Figure 1.
Test rig system layout used to perform the real tests.
Figure 1.
Test rig system layout used to perform the real tests.
Figure 2.
Three-dimensional model of the test rig displaying the main components of the system, including the helical and spur gear pairs (contact surfaces between the bodies) and the coupler (hydraulic loading mechanism).
Figure 2.
Three-dimensional model of the test rig displaying the main components of the system, including the helical and spur gear pairs (contact surfaces between the bodies) and the coupler (hydraulic loading mechanism).
Figure 3.
Numerical model of the test rig system considering the contact between the meshing surfaces of the gear teeth of the helical gear pair (right side) and the spur gear pair (left side), where the main analysis is performed for the healthy system and cases of damage.
Figure 3.
Numerical model of the test rig system considering the contact between the meshing surfaces of the gear teeth of the helical gear pair (right side) and the spur gear pair (left side), where the main analysis is performed for the healthy system and cases of damage.
Figure 4.
Elements and positions for the dynamic FEM simulations of the cases of damage. The axial reference axis was considered in three different positions (AD1, AD2, and AD3), representing the axial location of the damage, while each axial position location considered five different elements representing the severity of damage (ELEMs 1, 2, 3, 4, and 5).
Figure 4.
Elements and positions for the dynamic FEM simulations of the cases of damage. The axial reference axis was considered in three different positions (AD1, AD2, and AD3), representing the axial location of the damage, while each axial position location considered five different elements representing the severity of damage (ELEMs 1, 2, 3, 4, and 5).
Figure 5.
Deformed view of (a) medium and (b) severe damages of the first multi-class classification case.
Figure 5.
Deformed view of (a) medium and (b) severe damages of the first multi-class classification case.
Figure 6.
Deformed view of damages (a) 1 and (b) 2 of the second multi-class classification case.
Figure 6.
Deformed view of damages (a) 1 and (b) 2 of the second multi-class classification case.
Figure 7.
Deformed view of damages (a) 3 and (b) 4 of the second multi-class classification case.
Figure 7.
Deformed view of damages (a) 3 and (b) 4 of the second multi-class classification case.
Figure 8.
Simulation data organization for the first case (classification approach).
Figure 8.
Simulation data organization for the first case (classification approach).
Figure 9.
Simulation data organization for the second case (first multi-class classification approach).
Figure 9.
Simulation data organization for the second case (first multi-class classification approach).
Figure 10.
Simulation data organization for the third case (second multi-class classification approach).
Figure 10.
Simulation data organization for the third case (second multi-class classification approach).
Figure 11.
Points representing each object location from the simulated model of the test bench (tangential shaft surface). The first step aimed at the extraction of the displacements from each point, while the second step aimed at the extraction of the vibrations after a double integration.
Figure 11.
Points representing each object location from the simulated model of the test bench (tangential shaft surface). The first step aimed at the extraction of the displacements from each point, while the second step aimed at the extraction of the vibrations after a double integration.
Figure 12.
Example of a Neural Network Pattern Recognition for damage presence (classification). is the weight and is the bias, which are the learnable parameters of the ANN model.
Figure 12.
Example of a Neural Network Pattern Recognition for damage presence (classification). is the weight and is the bias, which are the learnable parameters of the ANN model.
Figure 13.
Example of a Neural Network Pattern Recognition for damage severity (multi-class classification). is the weight and is the bias, which are the learnable parameters of the ANN model.
Figure 13.
Example of a Neural Network Pattern Recognition for damage severity (multi-class classification). is the weight and is the bias, which are the learnable parameters of the ANN model.
Figure 14.
Example of target file for a classification problem.
Figure 14.
Example of target file for a classification problem.
Figure 15.
Example of target file for a multi-class classification problem.
Figure 15.
Example of target file for a multi-class classification problem.
Figure 16.
Example of signals for the classification problem in the (a) time and (b) frequency domains. Both domains show comparisons of vibrational spectra on a bearing between a healthy transmission and a damaged one.
Figure 16.
Example of signals for the classification problem in the (a) time and (b) frequency domains. Both domains show comparisons of vibrational spectra on a bearing between a healthy transmission and a damaged one.
Figure 17.
Example of signals for the multi-class classification problems in the (a) time and (b) frequency domains. Both domains show comparisons of vibrational spectra on a bearing between a healthy transmission and cases of damage.
