Model Migration Neural Network for Predicting Battery Aging Trajectories
Xiaopeng Tang, Kailong Liu, Xin Wang, Furong Gao, James Macro, Widanalage Dhammika Widanage
Abstract
An accurate prediction of batteries' future degradation is a key solution to relief the users' anxiety on battery lifespan and electric vehicles' driving range. Technical challenges arise from the highly nonlinear dynamics of battery aging. In this article, a feed-forward migration neural network (NN) is proposed to predict the batteries' aging trajectories. Specifically, a base model that describes the capacity decay over time is first established from the existed battery aging data set. This base model is then transformed by an input-output slope and bias correction (SBC) method structure to capture the degradation of target cell. To enhance the model's nonlinear transfer capability, the SBC model is further integrated into a four-layer NN and easily trained via the gradient correlation algorithm. The proposed migration NN is experimentally verified with four different commercial batteries. The predicted root-mean-square errors (RMSEs) are all lower than 2.5% when using only the first 30% of aging trajectories for NN training. In addition, the illustrative results demonstrate that a small-sized feed-forward NN (down to 1-5-5-1) is sufficient for battery aging trajectory prediction.