State of health estimation for lithium battery random charging process based on CNN-GRU method
Yuxuan Zheng, Jiaxiang Hu, Jianjun Chen, Huiwen Deng, Weihao Hu
Abstract
The accurate estimation of lithium battery state of health (SOH) is very important for the safe and stable operation of the battery. Since the user’s charging process is random, it is difficult for the user to know the battery SOH through the charging segment. In this article, we proposed a lithium battery SOH estimation method of random charging process based on convolutional gated recurrent unit (CNN-GRU). The method extracts key features adaptively from the segments of voltage, current and temperature curves in the charging process through the CNN-GRU framework to realize the lithium battery SOH estimation. Compared with traditional methods, this method does not need to manually select or construct feature information and it can achieve high precision SOH evaluation. Through experimental verification, the error of this method can reach to 0.901%.