Fast EIS acquisition method based on SSA-DNN prediction model.

Electrochemical impedance spectroscopy (EIS) is an efficient and information-rich technique for detecting lithium-ion batteries. However, the measurement of EIS takes much time, and the lower the measurement frequency, the longer the measurement takes. To address this problem, this study innovatively proposes an EIS prediction method based on a sparrow search algorithm optimized deep neural network (SSA-DNN). The overall measurement time is reduced by extracting features from the medium-high frequency segments, where the EIS measurement is less time-consuming, and predicting the medium-low frequency segments that consume more measurement time. After evaluating the EIS prediction results at different cycling temperatures and states of charge (SOC), it is concluded that the EIS prediction method proposed in this paper has the advantages of fast measurement speed, high accuracy and applicability. Finally, the predicted EIS is used to estimate the state of health (SOH), and the distribution of relaxation time (DRT) is calculated. The results show that the proposed EIS prediction method has a maximum prediction RMSE of 29.15 m Ω , and the measurement time is reduced to 2.94 % of the original measurement time, which can be widely used in various scenarios based on EIS technology. • Proposing an EIS prediction method based on optimized deep neural network. • Reducing acquisition time for complete full-band EIS with less than 2 % error. • The method is applicable to different SOC, SOH, and temperature status. [ABSTRACT FROM AUTHOR]