A Hybrid Technique for Estimating the State of Health of Lithium‐Ion Batteries

ABSTRACT

Lithium‐ion Battery State of Health (SOH) estimation is essential for reliability and safety. Rechargeable lithium‐ion availability is decreased by thickening the solid electrolyte interphase (SEI) layer due to interactions between electrodes and electrolytes during cycles of discharging and charging. This paper proposes a hybrid approach, called LOA‐FENN, to reduce estimation errors by fusing the fully Elman neural network (FENN) with the lyrebird optimization algorithm (LOA). The LOA optimizes the neural network's weight during training, while the FENN predicts the SOH. Implemented in MATLAB, the LOA‐FENN approach achieved an estimation error of 1.08%, outperforming existing methods such as the hybrid genetic algorithm (HGA), box‐cox transformation (BCT), and particle filter algorithm (PFA), which showed errors of 1.38%, 1.28%, and 1.18%, respectively.