System Identification for Lithium-Ion Batteries with Nonlinear Coupled Electro-Thermal Dynamics via Bayesian Optimization

TL;DR

This paper introduces a Bayesian optimization-based method for accurately identifying parameters in a complex nonlinear electro-thermal model of lithium-ion batteries, improving model precision for practical applications.

Contribution

It presents a novel approach leveraging Bayesian optimization to efficiently estimate parameters of a coupled electro-thermal battery model, addressing nonlinear and complex dynamics.

Findings

Efficient parameter estimation with fewer experimental requirements.

Improved accuracy in modeling lithium-ion battery electro-thermal behavior.

Method applicable to various battery models and practical scenarios.

Abstract

Essential to various practical applications of lithium-ion batteries is the availability of accurate equivalent circuit models. This paper presents a new coupled electro-thermal model for batteries and studies how to extract it from data. We consider the problem of maximum likelihood parameter estimation, which, however, is nontrivial to solve as the model is nonlinear in both its dynamics and measurement. We propose to leverage the Bayesian optimization approach, owing to its machine learning-driven capability in handling complex optimization problems and searching for global optima. To enhance the parameter search efficiency, we dynamically narrow and refine the search space in Bayesian optimization. The proposed system identification approach can efficiently determine the parameters of the coupled electro-thermal model. It is amenable to practical implementation, with few requirements on the experiment, data types, and optimization setups, and well applicable to many other battery models.