Transfer learning for battery smarter state estimation and ageing prognostics: Recent progress, challenges, and prospects

Abstract

With the advent of sustainable and clean energy transitions, lithium-ion batteries have become one of the most important energy storage sources for many applications. Battery management is of utmost importance for the safe, efficient, and long-lasting operation of lithium-ion batteries. However, the frequently changing load and operating conditions, the different cell chemistries and formats, and the complicated degradation patterns pose challenges for traditional battery management. The data-driven solutions that have emerged in recent years offer great opportunities to uncover the underlying data mapping within a battery system. In particular, transfer learning improves the performance of data-driven strategies by transferring existing knowledge from different but related domains, and if properly applied, would be a promising approach for smarter battery management. To this end, this paper presents a systematic review for the applications of transfer learning in the field of battery management for the first time, with particular focuses on battery state estimation and ageing prognostics. Specifically, the general issues faced by conventional battery management are identified and the applications of transfer learning to these issues are summarized. Then, the specific challenges of each topic are identified and the potential solutions based on transfer learning are explained, followed by a discussion of the state of the art in terms of principles, algorithm frameworks, advantages and disadvantages. Finally, future trends of data-driven battery management with transfer learning are discussed in terms of key challenges and promising opportunities.