Learning Battery Model Parameter Dynamics From Data With Recursive Gaussian Process Regression

Abstract Estimating the state of health is a critical function of a battery management system, but remains challenging due to variability of operating conditions and usage requirements in real applications. As a result, existing techniques based on fitting equivalent circuit models may exhibit inaccuracy at extremes of performance and over long-term ageing, or instability of parameter estimates. Pure data-driven techniques, on the other hand, suffer from a lack of generality beyond their training dataset. Here, we propose a novel hybrid approach combining data- and model-driven techniques for battery health estimation, estimating both capacity loss and resistance increase. Specifically, we use a Bayesian method, Gaussian process regression, to estimate model parameters as functions of states, operating conditions, and lifetime. Computational efficiency is ensured by a recursive implementation, yielding a joint state-parameter estimator that learns parameter dynamics from data and is robust to gaps and varying operating conditions. Results show the efficacy of the method, on both simulated and measured drive cycle data, including accurate estimates and forecasts of battery capacity and internal resistance. This opens up new opportunities to understand battery ageing from field data.