SOH Estimation for Lithium-Ion Batteries Based on Health Indicators Extraction and MKRVR

Abstract

Aiming at the problems of difficult feature extraction and low State of Health (SOH) prediction accuracy of lithium-ion batteries, this paper proposes a SOH estimation approach that involves extracting Health Indicators (HIs) and utilizing mixed kernel function relevance vector regression (MKRVR). In order to accurately and efficiently extract battery HIs, the paper first examines the limitations of extracting HIs based on Incremental Capacity (IC) curves and puts forward an alternative method of HIs extraction based on voltage-capacity (V-C) curves. Following correlation analysis of the HIs, the paper establishes the MKRVR model that combines a range of kernel functions to estimate SOH. To determine the hyper-parameters and weight coefficients of the MKRVR model, the paper integrates Differential Evolution (DE) and Levy flight into the Gray Wolf Optimizer (GWO) to enhance the population diversity and random search ability of GWO. Finally, the paper conducts experimental validation utilizing three distinct battery datasets. The results indicate that the proposed approach outperforms Support Vector Regression (SVR) and Relevance Vector Regression (RVR), with evaluation index values of MAE, MSE, and RMSE all below 1%. Moreover, the coefficients of determination exceed 0.95, which demonstrates the superiority of this approach over other methods.