Advances, Systems and Applications
From: Bearing fault diagnosis method based on improved Siamese neural network with small sample
Method | Training set A | Training set B | Training set C | Training set D |
---|---|---|---|---|
1D CNN | 49.80% | 68.20% | 88.60% | 93.40% |
Prototype net | 60.20% | 74.60% | 82.50% | 90.30% |
Siamese net | 58.60% | 66.80% | 75.80% | 86.70% |
ISNN | 84.10% | 92.30% | 95.00% | 98.10% |