SOC Estimation of Lithium Batteries Based on DEKF Combined with CNN-LSTM-Attention
The State of Charge(SOC)of lithium-ion batteries is the basis for battery management systems(BMS)to achieve important functions such as energy optimization distribution and balanced management,and is also an important basis for real-time analysis of battery operation status.This article mainly focuses on lithium iron phosphate batteries.Firstly,a Thevenin equivalent circuit model is established,and the battery SOC estimation is carried out through double extended Kalman filtering(DEKF);Secondly,the SOC estimation value obtained by the DEKF algorithm is used as the feature value,and combined with the actual measured current and voltage signal as the input for model training,to construct the DEKF-CNN-LSTM Attention algorithm,thereby achieving more accurate SOC estimation under different working conditions,with an average estimation error of about 1%.
state of chargedouble extended kalman filterTheveninDEKF-CNN-LSTM-Attention
万方数据
维普
