基于IGWO-MKELM的锂离子电池剩余使用寿命预测

Remaining Useful Life Prediction of Lithium-ion Batteries Based on Improved Grey Wolf Optimization Multiple Kernel Extreme Learning Machine

随着锂离子电池在储能系统中比例迅速增大,为避免因电池性能退化导致的事故,如何准确预测锂离子电池剩余使用寿命就成为保障储能系统可靠运行的关键。针对锂离子电池剩余使用寿命预测的问题,提出一种改进灰狼优化多核极限学习机(IGWO-MKELM)预测方法。首先从电池充放电过程中提取能够表征电池寿命退化的间接健康因子作为输入量,然后采用改进灰狼算法对多核极限学习机参数进行寻优,建立改进灰狼优化多核极限学习机预测方法,最后使用NASA电池数据集进行仿真实验。结果表明,IGWO-MKELM方法可以更加精确地预测锂离子电池剩余寿命。

With the rapid increase of the proportion of lithium-ion batteries in energy storage systems,in order to avoid accidents caused by the degradation of battery performance,how to accurately predict the remaining useful life(RUL)of lithium-ion batteries has become the key to ensuring the reliable operation of energy storage systems.Aimed at the RUL prediction,a predictive method based on improved grey wolf optimization multiple kernel extreme learning machine(IGWO-MKELM)is proposed.First,the indirect health factors that can characterize the degradation of battery life are extracted from the charging and discharging process and used as the input.Then,the IGWO algorithm is used to optimize the parameters of MKELM,and the predictive method based on IGWO-MKELM is established.Finally,a simulation experiment is carried out on the NASA batteries dataset,and results show that the IGWO-MKELM method can more accurately predict the RUL of lithium-ion batteries.