Table 3 Model optimal parameter settings.
From: Remaining useful life prognosis of turbofan engines based on deep feature extraction and fusion
imSSAE parameters | Value | imESN parameters | Value |
|---|---|---|---|
Sparsity parameter \(\rho\) | 0.05 | Reservoir node \(m\) | 300 |
Learning rate | 0.01 | Spectral radius \(\rho (\hat{W})\) | 0.9 |
Batch size | 64 | Sparsity SD | 0.05 |
Epoch | 50 | Leakage rate \(\lambda\) | 0.23 |
Dropout | 0.2 | Scaling factor IS | 0.4 |
Network structure | 14-8-4-1 | Â | Â |
