fig5

A hybrid deep learning model for robust and data-efficient lithium-ion battery remaining useful life prediction

Figure 5. Validation of RUL prediction performance. (A) RUL prediction results and (B) Evaluation metrics for NASA-B005 battery cell using different schemes; (C) RUL prediction results for NCM-1 battery cell using different schemes; (D) Evaluation metrics for NCM-1 prediction results; (E) Predicted versus actual RUL curves for the NCM-1 and NCM-2 batteries using the model trained exclusively on NASA-B005 data; (F) Generalization results on NASA-B005, B006, and B007 batteries from the model trained on NCM-1 data. RUL: Remaining useful life; NASA: National Aeronautics and Space Administration; NCM: nickel cobalt manganese; MAE: mean absolute error; RMSE: root mean square error; MAPE: mean absolute percentage error..

Journal of Materials Informatics
ISSN 2770-372X (Online)
Follow Us

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/