. 考虑PMSM转子偏心作用的EV动力传动系统非线性扭振特性分析[J]. 机械工程学报, 2018, 54(22): 128-136.
[8]	黄万友;程勇;曹红;李闯;张笑文. 纯电动汽车能量回馈效率特性测试分析[J]. , 2012, 48(12): 88-95.
[9]	王志福;陈伟;叶辉萍;史建军. 加装超级电容纯电动汽车的性能分析[J]. , 2005, 41(12): 82-86.