Research Article
A Deep Transfer Learning Method for Bearing Fault Diagnosis Based on Domain Separation and Adversarial Learning
Table 3
Network parameters of the reconstructor.
| Layer name | Kernel size | Stride | Channel | Output size |
| Input | — | — | 1 | 128 + 152 | Linear | — | — | 1 | 8 × 256 | Reshape | — | — | 256 | 1 × 8 | Deconv 1 | 3 | 2 | 128 | 1 × 17 | Deconv 2 | 3 | 2 | 96 | 1 × 35 | Deconv 3 | 3 | 2 | 64 | 1 × 71 | Deconv 4 | 3 | 2 | 32 | 1 × 143 | Deconv 5 | 5 | 3 | 16 | 1 × 431 | Deconv6 | 7 | 3 | 1 | 1 × 1,297 |
|
|