Table 5 Results of different fault diagnosis methods for motors
From: Motor Fault Diagnosis Based on Short-time Fourier Transform and Convolutional Neural Network
Method | Sample | Sample number | Diagnostic accuracy |
|---|---|---|---|
PCA + SVM | Time domain signal | 9100 | 30.52% |
EMD + SVM | Time domain signal | 9100 | 93.67% |
Diagnostic Features + SVM | Time domain signal | 9100 | 95.05% |
SDAE | Frequency signal | 9100 | 99.9048% |
STFT + CNN | Time spectrum diagram | 14000 | 100% |
Wavelet + CNN | Time spectrum diagram | 14000 | 100% |