Table 3 Results of several methods' categorization using the CWRU dataset
From: A fault diagnosis method for rolling bearings based on graph neural network with one-shot learning
Model | Accuracy of each test (%) | Mean (%) | ||||
|---|---|---|---|---|---|---|
1 | 2 | 3 | 4 | 5 | ||
Siamese Net | 85.82 | 87.79 | 88.97 | 87.20 | 87.33 | 87.42 |
Matching Net | 84.57 | 84.59 | 83.79 | 87.12 | 86.40 | 85.29 |
Prototypical Net | 86.53 | 82.54 | 84.59 | 87.25 | 81.67 | 84.52 |
SAE | 87.32 | 90.23 | 86.37 | 85.46 | 89.12 | 87.70 |
GNN | 96.73 | 97.82 | 99.63 | 98.12 | 97.79 | 98.02 |