Research Article
A Fault Diagnosis Method for Rotating Machinery Based on PCA and Morlet Kernel SVM
Table 3
The recognition rate of traditional RBF SVM and the MWSVM.
|
SVM type | Recognition rate /% | Normal state | 0.18 mm fault depth | 0.36 mm fault depth | 0.53 mm fault depth | 0.71 mm fault depth |
| Neural network | 90 | 96 | 94 | 93 | 90 | RBF kernel | 94 | 93 | 91 | 96 | 91 | Symlet wavelet kernel | 91 | 95 | 94 | 97 | 99 | db wavelet kernel | 90 | 98 | 96 | 92 | 90 | Gaussian kernel | 98 | 99 | 97 | 98 | 98 | MWSVM | 100 | 100 | 100 | 100 | 100 |
|
|