考虑温差特征的锂离子电池寿命预测  

Life prediction for Li-ion battery considering temperature difference feature

作　　者：王菁 邓翔天 王浩然 朱国荣[1] WANG Jing;DENG Xiang-tian;WANG Hao-ran;ZHU Guo-rong(School of Automation,Wuhan University of Technology,Wuhan,Hubei 430070,China;Three Gorges Intelligent Control Technology Co.,Ltd.,Wuhan,Hubei 430070,China)

机构地区：[1]武汉理工大学自动化学院,湖北武汉430070 [2]三峡智控科技有限公司,湖北武汉430070

出　　处：《电池》2023年第1期9-13,共5页Battery Bimonthly

基　　金：国家自然科学基金(51777146,51977163)。

摘　　要：寿命耗尽的锂离子电池继续使用会存在安全隐患,准确预测锂离子电池的循环寿命,有利于保障电池系统的安全。基于实验所得的循环老化数据,分析电池充放电过程中的温差及其他特征与电池寿命的相关性;建立弹性网络回归模型,基于不同特征组合对测试集电池进行寿命及置信区间的预测。温差特征可提高模型的预测精度:单一温差情形与单一放电容量差情形相比,均方根误差(RMSE)、绝对误差(AE)和平均置信区间宽度(AW)分别减小66.8%、58.0%和69.7%;多特征(含温差)情形和多特征(无温差)情形相比,RMSE、AE和AW分别减小62.9%、55.9%和19.6%。There were potential safety hazards if life-exhausted Li-ion battery was used continuously.Accurate prediction of the cycle life of Li-ion battery was beneficial to ensure the safety of the battery system.Based on the cyclic aging data obtained from the experiment,the correlation between temperature difference and other characteristics of the battery during the charging and discharging process and battery life was analyzed.The elastic network regression model was established to predict the battery life and confidence interval of the test set based on different feature combinations.The temperature difference feature could improve the prediction accuracy of the model.The root mean square error(RMSE),absolute error(AE)and average confidence interval width(AW)were reduced by 66.8%,58.0%and 69.7%respectively in the case of single temperature difference compared with that of single discharge capacity difference.Compared with the multi-feature case without temperature difference,the RMSE,AE and AW of the multi-feature case with temperature difference were reduced by 62.9%,55.9%and 19.6%,respectively.

关 键 词：锂离子电池 寿命预测 温差 弹性网络回归 老化 

分 类 号：TM912.9[电气工程—电力电子与电力传动]