Online State of Health Estimation with Deep Learning Frameworks Based on Short and Random Battery Charging Data Segments

• Published in: Journal of the Electrochemical Society Vol. 170; no. 9; pp. 90537 - 90548
• Main Authors: Zhao, Lei, Du, Xuzhi, Yang, Zhigang, Xia, Chao, Xue, Jinwei, Hoque, Muhammad Jahidul, Fu, Wuchen, Yan, Xiao, Miljkovic, Nenad
• Format: Journal Article
• Language: English
• Published: IOP Publishing 01.09.2023
• ISSN: 0013-4651; 1945-7111
• DOI: 10.1149/1945-7111/acf8ff

Lithium-ion (Li-ion) batteries find wide application across various domains, ranging from portable electronics to electric vehicles (EVs). Reliable online estimation of the battery’s state of health (SOH) is crucial to ensure safe and economical operation of battery-powered devices. Here, we developed three deep learning models to investigate their potential for online SOH estimation using partial and random charging data segments (voltage and charging capacity). The models employed were developed from the feed-forward neural network (FNN), the convolutional neural network (CNN) and the long short-term memory (LSTM) neural network, respectively. We show that the proposed deep learning frameworks can provide flexible and reliable online SOH estimation. Particularly, the LSTM-based estimation model exhibits superior performance across the test set in both direct learning and transfer learning scenarios, while the CNN and FNN-based models show slightly diminished performance, especially in the complex transfer learning scenario. The LSTM-based model achieves a maximum estimation error of 1.53% and 2.19% in the direct learning and transfer learning scenarios, respectively, with an average error as low as 0.28% and 0.30%. Our work highlights the potential for conducting online SOH estimation throughout the entire life cycle of Li-ion batteries based on partial and random charging data segments.