Table 11 Experimental accuracy comparison.
From: SCBM-Net: a multimodal feature fusion-based dual-channel method for bearing fault diagnosis
Model | Dataset | Accuracy (%) | Average accuracy (%) | |
|---|---|---|---|---|
CWRU | SEU | |||
VMD + CNN | √ | 82.00% | 56.78% | |
√ | 31.56% | |||
VMD + CNN-BiGRU | √ | 87.50% | 66.31% | |
√ | 45.11% | |||
VMD + CNN-BiGRU-Attention | √ | 97.50% | 76.42% | |
√ | 55.33% | |||
CWT + Swin transformer | √ | 99.33% | 98.50% | |
√ | 97.67% | |||
SCBM-Net | √ | 99.83% | 99.08% | |
√ | 98.33% | |||
