基于改进鸟群算法优化最小二乘支持向量机的锂离子电池寿命预测方法研究  

Research on lithium-ion battery life prediction method based on improved bird swarm algorithm least squares support vector machine

作　　者：王雪莹[1] 赵全明[1] WANG Xueying;ZHAO Quanming(Hebei University of Technology,Tianjin 300401,China)

机构地区：[1]河北工业大学学院,天津300401

出　　处：《电气应用》2020年第5期12-16,共5页Electrotechnical Application

摘　　要：随着锂离子电池的广泛应用,其寿命预测与健康管理已成为当今的热点问题。锂电池寿命预测对于电池管理系统的稳定运行有着重要意义。采用最小二乘支持向量机(LSSVM)模型对锂离子电池剩余寿命进行预测,并采用鸟群优化算法(BSA)对LSSVM参数进行寻优。为提高BSA算法的全局搜索能力,对BSA算法进行改进,并提出改进鸟群算法(IBSA)。最后采用IBSA算法优化LSSVM模型,建立了IBSA-LSSVM预测模型并对锂离子电池寿命进行预测。测试结果表明,IBSA-LSSVM模型有良好的预测效果和预测稳定性。With the wide application of lithium-ion batteries,life prediction and health management have become a hot issue nowadays.Life prediction of lithium batteries is of great signifcance to the stable operation of battery management system.Least squares support vector machine(LSSVM)model is used to predict the residual life of lithium ion batteries,and bird swarm optimization algorithm(BSA)is used to optimize the parameters of LSSVM.In order to improve the global search ability of BSA,the BSA is improved and an improved bird swarm algorithm(IBSA)is proposed.Finally,the least squares support vector machine(LSSVM)is optimized by using IBSA,and the IBSA-LSSVM prediction model is established to predict the life of lithium-ion batteries.The test results show that IBSA-LSSVM model has good prediction effect and stability.

关 键 词：可持续锂离子电池 鸟群算法 最小二乘支持向量机 锂离子电池寿命预测 

分 类 号：TM912[电气工程—电力电子与电力传动] TP18[自动化与计算机技术—控制理论与控制工程]