A review of deep learning-based methods for lithium-ion battery remaining useful life prediction
TL;DR
This paper systematically sorts out and analyzes the application progress of four deep learning methods, namely RNN, LSTM, CNN and Transformer, elaborating on their technical principles, advantages, application scenarios and limitations, and points out the common problems of all these models.
Abstract
Against the backdrop of the global energy transition and the "dual carbon" goals, the safety and reliability issues caused by lithium-ion battery aging are in urgent need of resolution, and Remaining Useful Life (RUL) prediction serves as a core technical measure. Traditional mechanistic models and shallow machine learning methods struggle to adapt to the complex nonlinear characteristics of battery aging. Thanks to its strong capabilities in feature extraction and modeling, deep learning has become the core research direction for lithium-ion battery RUL prediction. This paper systematically sorts out and analyzes the application progress of four deep learning methods, namely RNN, LSTM, CNN and Transformer, elaborating on their technical principles, advantages, application scenarios and limitations. It also points out the common problems of all these models, including insufficient interpretability of the "black box" and lack of support from electrochemical mechanisms. Finally, two research directions are proposed: integrating mechanistic principles with deep learning modeling, and advancing the lightweight design of models, which provides a reference for the selection, optimization and engineering implementation of relevant models.