Remaining useful life prediction of lithium-ion batteries based on the Support Vector Regression Optimized and Enhanced Whale Optimization Algorithm

Abstract

Accurate and reliable predictions of the remaining useful life (RUL) of lithium-ion batteries are crucial for ensuring the proper functioning and longevity of lithium-ion battery systems. Predicting the RUL in its early stages can be challenging and difficult for conventional RUL prediction techniques. To tackle this challenge, this paper proposes a novel approach that integrates five carefully chosen health features with a Support Vector Regression Optimized model and Enhanced Whale Optimization Algorithm (EWOA-SVR) to predict the future capacity trend and subsequently estimate the RUL using XGBoost method according to the predicted capacity. The proposed approach aims to achieve early and accurate capacity estimation and RUL prediction for lithium-ion batteries. To begin, this method extracts some health features during the relaxation process and during the constant-current and constant-voltage charge (CC-CV) process. To demonstrate the strength of the correlation between the health features and capacity, both Pearson and Spearman rank correlation analysis are employed in this study. Then based on the measurable health features and faded capacity data, Ant Lion Optimization (ALO), Whale Optimization Algorithm (WOA) and EWOA are used to select suitable penalty factor and kernel parameter in the SVR algorithm to improve the performance of SVR. With the well-trained model, the future capacity can be predicted with an accuracy of MAPE within 1%, and the RUL prediction error is lower than 11 cycles. The results suggest that the proposed model can achieve a precise and dependable early estimation of the future capacity and RUL prediction.