Semi-supervised estimation of capacity degradation for lithium ion batteries with electrochemical impedance spectroscopy

• Published in: Journal of energy chemistry 2023-01, Vol.76, p.404-413
• Main Authors: Xiong, Rui, Tian, Jinpeng, Shen, Weixiang, Lu, Jiahuan, Sun, Fengchun
• Format: Article
• Language: English
• Subjects: Capacity degradation; Deep learning; Electrochemical impedance spectroscopy; Lithium-ion battery
• ISSN: 2095-4956
• DOI: 10.1016/j.jechem.2022.09.045

A semi-supervised deep learning method is proposed to take advantage of impedance spectra with/without capacity measurements for enhancing battery capacity estimation performance. [Display omitted] Machine learning-based methods have emerged as a promising solution to accurate battery capacity estimation for battery management systems. However, they are generally developed in a supervised manner which requires a considerable number of input features and corresponding capacities, leading to prohibitive costs and efforts for data collection. In response to this issue, this study proposes a convolutional neural network (CNN) based method to perform end-to-end capacity estimation by taking only raw impedance spectra as input. More importantly, an input reconstruction module is devised to effectively exploit impedance spectra without corresponding capacities in the training process, thereby significantly alleviating the cost of collecting training data. Two large battery degradation datasets encompassing over 4700 impedance spectra are developed to validate the proposed method. The results show that accurate capacity estimation can be achieved when substantial training samples with measured capacities are given. However, the estimation performance of supervised machine learning algorithms sharply deteriorates when fewer samples with measured capacities are available. In this case, the proposed method outperforms supervised benchmarks and can reduce the root mean square error by up to 50.66%. A further validation under different current rates and states of charge confirms the effectiveness of the proposed method. Our method provides a flexible approach to take advantage of unlabelled samples for developing data-driven models and is promising to be generalised to other battery management tasks.