Online capacity estimation of lithium-ion batteries based on convolutional self-attention

Abstract

ABSTRACT It is of great significance to improve the safety, efficiency, and economy of lithium-ion batteries by improving the capacity estimation accuracy of lithium-ion batteries. In this paper, feature extraction and correlation analysis are carried out on the data of lithium-ion battery charging process, and the voltage curve of constant current charging stage is extracted. The difference characteristics between each cycle are used to describe the battery capacity, and these statistical characteristics are proved to be highly correlated with the battery capacity. Furthermore, an online estimation model of battery capacity based on convolution self-attention is established, and the above characteristics of constant current charging process and the battery capacity of the latest cycle are fused as input vectors of the model to realize online estimation of battery capacity. Finally, an open data set is used to verify the model experiment. The results show that the prediction error of MAE is 0.17% and that of RMSE is 0.22%.