Research on SOH Estimation Method of Lithium-ion Battery based on Fusion of VMD and SVR

Precisely estimating the State of Health (SOH) of lithium-ion batteries is crucial for their safe and reliable operation. To solve the problem of insufficient accuracy in current state-of-health (SOH) estimations for lithium-ion batteries, this paper proposes an SOH estimation method based on Variational Mode Decomposition (VMD) and Support Vector Regression (SVR). Initially, the aging data from parameters such as voltage, current, and temperature during the charging process of lithium-ion batteries is analyzed. Secondly, through correlation analysis, the correlation analysis of health indicators and capacity decay of lithium-ion batteries is carried out, with four features identified and modal components obtained through VMD decomposition. Finally, SVR is used as the model to estimate the SOH of lithium-ion batteries. Based on the lithium-ion battery public dataset from the Toyota Research Institute (TRI), the experimental results show that the RMSE, MAE, and MAPE of the proposed method are 0.175%, 0.223%, and 0.176%, respectively. This indicates that the proposed method can accurately estimate SOH.