Cycle Mileage Prediction of Electric Vehicle over Macro Timescale

doi:10.3901/JME.2021.24.250

Abstract

Abstract: Due to the different characteristics of power systems, the maintenance strategy for traditional internal combustion engine vehicles is not suitable for electric vehicles. According to the historical operation data of electric vehicles, the change trend of its future cycle mileage can be predicted, and personalized maintenance suggestions can be put forward to prolong the service life of battery system. First, based on the slow charging data of the real electric vehicles, the IC curve of each cell under different charging segments is drawn. Pearson correlation analysis is used to extract features that have high correlations with mileage, then the IC feature zone of the battery pack can be constructed. In addition, the number of equivalent cycles, charging time, and average temperature are proven with a high correlation to cycle mileage. Using the above features and the average value and width of the IC feature zone, a 5-dimensional feature set can be constructed. Then, by using the multi-dimensional features as the input and the cycle mileage as the output, different data-driven models based on a variety of machine learning algorithms can be established. The results show that each model has good prediction accuracy, and the average error of cycle mileage prediction is less than 3%. Among them, the support vector regression model has the best prediction accuracy, and its average error is less than 1%. By predicting the future cycle mileage, the rate of battery degradation can be effectively identified, which provides guidance and suggestions for the maintenance of electric vehicles.

Key words: electric vehicles, mileage prediction, data-driven, IC feature zone, support vector regression

CLC Number:

TG156

DENG Zhongwei, XIAO Wei, LI Yang, HUANG Yong, JIA Jun, HU Xiaosong. Cycle Mileage Prediction of Electric Vehicle over Macro Timescale[J]. Journal of Mechanical Engineering, 2021, 57(24): 250-258.

References

[1] 中华人民共和国中央人民政府. 中共中央关于制定国民经济和社会发展第十四个五年规划和二〇三五年远景目标的建议[EB/OL].[2020-11-03]. http://www.gov.cn/zhengce/2020-11/03/content_5556991.htm. The Central Government of the People's Republic of China. Proposals of the Central Committee of the Communist Party of China on Formulating the 14th Five-Year Plan for Economic and Social Development and the Long-term Goals for 2035[EB/OL].[2020-11-03]. http://www.gov.cn/zhengce/2020-11/03/content_5556991.htm.
[2] 张憧. 电动汽车续驶里程影响因素及预测研究[D]. 合肥:合肥工业大学,2018. ZHANG Chong. Research on influencing factors and prediction of the remaining driving range for electric vehicles[D]. Hefei:Heifei University of Technology,2018.
[3] 高航. 基于机器学习的纯电动汽车的行驶里程预测研究[D]. 北京:北京交通大学,2018. GAO Hang. Study on driving mileage prediction of pure electric vehicle based on machine learning[D]. Beijing:Beijing Jiaotong University,2018.
[4] 张家玮. 基于数据驱动的电动汽车行驶里程模型建立与分析[D]. 北京:北京交通大学,2015. ZHANG Jiawei. Modeling and analyzing of driving mileage of electric vehicle based on data-driven[D]. Beijing:Beijing Jiaotong University,2015.
[5] 张廷. 纯电动乘用车行驶里程建模与分析[D]. 北京:北京交通大学,2017. ZHANG Ting. Modeling and analysis of the driving range for electric passenger vehicles[D]. Beijing:Beijing Jiaotong University,2017.
[6] 晏玖江,肖伟,贾俊,等. 基于能耗参数辨识和路况预测的剩余续驶里程数据驱动算法[J]. 重庆理工大学学报,2020,34(10):83-90. YAN Jiujiang,XIAO Wei,JIA Jun,et al. Remaining driving range data-driven algorithm based on energy consumption parameter identification and road condition prediction[J]. Journal of Chongqing University of Technology,2020,34(10):83-90.
[7] ZHAO Q,QIN X,ZHAO H,et al. A novel prediction method based on the support vector regression for the remaining useful life of lithium-ion batteries[J]. Microelectronics Reliability,2018,85:99-108.
[8] LI Y,ABDEL-MONEMA M,GOPALAKRISHNAN R,et al. A quick on-line state of health estimation method for Li-ion battery with incremental capacity curves processed by Gaussian filter[J]. Journal of Power Sources,2018,373:40-53.
[9] JIANG Y,JIANG J,ZHANG C,et al. Recognition of battery aging variations for LiFePO4 batteries in 2nd use applications combining incremental capacity analysis and statistical approaches[J]. Journal of Power Sources,2017,360:180-188.
[10] WENG C,SUN J,PENG H. A unified open-circuit-voltage model of lithium-ion batteries for state-of-charge estimation and state-of-health monitoring[J]. Journal of Power Sources,2014,258:228-237.
[11] ZHOU Y,HUANG M,CHEN Y,et al. A novel health indicator for on-line lithium-ion batteries remaining useful life prediction[J]. Journal of Power Sources,2016,321:1-10.
[12] 王明. 风储联合应用中储能的需求评估方法研究[D]. 长沙:湖南大学,2015. WANG Ming. Research on the needs assessment methodology of energy storage in the wind power and energy storage combined application[D]. Changsha:Hunan University,2015.
[13] WENG C,SUN J,PENG H. An open-circuit-voltage model of lithium-Ion batteries for effective incremental capacity analysis[C]//Dynamic systems and control conference,21 Oct. 2013,Palo Alto,California,USA. American Society of Mechanical Engineers,2013,56123:V001T05A002.
[14] 熊缨,岑恺. 基于相对误差平方和的神经网络预测镁合金多轴疲劳寿命[J]. 机械工程学报,2016,52(4):73-81. XIONG Ying,CEN Kai. Neural network based on sum squared relative error to predict the multixial fatigue life of magnesium alloy[J]. Journal of Mechanical Engineering,2016,52(4):73-81.
[15] 郭姣姣,刘伟,翟玮昊,等. 随机故障注入结合神经网络法的机电系统可靠性计算方法[J]. 机械工程学报,2017,53(6):195-202. GUO Jiaojiao,LIU Wei,ZHAI Weihao,et al. Reliability calculation method of electromechanical system based on random fault injection combined with artificial neural network[J]. Journal of Mechanical Engineering,2017,53(6):195-202.
[16] SEVERSON K A,ATTIA P M,JIN N,et al. Data-driven prediction of battery cycle life before capacity degradation[J]. Nature Energy,2019,4(5):383-391.
[17] BISHOP C,TIPPING M. Bayesian regression and classification[J]. Advances in Learning Theory Methods Models & Applications,2003:267-285.
[18] LI X,WANG Z,YAN J. Prognostic health condition for lithium battery using the partial incremental capacity and Gaussian process regression[J]. Journal of Power Sources,2019,421:56-67.