基于双层ELM模型的汽车锂电池充电状态评估分析  

Analysis of State-of-Charge Assessment of Automotive Lithium Batteries Based on a Two-Layer ELM Model

作　　者：温喜梅 丁志成 康金龙 李前通 Wen Ximei;Ding Zhicheng;Kang Jinlong;Li Qiantong(School of Electrical and Mechanical Engineering,Zhengzhou Institute of Industrial Applied Technology,Zhengzhou Henan 451150,China)

机构地区：[1]郑州工业应用技术学院机电工程学院,河南郑州451150

出　　处：《现代工业经济和信息化》2024年第9期215-216,219,共3页Modern Industrial Economy and Informationization

摘　　要：锂电池充电状态直接影响到新能源汽车领域的经济效益,采用双层集成极限学习机(ELM)模型对锂电池充电荷电状态(SOC)和健康状态(SOH)进行评估。通过分析电池健康特征实现充电状态的迭代计算。研究结果表明:以等电压区间健康特征来估算双层集成ELM模型获得SOC和老化SOC估计参数偏差不超过1.4%,模型实现了高精度估计效果并表现出了优异鲁棒性。相比较其他算法,集成ELM预测准确率、训练与测试精度都达到了最高,在更短时间内集成ELM模型。该研究有助于提高新能源汽车行业的高效率运行和降低成本。The state of charge of lithium battery directly affects the economic benefits in the field of new energy vehicles,and a two-layer integrated extreme learning machine(ELM)model is used to evaluate the state of charge(SOC)and state of health(SOH)of lithium battery.The iterative calculation of the state of charge is realized by analyzing the battery health characteristics.The results show that the deviation of the estimated parameters of SOC and aging SOC obtained from the two-layer integrated ELM model by estimating the health characteristics of equal voltage intervals is no more than 1.4%,and the type achieves high precision estimation effect and shows excellent robustness.Compared with other algorithms,the integrated ELM prediction accuracy,training and testing accuracy are the highest,and the ELM model is integrated in a shorter time.This research helps to improve the efficient operation and reduce the cost in the new energy vehicle industry.

关 键 词：锂电池 充电状态 健康特征 集成极限学习机 

分 类 号：TM912[电气工程—电力电子与电力传动]