Lithium-ion battery capacity estimation based on fragment charging data using deep residual shrinkage networks and uncertainty evaluation

Abstract

Accurate and reliable capacity estimation is crucial for lithium-ion batteries to operate safely and stably. However, the extraction steps of health indicators (HIs) limit the feasibility and applicability of data-driven methods. This study proposes a novel estimation framework using deep residual shrinkage network (DRSN) and uncertainty evaluation to estimate the lithium-ion battery capacity directly; model inputs are only random fragment charging data. Results on three datasets confirm that accurate capacity estimation is achieved by DRSN through integrated attention mechanisms and soft thresholding (the mean absolute percentage error is below 2 %). Meanwhile, the inherent noise sensitivity in data-driven methods is alleviated. Additionally, uncertainty evaluation implemented by Bayesian neural networks provides valuable metrics for the reliability of estimated results from different voltage ranges. The significant correlation between uncertainty and error proves the potential of uncertainty to assist battery management systems for control and decision-making. The experimental study demonstrates the high accuracy, adaptability, and robustness of the proposed framework, especially in coping with the frequent occurrence of random incomplete charging scenarios.