Bearing Fault Diagnosis Based on Frequency Subbands Feature Extraction and Multibranch One-Dimension Convolutional Neural Network

Table 7

CNN branch HL.

Layer	Filters	Kernel size	Stride	Output size	Padding
Convolution; ReLU	16	16 × 1	2 × 1	128 × 16	Same
Convolution		4 × 1	2 × 1	63 × 16	Valid
Max pooling	24	4 × 1	1 × 1	63 × 24	Same
Convolution; ReLU		2 × 1	2 × 1	31 × 24
Max pooling		8 × 1	1 × 1	24 × 24	Valid
Convolution; ReLU	32	3 × 1	1 × 1	24 × 32	Same
Max pooling		2 × 1	2 × 1	12 × 32	Valid