fig6

Figure 6. The RUL prediction results for the NASA-B005 battery. (A, C, E) respectively shows the prediction results using the first 40%, 50%, and 60% of the data as the training set, while (B, D, F) displays the corresponding metric analyses. RUL: Remaining useful life; NASA: National Aeronautics and Space Administration; CNN: convolutional neural network; BiGRU: bidirectional gated recurrent unit; GRU: gated recurrent unit; BiLSTM: bidirectional LSTM; LSTM: long short-term memory; MAE: mean absolute error; RMSE: root mean square error; MAPE: mean absolute percentage error.