基于机器学习的锂离子电池荷电状态多步预测  

Multi-Step Ahead Forecasting of Lithium-Ion Battery State of Charge Based on Machine Learning

作　　者：于秋月 刘江岩 何林[1,2] 张青[1,2] 谢翌[3] 李夔宁[1,2] YU Qiuyue;LIU Jiangyan;HE Lin;ZHANG Qing;XIE Yi;LI Kuining(Key Laboratory of Low-Grade Energy Utilization Technologies and Systems,Chongqing University,Chongqing 400044,China;School of Energy and Power Engineering,Chongqing University,Chongqing 400044,China;School of Mechanical and Vehicle Engineering,Chongqing University,Chongqing 400044,China)

机构地区：[1]重庆大学低品位能源利用技术及系统教育部重点实验室,重庆400044 [2]重庆大学能源与动力工程学院,重庆400044 [3]重庆大学机械与运载工程学院,重庆400044

出　　处：《汽车工程学报》2023年第4期586-596,共11页Chinese Journal of Automotive Engineering

基　　金：重庆市自然科学基金面上项目(cstc2019jcyj-msxmX0537)。

摘　　要：先进电池管理技术依赖于对未来一段时间荷电状态变化的预测,难点在于误差积累和时间依赖性降低引起的预测精度下降。提出采用机器学习结合多步预测策略来提升荷电状态多步预测精度,利用实际锂电池数据研究了不同多步预测策略的效果。结果表明,实际锂电池荷电状态预测在充电过程中具有显著线性特性,放电过程表现出非线性特性。预测步长为15个时,LR模型、KNN模型、RF模型的MAPE均低于6%,R^(2)均大于0.90。线性回归结合MIMO策略具有最大的实际应用潜力。Advanced battery management technology relies on the near-future prediction of state of charge(SOC).However,the accumulation of errors and the diminished time-dependency lead to a decline in prediction accuracy.In this paper,the machine learning algorithms combined with multi-step prediction strategies are proposed to improve the accuracy of SOC over multiple steps ahead.The effects of different multi-step prediction strategies are studied based on actual lithium battery data.The results show that the actual lithium battery SOC prediction exhibits a significant linear characteristic during the charging phase,and conversely,a nonlinear characteristic in the discharging process.Furthermore,with the prediction step size of 15,the MAPEs of the LR,KNN,and RF models are below 6%,and the R^(2) values are greater than 0.90.It is found that the LR combined with MIMO shows the greatest potential for practical applications.

关 键 词：锂离子电池 荷电状态 机器学习 多步预测 

分 类 号：TM912[电气工程—电力电子与电力传动]