Rolling Bearing Fault Diagnostic Method Based on VMD-AR Model and Random Forest Classifier

Table 5

The performance for fault location 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	100	88.03	99.06	98.97	0.0771	0.009	1.719	4.108
160	240	100	87.71	99.67	99.96	0.1153	0.0104	3.349	9.274
240	160	100	88.31	99.75	99.88	0.1511	0.0107	6.026	16.89
320	80	100	93.13	100	99.88	0.187	0.011	9.266	27.36