An Integrated Health Condition Detection Method for Rotating Machinery Using Refined Composite Multivariate Multiscale Amplitude-Aware Permutation Entropy

Table 8

The diagnostic results gained by combining diverse methods with four classifiers.

Diverse classifiers	The testing accuracy of classifiers with diverse approaches (%)					Average accuracy (%)
	RCmvMAAPE (%)	RCmvMPE (%)	mvMAAPE (%)	RCmvMSE (%)	RCMAAPE (%)
ELM	93.75	91.67	83.33	87.50	85.42	88.33
SVM	91.67	89.58	79.17	87.50	83.33	86.25
KELM	97.92	93.75	87.50	89.58	85.42	90.83
WOA-KELM	100	95.83	89.58	93.75	87.50	93.33
Average accuracy (%)	95.84	92.71	84.90	89.58	85.42	—