基于经验模态分解-灰色关联度分析-蒲公英优化器改进Elman网络的锂离子电池健康状态估计

State-of-health Estimation of Lithium-ion Batteries Based on EMD-DO-Elman and GRA

准确、可靠的锂离子电池健康状态(state-of-health,SOH)估计有助于提高电池设备的安全和稳定运行。针对目前SOH无法直接测量、健康特征难以提取和估计方法不足等问题,提出了一种基于经验模态分解-灰色关联度分析-蒲公英优化器(empirical mode decomposition-dandelion optimizer,EMDDO)Elman的锂离子电池SOH估计方法。基于NASA Ames研究中心公开的锂离子电池老化测试数据和实际实验测试数据,提出利用经验模态分解(empirical mode decomposition,EMD)对电池老化数据进行信号分解,从而得到反映电池SOH的特征分量,然后利用灰色关联度分析(grey relation analysis,GRA)对特征分量进行相关性分析来选择模型输入。最后,应用蒲公英优化器(dandelion optimizer,DO)对Elman网络的参数进行优化来提高神经网络的估计性能。实验结果表明,该方法能够准确地估计出锂离子电池的SOH,其估计结果的R2始终大于98%,此外,通过对电池数据在不同训练集数量情况下的SOH估计验证,进一步证明了所提出的估计模型有着良好的泛化性和鲁棒性。

Accurate and reliable state-of-health(SOH)estimation of lithium-ion batteries can help improve battery equipment's safety and stability.This paper proposes an EMD-DO-Elman method for estimating the SOH of lithium-ion batteries in response to current issues such as the inability to measure SOH directly,difficulty extracting health features,and insufficient estimation methods.Based on the lithium-ion battery aging test data publicly available at NASA Ames Research Center and actual experimental test battery data,it is proposed to use empirical mode decomposition(EMD)to decompose the battery aging data into signal decomposition,to obtain the characteristic components reflecting the battery SOH.Besides,grey relation analysis(GRA)is used to conduct correlation analysis on the characteristic components to select model inputs.Finally,the dandelion optimizer(DO)is applied to optimize the parameters of the Elman network to improve the estimation performance.The experimental results show that this method can accurately estimate the SOH of lithium-ion batteries,and the R2 of the estimation results is always greater than 98%.In addition,verifying the SOH estimation of battery data under different training set quantities further proves that the estimation model proposed in this paper has good generalization and robustness.