Table 4 Performance comparison of deep learning models for cycle-based SoH estimation.
From: Cycle based state of health estimation of lithium ion cells using deep learning architectures
Model | RMSE | MAE | R² | Training time (s) |
|---|---|---|---|---|
MLP | 0.0069 | 0.0049 | 0.9955 | 6.5893 |
TCN | 0.0071 | 0.0051 | 0.9951 | 17.9292 |
LSTM | 0.0076 | 0.0055 | 0.9944 | 16.8527 |
GRU | 0.0160 | 0.0111 | 0.9754 | 150.0615 |
