Learning battery model parameter dynamics from

Estimating state of health is a critical function of a battery management system but remains challenging due to the variability of operating conditions and usage requirements of real applications. This paper proposes a hybrid approach combining data- and model-driven techniques for battery health estimation. We demonstrate a Bayesian data-driven method, Gaussian process regression, to estimate model parameters as functions of states, operating conditions, and lifetime. A recursive approach ensures computational efficiency, resulting in a joint state-parameter estimator that learns parameter dynamics from data and is robust to gaps and varying operating conditions. Results indicate that the method is effective on both simulated and measured data, providing accurate estimates and forecasts of battery capacity and internal resistance. This research opens new opportunities for understanding battery ageing in real applications.