A Fault Diagnosis Model Based on LCD-SVD-ANN-MIV and VPMCD for Rotating Machinery

Table 5

The test results of different classifier based VPMCD methods.

Different model and different predictor order	Accuracy (%)	Cost time (s)	Least number for acquired training samples
Linear VPM with (prm(1, 1))	94.16	0.1063	2
Linear VPM with (prm(1, 2))	95.34	0.1156	3
Linear VPM with (prm(1, 3))	96.65	0.1280	4
Linear + interaction VPM with (prm(2, 2))	99.74	0.1656	4
Linear + interaction VPM with (prm(2, 3))	100	0.1653	7
Quadratic + interaction VPM with (prm(3, 2))	99.48	0.1518	6
Quadratic + interaction VPM with (prm(3, 3))	100	0.1281	10
Pure quadratic VPM with (prm(4, 1))	98.74	0.1391	3
Pure quadratic VPM with (prm(4, 2))	100	0.1218	5
Pure quadratic VPM with (prm(4, 3))	99.74	0.1012	7