Publication

Abstract : Accurate State of Charge (SOC) and State of Health (SOH) estimations are critical for optimizing performance, longevity, and safety of Li-ion batteries in electric vehicles and renewable energy systems. The study introduces a Neuro-Adaptive Backstepping (NAB) controller, leveraging neural networks and backstepping techniques to address the nonlinear dynamics and uncertainties in Li-ion batteries. The NAB controller is evaluated against Non-Neuro Adaptive Backstepping (NNAB) and Fuzzy Logic Controllers (FLC) using a 3RC equivalent circuit model in MATLAB. Performance metrics, including ITAE, ITSE, and IAE, demonstrate The NAB controller’s superior accuracy and robustness, with the lowest error metrics (MAE = 0.0115, RMSE = 0.0806) and the fastest convergence, making it ideal for dynamic battery management systems.