基于VMD-PSO-ELM的锂离子电池剩余寿命预测

Residual Life Prediction of Lithium-ion Batteries Based on VMD-PSO-ELM

为了准确地预测锂离子电池的剩余寿命,提出了变分模态分解(VMD)结合粒子群算法(PSO)优化极限学习机(ELM)的锂离子电池剩余寿命预测模型。首先,根据放电容量与电压曲线、最高温度、最大内阻和放电容量提取出与锂离子电池剩余寿命高度相关的健康因子,然后利用PSO算法对ELM神经网络的权值和阈值进行优化,采用VMD分解将锂离子电池的剩余寿命原始数据分解为若干子序列,基于PSO-ELM模型对各个子序列进行预测,最后将各个子序列的预测结果求和,即为锂离子电池剩余寿命的预测值。结果表明,VMD-PSO-ELM模型与其他模型相比,更能精准地预测锂电池的剩余寿命。

In order to accurately predict the remaining useful life of lithium-ion batteries,a variational mode decomposition(VMD)combined with particle swarm optimization(PSO)optimized extreme learning machine(ELM)model for predicting the remaining lifespan of lithium-ion batteries was proposed.Firstly,according to the discharge capacity and voltage curve,the maximum temperature,the maximum internal resistance and the discharge capacity,the health factors that are highly related to the remaining life of the battery were extracted.Then,the weight and threshold of the ELM neural network were optimized using the PSO.The original data of the remaining life of lithium-ion battery was divided into several subsequences using VMD decomposition,and each subsequence was predicted based on the PSO-ELM model.Finally,the prediction results of the subsequences are summed up,it is the predicted value of the remaining life of the lithium-ion battery.The results indicated that compared with other models,VMD-PSO-ELM could more accurately predict the remaining life of lithium-ion batteries.