Research Article
A Fault Diagnosis Method of Rolling Mill Bearing at Low Frequency and Overload Condition Based on Integration of EEMD and GA-DBN
Table 4
Comparison of models for various input conditions.
| | Input | Model | Best accuracy (%) | Time (s) |
| | Time domain signals | DBN | 85.6 | 5427 | | Time domain features of vibration signals | DBN | 82.1 | 321 | | Time domain features of all signals | DBN | 92.5 | 403 | | Time domain signals | GA-DBN | 87.3 | 5803 | | Time domain features of vibration signals | GA-DBN | 85.0 | 357 | | Time domain features of all signals | GA-DBN | 98.3 | 431 |
|
|
