Research Article
A New Generative Neural Network for Bearing Fault Diagnosis with Imbalanced Data
Table 3
Bearing dataset setting with three classes.
| Condition | Faulty severity level (mm) | Scenario 1 label (four classes) | Scenario 2 label (ten classes) | Scenario 3 label (sixteen classes) |
| Norm | 0 | 1 | 1 | 1 | IF | 0.2 | 2 | 2 | 2 | 0.3 | — | 3 | 3 | 0.4 | — | 4 | 4 | 0.5 | — | — | 5 | 0.6 | — | — | 6 |
| BF | 0.2 | 3 | 5 | 7 | 0.3 | — | 6 | 8 | 0.4 | — | 7 | 9 | 0.5 | — | — | 10 | 0.6 | — | — | 11 |
| OF | 0.2 | 4 | 8 | 12 | 0.3 | — | 9 | 13 | 0.4 | — | 10 | 14 | 0.5 | — | — | 15 | 0.6 | — | — | 16 |
|
|