Research Article
Development of Deep Convolutional Neural Network with Adaptive Batch Normalization Algorithm for Bearing Fault Diagnosis
Table 1
Structural parameters of the WFK-CNN.
| Number | Network layer | Convolution kernel size (step) | Number of convolution kernels | Output size (scale × depth) | Supplement |
| 1 | Convolution 1 | 64 × 1/16 × 1 | 16 | 128 × 16 | Y | 2 | Pooling 1 | 2 × 1/2 × 1 | 16 | 64 × 16 | N | 3 | Convolution 2 | 3 × 1/1 × 1 | 32 | 64 × 32 | Y | 4 | Pooling 2 | 2 × 1/2 × 1 | 64 | 32 × 32 | N | 5 | Convolution 3 | 3 × 1/1 × 1 | 64 | 32 × 64 | Y | 6 | Pooling 3 | 2 × 1/2 × 1 | 64 | 16 × 64 | N | 7 | Convolution 4 | 3 × 1/1 × 1 | 64 | 16 × 64 | Y | 8 | Pooling 4 | 2 × 1/2 × 1 | 64 | 8 × 64 | N | 9 | Convolution 5 | 3 × 1/1 × 1 | 64 | 6 × 64 | N | 10 | Pooling 5 | 2 × 1/2 × 1 | 64 | 3 × 64 | N | 11 | Full connection | 100 | 1 | 100 × 1 | | 12 | Softmax | 10 | 1 | 10 | |
|
|