A simple feature extraction method for estimating the whole life cycle state of health of lithium-ion batteries using transformer-based neural network

Accurately estimating the state of health (SOH) of lithium-ion batteries (LIBs) can avoid safety accidents and economic losses, and it remains a big research challenge. In this paper, electrochemical impedance spectroscopy (EIS) is used as the feature for the SOH prediction. EIS contains rich information such as material properties and electrochemical reactions, which directly reflects the aging state of LIBs. In order to obtain valuable data for SOH estimation, we propose a new feature extraction method from the perspective of electrochemistry, and then apply the transformer-based neural network for SOH estimation. Through feature extraction, the mean absolute percentage error of the estimation is reduced to 1.63% in the whole life cycle, which is decreased by 70% compared to the original data before feature extraction.