Abstract
Accurately predicting the remaining useful life (RUL) of lithium-ion batteries is critical for ensuring the safety, longevity, and operational efficiency of electric vehicles and smart grid applications. However, battery degradation is a highly complex, non-linear electrochemical process. Existing data-driven models often struggle to track long-term health metrics because raw sensor signals—such as voltage, current, and capacity—are highly dynamic and prone to localized temporal fluctuations. This paper proposes HyBattNet, a hybrid deep learning framework that combines convolutional neural networks (CNNs) for local feature extraction and long short-term memory (LSTM) networks for capturing long-range temporal dependencies. The model also incorporates an attention mechanism to focus on salient degradation patterns. Extensive experiments on public battery datasets show that HyBattNet achieves superior RUL prediction accuracy compared to state-of-the-art approaches, with robust performance across different operating conditions and aging scenarios.
@article{tran2026hybattnet,
title={HyBattNet: Hybrid Framework for Predicting the Remaining Useful Life of Lithium-Ion Batteries},
author={Tran, Khoa and Nguyen, Minh and Le, Anh},
journal={IEEE Access},
volume={14},
number={1},
pages={1-14},
year={2026},
doi={10.1109/ACCESS.2026.3656882}
}