A Framework for Final Drive Simultaneous Failure Diagnosis Based on Fuzzy Entropy and Sparse Bayesian Extreme Learning Machine

Table 4

Comparison of paired strategy and one-to-all strategy.

Classifier	Decision threshold	Multiclass classification strategy	Accuracy (%)
			Single failures	Simultaneous failures	Entire sample
PNN	0.69	One-to-all	91.54 (±1.02)	88.22 (±1.55)	89.42 (±1.67)
		paired strategy	93.21 (±1.25)	89.14 (±1.76)	92.33 (±2.05)
SVM	0.69	One-to-all	92.02 (±2.35)	80.90 (±1.62)	84.70 (±1.87)
		paired strategy	94.84 (±1.75)	84.32 (±1.35)	88.92 (±2.14)
SBELM	0.72	One-to-all	95.13 (±1.22)	90.54 (±2.05)	92.94 (±1.73)
		paired strategy	98.42 (±1.41)	92.81 (±2.35)	96.23 (±1.59)