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

Table 8

Comparison between different diagnosis methods.

Method	Sample size	Feature variables	Average accuracy	Cost time
SSA and BP-ANN [18]	Training: 336; Testing: 144	4 singular values	96.53%	—
		3 energy features	95.14%	—
Multiscale entropy and SVM [23]	Training: 525; Testing: 237	6 entropies at different time scale	97.42%	—
Envelope spectra and SVM [24]	Training: 60; Testing: 20	3 fault characteristic frequencies in the envelope spectra	100%	76.68 s
LCD-SVD and LSSVM	Training: Testing:	8 singular values of ISCs	95.23%	146.13 s
LCD-SVD and VPMCD	Training: Testing:	8 singular values of ISCs	96.19%	12.84 s
LCD-SVD-ANN-MIV and LSSVM	Training: Testing:	4 singular values of ISCs	96.67%	67.42 s
LCD-SVD-ANN-MIV and VPMCD	Training: Testing:	4 singular values of ISCs	100%	0.1028 s