Predicting the Cycle Life of Lithium-Ion Batteries Using Data-Driven Machine Learning Based on Discharge Voltage Curves
Yinfeng Jiang, Wenxiang Song
Abstract
Battery degradation is a complex nonlinear problem, and it is crucial to accurately predict the cycle life of lithium-ion batteries to optimize the usage of battery systems. However, diverse chemistries, designs, and degradation mechanisms, as well as dynamic cycle conditions, have remained significant challenges. We created 53 features from discharge voltage curves, 18 of which were newly developed. The maximum relevance minimum redundancy (MRMR) algorithm was used for feature selection. Robust linear regression (RLR) and Gaussian process regression (GPR) algorithms were deployed on three different datasets to estimate battery cycle life. The RLR and GPR algorithms achieved high performance, with a root-mean-square error of 6.90% and 6.33% in the worst case, respectively. This work highlights the potential of combining feature engineering and machine learning modeling based only on discharge voltage curves to estimate battery degradation and could be applied to onboard applications that require efficient estimation of battery cycle life in real time.