Skip to main content

Advances, Systems and Applications

Table 4 Network parameters of the proposed model

From: A multi-fault diagnosis method of gear-box running on edge equipment

Layertype

Kernel size

Stride

Kernel channel size

Output Size

Batch Normalization

Batch Input

∖

∖

∖

1000*1

∖

Convolution C1

32*1

2

32

485*32

Yes

Pooling P1

2*1

2

32

242*32

∖

Convolution C2

16*1

1

64

227*64

Yes

Pooling P2

2*1

2

64

113*64

∖

Convolution C3_1

8*1

1

32

106*32

Yes

Pooling P3_1

2*1

2

32

53*32

∖

Convolution C3_2

8*1

1

32

106*32

Yes

Pooling P3_2

2*1

2

32

53*32

∖

Fully-connected F1

100

∖

1,Dropout = 0.8

100*1

Yes

Fully-connected F2

100

∖

1,Dropout = 0.8

100*1

Yes

Softmax S1

5

∖

∖

5*1

∖

Softmax S2

6

∖

∖

6*1

∖