Research Article
Rolling Bearing Fault Diagnostic Method Based on VMD-AR Model and Random Forest Classifier
Table 4
Classification results for fault severity level problem using VMD-AR model and SVM classifier.
| Number of modes | Number of training samples | Number of testing samples | Classification accuracy (%) | Total accuracy (%) | Normal | 0.18 mm | 0.36 mm | 0.53 mm |
| 4 | 80 | 320 | 97.25 | 94.75 | 47.88 | 88 | 81.97 | 160 | 240 | 96.5 | 100 | 56.5 | 94.83 | 86.96 | 240 | 160 | 98.25 | 100 | 63.25 | 95 | 89.13 | 320 | 80 | 100 | 100 | 66 | 95.5 | 91 |
| 5 | 80 | 320 | 100 | 89.5 | 88.88 | 75.63 | 88.5 | 160 | 240 | 100 | 91.83 | 89.5 | 85 | 91.58 | 240 | 160 | 100 | 92.75 | 90 | 91.2 | 93.56 | 320 | 80 | 100 | 100 | 90.5 | 93 | 95.88 |
| 6 | 80 | 320 | 100 | 99.13 | 92 | 85.38 | 94.13 | 160 | 240 | 100 | 100 | 94 | 89.17 | 95.79 | 240 | 160 | 100 | 100 | 92 | 91.25 | 95.81 | 320 | 80 | 100 | 100 | 94.5 | 89.5 | 96 |
| 7 | 80 | 320 | 98.13 | 100 | 89 | 83.63 | 92.69 | 160 | 240 | 99.33 | 100 | 93.5 | 87 | 94.96 | 240 | 160 | 98.75 | 100 | 94.25 | 87.25 | 95.06 | 320 | 80 | 99.5 | 100 | 95 | 86.5 | 95.25 |
|
|