Fault Diagnosis of Rotating Machinery Based on Multisensor Information Fusion Using SVM and Time-Domain Features

Table 4

Diagnostic results of rolling bearing by using different features for fusion.

Feature	The best parameter		Diagnostic accuracy (%)
	𝐶	𝑔	Normal	Inner race defect	Outer race defect	Ball defect	All testing samples
Mean	2^−3	2^15	100	100	100	100	100
Peak	2^3	2^7	94.29	94.29	100	100	97.14
Amplitude square	2^−3	2^5	100	100	100	100	100
Root mean square	2^4.5	2^15	100	100	100	100	100
Root amplitude	2^−2	2^15	100	100	100	100	100
Standard deviation	2^4.5	2^15	100	100	100	100	100
Skewness	2^2	2^4	65.71	84.29	62.86	80	73.21
Kurtosis	2^6	2^−2	90.00	72.86	82.86	97.14	85.71
Waveform factor	2^2	2^9	81.43	70.00	80.00	98.57	82.50
Peak factor	2^3	2^−3	64.29	64.29	78.57	95.71	75.71
Pulse factor	2^2	2^−3	71.43	64.29	81.43	95.71	78.21
Margin factor	2^5	2^−4.5	71.43	68.57	80	95.71	78.93