Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature Learning

Table 1

Details of 1DCNN architecture used in experiments.

No.	Layer type	Kernel size	Stride	Kernel number	Output	Padding
1	Convolution1	32 × 1	8 × 1	32	253 × 32	Yes
2	Pooling1	2 × 1	2 × 1	32	126 × 32	No
3	Convolution2	3 × 1	2 × 1	64	124 × 64	Yes
4	Pooling2	2 × 1	2 × 1	64	62 × 64	No
5	Convolution3	3 × 1	2 × 1	64	60 × 64	Yes
6	Pooling3	2 × 1	2 × 1	64	30 × 64	No
7	Convolution4	3 × 1	1 × 1	64	28 × 64	Yes
8	Pooling4	2 × 1	2 × 1	64	14 × 64	No
9	Fully connected1	100		1	100 × 1
10	Fully connected2	64		1	64 × 1
11	Softmax	10		1	10