Model-free fast charging of lithium-ion batteries by online gradient descent

TL;DR

This paper introduces a model-free, data-driven method for fast-charging lithium-ion batteries using online gradient descent, optimizing charging current based on real-time measurements without requiring detailed battery models.

Contribution

It presents a novel model-free approach for fast-charging that guarantees convergence and is validated on various battery models, avoiding the need for extensive training.

Findings

Proven convergence of the method under mild conditions

Validated on multiple linear and nonlinear battery models

Effective in optimizing charging without detailed models

Abstract

A data-driven solution is provided for the fast-charging problem of lithium-ion batteries with multiple safety and aging constraints. The proposed method optimizes the charging current based on the observed history of measurable battery quantities, such as the input current, terminal voltage, and temperature. The proposed method does not need any detailed battery model or full-charging training episodes. The theoretical convergence is proven under mild conditions and is validated numerically on several linear and nonlinear battery models, including single-particle and equivalent-circuit models.