Figure 17.
Example of signals for the multi-class classification problems in the (a) time and (b) frequency domains. Both domains show comparisons of vibrational spectra on a bearing between a healthy transmission and cases of damage.
Figure 18.
The detection performances of the ANN for Test 1. The results provided responses for the training, validation, and test phases.
Figure 18.
The detection performances of the ANN for Test 1. The results provided responses for the training, validation, and test phases.
Figure 19.
Plots of the results for Test 1. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 19.
Plots of the results for Test 1. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 20.
The detection performances of the ANN for Test 2. The results provided responses for the training, validation, and test phases.
Figure 20.
The detection performances of the ANN for Test 2. The results provided responses for the training, validation, and test phases.
Figure 21.
Plots of the results for Test 2. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 21.
Plots of the results for Test 2. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 22.
The detection performances of the ANN for Test 3. The results provided responses for the training, validation, and test phases.
Figure 22.
The detection performances of the ANN for Test 3. The results provided responses for the training, validation, and test phases.
Figure 23.
Plots of the results for Test 3. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 23.
Plots of the results for Test 3. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 24.
The detection performances of the ANN for Test 4. The results provided responses for the training, validation, and test phases.
Figure 24.
The detection performances of the ANN for Test 4. The results provided responses for the training, validation, and test phases.
Figure 25.
Plots of the results for Test 4. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 25.
Plots of the results for Test 4. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 26.
The detection performances of the ANN for Test 5. The results provided responses for the training, validation, and test phases.
Figure 26.
The detection performances of the ANN for Test 5. The results provided responses for the training, validation, and test phases.
Figure 27.
Plots of the results for Test 5. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 27.
Plots of the results for Test 5. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 28.
The detection performances of the ANN for Test 6. The results provided responses for the training, validation, and test phases.
Figure 28.
The detection performances of the ANN for Test 6. The results provided responses for the training, validation, and test phases.
Figure 29.
Plots of the results for Test 6. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 29.
Plots of the results for Test 6. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 30.
The detection performances of the ANN for Test 7. The results provided responses for the training, validation, and test phases.
Figure 30.
The detection performances of the ANN for Test 7. The results provided responses for the training, validation, and test phases.
Figure 31.
Plots of the results for Test 7. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 31.
Plots of the results for Test 7. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 32.
The detection performances of the ANN for Test 8. The results provided responses for the training, validation, and test phases.
Figure 32.
The detection performances of the ANN for Test 8. The results provided responses for the training, validation, and test phases.
Figure 33.
Plots of the results for Test 8. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 33.
Plots of the results for Test 8. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 34.
The detection performances of the ANN for Test 9. The results provided responses for the training, validation, and test phases.
Figure 34.
The detection performances of the ANN for Test 9. The results provided responses for the training, validation, and test phases.
Figure 35.
Plots of the results for Test 9. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Figure 35.
Plots of the results for Test 9. The (a) validation performance, (b) error histogram, and (c) training state of the ANN provided responses for the training, validation, and test phases.
Table 1.
Test bench parameters.
Table 1.
Test bench parameters.
Parameters | Symbol | Stage 1 (Service Gearbox) | Stage 2 (Test Gearbox) | Units |
---|
Helical Gear 1 | Helical Gear 2 | Spur Gear 1 | Spur Gear 2 |
---|
Center distance | | 91.5 | 91.5 | mm |
Face width | | 80 | 14 | mm |
N° of teeth | | 34 | 36 | 17 | 18 | - |
Normal module | | 2.5 | 5.0 | mm |
Mass | | 3.1 | 3.3 | 3.1 | 3.3 | |
Moment of inertia | | 0.0122 | 0.0146 | 0.0122 | 0.0146 | |
Pitch circle diameter | | 0.0888 | 0.0941 | 0.0888 | 0.0941 | |
Pressure angle | | 20 | 20 | |
Helix angle | | 12 | 0 | |
Contact ratio | | 1.0588 | 1.0588 | 1.0588 | 1.0588 | - |
Young’s modulus | | 200 | 200 | GPa |
Poisson’s ratio | | 0.3 | 0.3 | - |
Table 2.
Damage index.
