Calendar Ageing Model for Li-Ion Batteries Using Transfer Learning Methods

Getting accurate lifetime predictions for a particular cell chemistry remains challenging process, largely dependent on time and cost-intensive experimental battery testing. This paper proposes transfer learning (TL) method to develop LIB ageing models, which allow the leveraging of laboratory testing data previously obtained different technology. The TL is implemented through Neural Networks using LiNiMnCoO2/C as baseline model. model achieves an 1.01% overall error broad range operating conditions, retraining only two tests LiFePO4/C cells.