Learning battery model parameter dynamics from data with recursive Gaussian process regression
This work addresses battery health estimation for real-world applications, offering a robust method that improves accuracy and stability over existing techniques, though it is incremental as it builds on hybrid approaches.
The paper tackles the challenge of accurately estimating battery state of health by proposing a hybrid approach that combines data-driven Gaussian process regression with model-driven techniques to learn parameter dynamics from data, resulting in accurate estimates and forecasts of battery capacity and internal resistance on both simulated and measured data.
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. As a result, 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 lack of generality beyond their training dataset. In this paper, we propose a hybrid approach combining data- and model-driven techniques for battery health estimation. Specifically, we demonstrate a Bayesian data-driven method, Gaussian process regression, to estimate model parameters as functions of states, operating conditions, and lifetime. Computational efficiency is ensured through a recursive approach yielding a unified 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 data, including accurate estimates and forecasts of battery capacity and internal resistance. This opens up new opportunities to understand battery ageing in real applications.