Set of Simulations |
---|
Damage Index | Axial Dimension (AD) Longitudinal | Radial Dimension (RD) |
---|
Nº Elements | Clearance (0 mm) |
---|
Crack 1 | 1 | ✓ |
Crack 2 | 2 | ✓ |
Crack 3 | 3 | ✓ |
Crack 4 | 4 | ✓ |
Crack 5 | 5 | ✓ |
Simulated Systems | Damages |
1 | No crack | - |
2 | Pos 1-AD1 | Crack 1 |
3 | Pos 2-AD1 | Crack 2 |
4 | Pos 3-AD1 | Crack 3 |
5 | Pos 4-AD1 | Crack 4 |
6 | Pos 5-AD1 | Crack 5 |
7 | Pos 6-AD2 | Crack 1 |
8 | Pos 7-AD2 | Crack 2 |
9 | Pos 8-AD2 | Crack 3 |
10 | Pos 9-AD2 | Crack 4 |
11 | Pos 10-AD2 | Crack 5 |
12 | Pos 11-AD3 | Crack 1 |
13 | Pos 12-AD3 | Crack 2 |
14 | Pos 13-AD3 | Crack 3 |
15 | Pos 14-AD3 | Crack 4 |
16 | Pos 15-AD3 | Crack 5 |
Table 3.
Important parameters from the “nprtool” interface.
Table 3.
Important parameters from the “nprtool” interface.
Neural Pattern Recognition (nprtool) |
---|
Results | Samples | CE | %E |
---|
Training | 81 | 0.794494 | 1.60494 |
Validation | 27 | 1.56895 | 1.85185 |
Testing | 27 | 1.58625 | 3.33333 |
Table 4.
Confusion Matrix Guide—Classification Method.
Table 4.
Confusion Matrix Guide—Classification Method.
Confusion Matrix Guide—Classification Method |
---|
Total Number of Objects (n) = 360 | Predicted: No Damage (0) | Predicted: Damage (1) | Actual Objects (a) |
---|
Actual (0) | TN = 175 | FP = 4 | a1 = TN + FP = 179 | a = a1 + a2 = n = 360 |
Actual (1) | FN = 5 | TP = 176 | a2 = FN + TP = 181 |
Predicted Objects (p) | p1 = TN + FN = 180 | p2 = FP + TP = 180 | |
| p = p1 + p2 = n = 360 | |
Label 1 |
True Negative (TN) | Predicted no damage: yes, and there is no damage. |
True Positive (TP) | Predicted damage: yes, and there is damage. |
False Negative (FN) | Predicted no damage: yes, and there is damage. |
False Positive (FP) | Predicted damage: yes, and there is no damage. |
Label 2 |
Accuracy Index | What is the percentage of correct results for the classifier? |
(TN + TP)/n = (175 + 176)/360 = 0.975 = 97.5% |
Misclassification Index | What is the percentage of wrong results for it? |
(FP + FN)/n = (4 + 5)/360 = 0.025 = 2.5% |
True-Positive Index | When it is actually (1), what is the percentage of damage (1) prediction for it? |
TP/a2 = 176/181 = 0.972 = 97.2% |
False-Positive Index | When it is actually (0), what is the percentage of damage (1) prediction for it? |
FP/a1 = 4/179 = 0.022 = 2.2% |
True-Negative Index | When it is actually (0), what is the percentage of no damage (0) prediction for it? |
TN/a1 = 175/179 = 0.978 = 97.8% |
False-Negative Index | When it is actually (1), what is the percentage of no damage (0) prediction for it? |
FN/a2 = 5/181 = 0.028 = 2.8% |
Precision Index (0) | When it predicts no damage (0), what is the percentage of correct results for it? |
TN/p1 = 175/180 = 0.972 = 97.2% |
No-Precision Index (0) | When it predicts no damage (0), what is the percentage of wrong results for it? |
FN/p1 = 5/180 = 0.028 = 2.8% |
Precision Index (1) | When it predicts damage (1), what is the percentage of correct results for it? |
TP/p2 = 85/90 = 0.978 = 97.8% |
No-Precision Index (1) | When it predicts damage (1), what is the percentage of wrong results for it? |
FP/p2 = 5/90 = 0.022 = 2.2% |
Table 5.
Confusion Matrix Guide—Multi-Class Classification Method.
Table 5.
Confusion Matrix Guide—Multi-Class Classification Method.
