Page 103 - EER-2-1

Explora: Environment
and Resource Artificial neural networks

A B

C D

E F

Figure 11. Validation of the coupled electrothermal lifetime model for condition IV: (A) voltage comparison of 500 FECs; (B) temperature comparison of 500 cycles;
(C) voltage comparison of 1000 FECs; (D) temperature comparison of 1000 cycles; (E) voltage comparison of 1500 FECs; (F) temperature comparison of 1500 FECs.
Abbreviation: FECs: Full equivalent cycles.

Table 6. Root‑mean‑square error of the model validation for conditions II and IV
RMSE Condition II Condition IV
500 FECs 1000 FECs 1500 FECs 500 FECs 1000 FECs 1500 FECs
Electrical (%) 0.8 0.81 0.74 0.78 0.81 0.76
Thermal (%) 2.4 2.1 2.3 2.2 2.05 2.2
Abbreviation: RMSE: Root-mean-square error; FECs: Full equivalent cycles.

unexpected increase in measured capacity retention at 200 Despite this anomaly, the FNN accurately captured the
FECs was observed, likely due to a data acquisition system overall capacity retention trend, including the slight rise at 200
error. FECs. The error metric, calculated as the absolute difference

Volume 2 Issue 1 (2025) 10 doi: 10.36922/eer.7228