Research Article
Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature Learning
Table 4
Precision, Recall, and F-Measure of the proposed CACD-1DCNN and A2CNN on six domain shifts.
| | Fault location | N | RF | IF | OF |
| | Fault diameter (inch) | | 0.007 | 0.014 | 0.021 | 0.007 | 0.014 | 0.021 | 0.007 | 0.014 | 0.021 | | Category labels | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | | Precision | | | | | | | | | | | | A2CNN | | | | | | | | | | | | A ⟶ B | 100 | 100% | 100% | 99.88% | 100% | 100% | 100% | 100% | 100% | 100% | | A ⟶ C | 93.46 | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | B ⟶ C | 100 | 90.07% | 92.59% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | C ⟶ B | 100 | 100% | 100% | 100% | 100% | 99.01% | 100% | 100% | 100% | 100% | | C ⟶ A | 100 | 90.91% | 90.40% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | B ⟶ A | 100 | 99.88% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | CACD-1DCNN | | | | | | | | | | | | A ⟶ B | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | A ⟶ C | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | B ⟶ C | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | C ⟶ B | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | C ⟶ A | 100% | 89% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | B ⟶ A | 100% | 89% | 100% | 100% | 93% | 100% | 100% | 100% | 100% | 100% | | Recall | | | | | | | | | | | | A2CNN | | | | | | | | | | | | A ⟶ B | 100 | 100% | 99.88% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | A ⟶ C | 100 | 100% | 93.00% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | B ⟶ C | 100 | 100% | 100% | 81.75% | 100% | 100% | 100% | 100% | 100% | 100% | | C ⟶ B | 100 | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 99.00% | 100% | | C ⟶ A | 100 | 100% | 100% | 79.38% | 100% | 100% | 100% | 100% | 100% | 100% | | B ⟶ A | 100 | 100% | 100% | 99.88% | 100% | 100% | 100% | 100% | 100% | 100% | | CACD-1DCNN | | | | | | | | | | | | A ⟶ B | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | A ⟶ C | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | B ⟶ C | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | C ⟶ B | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | | C ⟶ A | 100% | 100% | 100% | 88% | 100% | 100% | 100% | 100% | 100% | 100% | | B ⟶ A | 100% | 100% | 100% | 80% | 100% | 100% | 100% | 100% | 100% | 100% | | F-Measure | | | | | | | | | | | | A2CNN | | | | | | | | | | | | A ⟶ B | 1 | 1 | 0.9994 | 0.9994 | 1 | 1 | 1 | 1 | 1 | 1 | | A ⟶ C | 0.9662 | 1 | 0.9637 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | | B ⟶ C | 1 | 0.9478 | 0.9615 | 0.8996 | 1 | 1 | 1 | 1 | 1 | 1 | | C ⟶ B | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 0.9950 | 1 | | C ⟶ A | 1 | 0.9524 | 0.9496 | 0.8850 | 1 | 1 | 1 | 1 | 1 | 1 | | B ⟶ A | 1 | 0.9994 | 1 | 0.9994 | 1 | 1 | 1 | 1 | 1 | 1 | | CACD-1DCNN | | | | | | | | | | | | A ⟶ B | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | | A ⟶ C | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | | B ⟶ C | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | | C ⟶ B | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | | C ⟶ A | 1 | 0.9434 | 1 | 0.9362 | 1 | 1 | 1 | 1 | 1 | 1 | | B ⟶ A | 1 | 0.9434 | 1 | 0.8889 | 0.9615 | 1 | 1 | 1 | 1 | 1 |
|
|
