Remaining Charging-Discharging Cycle Prediction of Lithium-ion Batteries Based on Cumulative Indicator

Abstract

The remaining charging-discharging cycle (RCDC) prediction is of great significance for lithium-ion battery (LIB) replacement and recycling. This paper proposes to construct a cumulative degradation indicator (CDI) to replace the original DI. The proposed CDI is better than the original DI in terms of monotonicity, linearity, and trend. In the stage of determining the end-of-life (EoL) threshold on the CDI curve, a relevance vector machine (RVM) is introduced to screen a small amount of available samples, and to reduce the prediction error of the CDI EoL threshold. In the experimental verification stage, this paper uses LIB full-life data from NASA to verify the early and long-term prediction performance of RCDC using a small sample. The experimental results show that when the proportion of training data approaches 50%, the prediction error gradually converges to the actual value.