Research Article
Rolling Bearing Fault Diagnostic Method Based on VMD-AR Model and Random Forest Classifier
Table 6
The performance for fault severity level problem using different classifiers under 4 modes.
| Number of training samples | Number of testing samples | Total accuracy (%) | Cost time (s) | RF | SVM | GA-SVM | PSO-SVM | RF | SVM | GA-SVM | PSO-SVM |
| 80 | 320 | 96.81 | 81.97 | 95.47 | 95.69 | 0.0859 | 0.0093 | 2.06 | 4.041 | 160 | 240 | 98.58 | 86.96 | 97.29 | 96.58 | 0.1377 | 0.0103 | 4.79 | 9.640 | 240 | 160 | 98.50 | 89.13 | 98.06 | 96.81 | 0.1822 | 0.0115 | 7.77 | 18.04 | 320 | 80 | 98.63 | 91.00 | 98.38 | 97.63 | 0.2356 | 0.0119 | 11.53 | 28.34 |
|
|