Table 1.
Essential parameters of the tested motor.
| PN (kW) | Pp (−) | nN (rpm) | TN (Nm) | IN (A) | J (kg . m2) | RS (Ω) | LS (mH) |
|---|---|---|---|---|---|---|---|
| 0.894 | 4 | 6,200 | 1.4 | 1.9 | 0.000039 | 4.6615 | 7.9835 |
Figure 1.
Block diagram (a) and photos (b) of experimental set-up. PMSM, permanent magnet synchronous motor.
Figure 2.
Control system diagram with measurement systems. PMSM, permanent magnet synchronous motor.
Table 2.
Types of individual failures and equations that enable their simulation.
| Type of the fault | Current value |
|---|---|
| Gain error | |
| Signal noise | |
| Signal loss |
Figure 3.
Sample transients with different types of faults – signal noise (a), gain error (b), and signal loss (c).
Figure 4.
Block diagram of the phase detection and localisation system based on Cri markers.
Figure 5.
Speed, current, and detector response waveforms in the standard version during periodic signal interruption in phases A (a) and B (b).
Figure 6.
Speed, current, and detector response waveforms in the modified version during periodic signal interruption in phases A (a) and B (b).
Figure 7.
Waveforms of speed, current, markers, marker differences, and detector response during signal loss in phases A (a) and B (b).
Figure 8.
Waveforms of speed, current, markers, marker differences, and detector response during signal noise in phases A (a) and B (b).
Figure 9.
Confusion matrices for the detector based on Cri markers for phases A (a) and B (b).
Table 3.
Parameters of training and testing data for the classifier based on MLP.
| Feature | Training data | Testing data |
|---|---|---|
| Number of samples | 380,010 | 228,006 |
| Speed | ±0.1ωref, ±0.2ωref, ±0.3ωref | ±0.075ωref, ±0.15ωref, ±0.225ωref |
| Motor load | 0.1 TN, 0.3 TN | 0.2 TN |
| Regenerative mode | 0.1 TN, 0.3 TN | 0.2 TN |
Figure 10.
Confusion matrices for the classifier based on MLP for phases A (a) and B (b) for the test data. MLP, multilayer perceptron.
Figure 11.
Speed, current, and classifier outputs transients during signal loss and signal noise for no-load conditions in phase A (a) and loaded motor conditions in phase B (b).
Figure 12.
Speed, current, and classifier outputs transients during faults in phase B.
Table 4.
Parameters of training and testing data for the classifier based on CNN.
| Feature | Training data | Testing data |
|---|---|---|
| Number of samples | 69,800 | 69,800 |
| Number of training examples | 698 | 698 |
| Speed | ±0.05ωref, ±0.1ωref, ±0.2ωref ±0.3ωref | ±0.07ωref, ±0.15ωref, ±0.25ωref ±0.35ωref |
| Motor load | 0.1 TN, 0.2 TN | 0.15 TN, 0.25 TN |
| Regenerative mode | 0.1 TN | 0.15 TN |
Table 5.
Structure of the CNN classifier network.
| Input layer: Matrix 40 × 10 | |||
| Feature detector | |||
| Convolutional layer 3 × 90 | Batch normalisation layer | Activation function: ReLu | MaxPooling layer |
| Padding method: same | Stride: 20 | ||
| Convolutional layer 3 × 120 | Batch normalisation layer | Activation function: ReLu | MaxPooling layer |
| Padding method: same | Stride: 2 | ||
| Convolutional layer 3 × 150 | Batch normalisation layer | Activation function: ReLu | MaxPooling layer |
| Padding method: same | Stride: 2 | ||
| Convolutional layer 3 × 180 | Batch normalisation layer | Activation function: ReLu | MaxPooling layer |
| Padding method: same | Stride: 2 | ||
| Classification | |||
| Fully connected layer (4) | Softmax layer | Classification layer | |
| Output layer: 1 – no fault, 2 – signal loss, 3 – signal noise, 4 – gain error | |||
Figure 13.
Confusion matrices for the classifier based on CNN for phases A (a) and B (b) for the test data.
Figure 14.
Speed, current, and classifier outputs transients during signal loss and load condition in phase A (a) and non-load condition in phase B (b).
Figure 15.
Speed, current, and classifier outputs transients during signal noise and gain error in regenerative mode conditions in phases A (a) and B (b).