New algorithm for battery knee-onset identification and early prediction of end of life

Lithium-ion battery degradation is characterised by an initial quasi-linear capacity fade, transitioning to an accelerated, non-linear degradation phase at the knee onset point, which intensifies until the knee point, followed by rapid degradation to end-of-life (EOL). Accurate identification of these critical points is crucial for effective battery management and predictive maintenance. This study proposes a novel offline method, the capacity loss slope-peak (CLSP) algorithm, designed to robustly determine both the knee onset and knee points directly from capacity fade data. The CLSP method demonstrates efficacy across diverse degradation pathways, including both concave and convex-shaped curves, with its predicted knee onset and knee points showing strong correlation with EOL. Furthermore, to enable early-stage prognostics, we developed a machine learning (ML) workflow to predict the knee onset point using data from as early as 10 cycles. This ML-based predictive capability serves as a valuable tool for early identification of the degradation trajectory and subsequent EOL, thereby significantly accelerating battery testing, reducing resource consumption, and cutting experimental costs.