High accuracy state-of-charge online estimation of EV/HEV lithium batteries based on Adaptive Wavelet Neural Network

Abstract

The state of charge online estimation of EV/HEV lithium battery with high accuracy is very important, Since it can be used to prolong the battery lifetime and improve its performances. Traditional SOC estimation algorithms have show their drawbacks apparently, so the Adaptive Wavelet Neural Network(AWNN) based SOC estimation model is presented. By using adaptive algorithm to train the model, the accurate online SOC estimation is implemented. The simulation and experiment results are given and show that the proposed algorithm is an effective and feasible method to estimate the SOC of the lithium battery with fastest convergence speed and most high accuracy.