Remaining Useful Life Prediction of Lithium-Ion Batteries by Using a Denoising Transformer-Based Neural Network

In this study, we introduce a novel denoising transformer-based neural network (DTNN) model for predicting the remaining useful life (RUL) of lithium-ion batteries. The proposed DTNN significantly outperforms traditional machine learning models and other deep architectures in terms accuracy reliability. Specifically, achieved an R2 value 0.991, mean absolute percentage error (MAPE) 0.632%, RUL 3.2, which are superior to such as Random Forest (RF), Decision Trees (DT), Multilayer Perceptron (MLP), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Unit (GRU), Dual-LSTM, DeTransformer. These results highlight efficacy providing precise reliable predictions battery RUL, making it promising tool management systems various applications.