State of health estimation of lithium-ion battery during fast charging process based on BiLSTM-Transformer

Lithium-ion batteries are the main energy source of electric vehicles, and the fast charging with a high-rate current is usually used to shorten the charging time. However, the high-rate current may accelerate the performance degradation of lithium-ion batteries and cause thermal runaway safety problems. Therefore, it is important to monitor the state of health (SOH) of lithium-ion batteries during the fast charging process. In this paper, a BiLSTM-Transformer model is proposed to estimate SOH of lithium-ion batteries during the fast charging process. Aging tests of lithium-ion batteries are performed at four different charging currents, and four features highly correlated with SOH are extracted from the voltage curve of the constant current charging stage. A BiLSTM-Transformer model is established with the four features as input and the SOH as output. The model was verified with the experimental dataset and the public dataset at different charging conditions separately, and it was also compared with other popular data-driven methods. The results show that the errors of the BiLSTM-Transformer model are all within 0.6%, which has the highest accuracy and best generalization performance compared with SVR and LSTM. Therefore, the BiLSTM-Transformer model is an effective SOH estimation method of lithium-ion batteries during the fast charging process.