Research Article
Fault Diagnosis of Rotating Machinery Based on Multisensor Information Fusion Using SVM and Time-Domain Features
Table 6
Diagnostic results of rotor crack by using different features for fusion.
| Feature |
The best parameter | Diagnostic accuracy (%) | | | Normal | Crack depth of 3 mm | Crack depth of 5 mm | All testing samples |
| Mean | 24.5 | 212 | 98 | 94 | 100 | 98.67 | Peak | 20 | 29.5 | 72 | 86 | 88 | 85.33 | Amplitude square | 27 | 22 | 100 | 96 | 94 | 96.67 | Root mean square | 26 | 24 | 100 | 98 | 100 | 99.67 | Root amplitude | 25.5 | 23 | 100 | 92 | 100 | 97.33 | Standard deviation | 24 | 28 | 98 | 96 | 98 | 98.67 | Skewness | 25 | 2−2 | 58 | 44 | 46 | 58.00 | Kurtosis | 23.5 | 2−1 | 44 | 74 | 84 | 71.00 | Waveform factor | 22 | 23 | 34 | 80 | 84 | 72.33 | Peak factor | 22.5 | 2−1.5 | 42 | 46 | 62 | 69.33 | Pulse factor | 2−3 | 2−1 | 28 | 74 | 76 | 64.00 | Margin factor | 21 | 2−3 | 32 | 72 | 74 | 64.67 |
|
|