Research Article
A Deep Transfer Learning Method for Bearing Fault Diagnosis Based on Domain Separation and Adversarial Learning
Table 2
Network parameters of the domain-invariant feature extractor.
| Layer name | Kernel size/stride | Channel | Output size | Structure |
| Input | — | 1 | 1 × 1,297 | — | Conv 1 | 7/3 | 48 | 1 × 431 | — | Max pool | 3/2 | 48 | 1 × 215 | — | Conv 2 | 5/3 | 72 | 1 × 71 | — | Block 3 | 3 | 72 | 1 × 35 | | Block 4 | 3 | 96 | 1 × 17 | | Block 5 | 3 | 152 | 1 × 8 | |
|
|