Research Article
Improving Rolling Bearing Fault Diagnosis by DS Evidence Theory Based Fusion Model
Table 5
Comparisons of classification performances of different models.
| Bearing condition | Classification accuracy | LVQ | BP | LVQ-PCA | Decision tree | Tree pruning | Tree-PCA | DS fusion |
| Good, (%) | 70.0 | 9.1 | 87.5 | 85.5 | 86.2 | 82.4 | 90.4 | Outer race fault, (%) | 66.7 | 11.1 | 78.9 | 72.7 | 74.0 | 97.9 | 96.6 | Inner race fault, (%) | 100.0 | 90.0 | 100.0 | 90.7 | 92.1 | 79.4 | 94.9 | Average accuracy (%) | 78.9 | 36.7 | 88.8 | 83.0 | 84.1 | 86.6 | 94.0 | Time (s) | 2.3 | 1.6 | 1.5 | 2.6 | 2.0 | 1.3 | 4.2 |
|
|