Confusion Matrix Guide—Multi-Class Classification Method |
---|
Number of Objects (n) = 135 | Predicted: No Damage (1) | Predicted: Medium Damage (2) | Predicted: Severe Damage (3) | Actual Objects (a) |
---|
Actual (1) | TND11 = 42 | FMD12 = 0 | FSD13 = 3 | a1 = TND11 + FMD12 + FSD13 = 45 | a = a1 + a2 + a3 = n = 135 |
Actual (2) | FND21 = 1 | TMD22 = 45 | FSD23 = 1 | a2 = FND21 + TMD22 + FSD23 = 47 |
Actual (3) | FND31 = 2 | FMD32 = 0 | TSD33 = 41 | a3 = FND31 + FMD32 + TSD33 = 43 |
Predicted Objects (p) | p1 = TND11 + FND21 + FND31 = 45 | p2 = FMD12 + TMD22 + FMD32 = 45 | p3 = FSD13 + FSD23 + TSD33 = 45 | |
| p = p1 + p2 + p3 = n = 135 | | |
Label 1 |
True No Damage (TND11) | Predicted no damage: yes, and there is no damage. |
False No Damage (FND21) | Predicted no damage: yes, and there is damage. |
False No Damage (FND31) | Predicted no damage: yes, and there is damage. |
False Medium Damage (FMD12) | Predicted medium damage: yes, and there is no damage. |
True Medium Damage (TMD22) | Predicted medium damage: yes, and there is damage. |
False Medium Damage (FMD32) | Predicted medium damage: yes, and there is no damage. |
False Severe Damage (FSD13) | Predicted severe damage: yes, and there is no damage. |
False Severe Damage (FSD23) | Predicted severe damage: yes, and there is no damage. |
True Severe Damage (TSD33) | Predicted severe damage: yes, and there is damage. |
Label 2 |
Accuracy Index | What is the percentage of correct results for the classifier? |
(TND11 + TMD22 + TSD33)/n = (42 + 45 + 41)/135 = 0.948 = 94.8% |
Misclassification Index | What is the percentage of wrong results for it? |
(FND21 + FND31 + FMD12 + FMD32 + FSD13 + FSD23)/n = (1 + 2 + 0 + 0 + 3 + 1)/135 = 0.052 = 5.2% |
True No Damage Index | When it is actually (1), what is the percentage of no damage (1) prediction for it? |
TND11/a1 = 42/45 = 0.933 = 93.3% |
False No Damage Index | When it is actually (1), what is the percentage of medium damage (2) and severe damage (3) predictions for it? |
(FMD12 + FSD13)/a1 = (0 + 3)/45 = 0.067 = 6.7% |
True Medium Damage Index | When it is actually (2), what is the percentage of medium damage (2) prediction for it? |
TMD22/a2 = 45/47 = 0.957 = 95.7% |
False Medium Damage Index | When it is actually (2), what is the percentage of no damage (1) and severe damage (3) predictions for it? |
(FND21 + FSD23)/a2 = (1 + 1)/47 = 0.043 = 4.3% |
True Severe Damage Index | When it is actually (3), what is the percentage of severe damage (3) prediction for it? |
TSD33/a3 = 41/43 = 0.953 = 95.3% |
False Severe Damage Index | When it is actually (3), what is the percentage of no damage (1) and medium damage (2) predictions for it? |
(FND31 + FMD32)/a3 = (2 + 0)/43 = 0.047 = 4.7% |
Precision Index (1) | When it predicts no damage (1), what is the percentage of correct results for it? |
TND11/p1 = 42/45 = 0.933 = 93.3% |
No-Precision Index (1) | When it predicts no damage (1), what is the percentage of wrong results for it? |
(FND21 + FND31)/p1 = (1 + 2)/45 = 0.067 = 6.7% |
Precision Index (2) | When it predicts medium damage (2), what is the percentage of correct results for it? |
TMD22/p2 = 45/45 = 1.000 = 100.0% |
No-Precision Index (2) | When it predicts medium damage (2), what is the percentage of wrong results for it? |
(FMD12 + FMD32)/p2 = (0 + 0)/45 = 0.000 = 0.0% |
Precision Index (3) | When it predicts severe damage (3), what is the percentage of correct results for it? |
TSD33/p3 = 41/45 = 0.911 = 91.1% |
No-Precision Index (3) | When it predicts severe damage (3), what is the percentage of wrong results for it? |
(FSD13 + FSD23)/p3 = (3 + 1)/45 = 0.089 = 8.9% |