摘要
针对锂离子电池剩余寿命精确预测的问题,提出一种基于变分模态分解(Variational Mode Decomposition,VMD)和极限学习机(Extreme Learning Machine,ELM)的锂离子电池剩余寿命预测方法。利用VMD分解锂电池容量信号得到一系列表征信号局部特性的本征模态函数(Intrinsic Mode Function,IMF),然后基于每个IMF,分别训练ELM模型,最后将每个ELM模型的预测结果加和求得锂离子电池的剩余寿命。基于NASA锂离子电池数据集对方法进行验证。结果表明,基于VMD-ELM的锂离子电池剩余寿命预测方法相较于ELM寿命预测模型和EMD-ELM寿命预测模型,提高了锂电池寿命预测的精度。
To address the problem of accurate prediction of the remaining life of lithium-ion batteries,this paper proposes a method for lithium-ion battery remaining life prediction based on Variational Mode Decomposition(VMD)and Extreme Learning Machine(ELM).Firstly,a series of Intrinsic Mode Functions(IMFs)characterizing the local characteristics of the signal are obtained by decomposing the lithium battery capacity signal with VMD.Then based on each IMF,train the ELM model respectively.Finally,the prediction results of each ELM model are summed to obtain the remaining life of the lithium-ion battery.The validation of the proposed method based on the NASA Li-ion battery dataset shows that the VMD-ELM-based method for lithium-ion battery residual life prediction improves the accuracy of lithium-ion battery life prediction compared to the ELM life prediction model and the EMD-ELM life prediction model.
作者
邹博雨
张营
李泱
陈璐
徐剑澜
顾杰
Zou Boyu;Zhang Ying;Li Yang;Chen Lu;Xu Jianlan;Gu Jie(College of Automobile and Traffic Engineering,Nanjing Forestry University,Nanjing City,Jiangsu Province 210037,China)
出处
《农业装备与车辆工程》
2021年第11期64-67,共4页
Agricultural Equipment & Vehicle Engineering
基金
江苏省高等学校大学生创新创业训练计划项目“基于自适应多核RVM的锂电池剩余寿命预测方法研究”(201910298032Z)。
关键词
锂离子电池
变分模态分解
极限学习机
剩余寿命预测
lithium-ion batteries
variable fractional modal decomposition
extreme learning machine
remaining life prediction