Research Article
Discrete Cosine Transformation and Temporal Adjacent Convolutional Neural Network-Based Remaining Useful Life Estimation of Bearings
Table 2
Topology of the sparse TACNN.
| Layer | Parameters and output channel size |
| Input | | Convolution | Kernel: , channel: 12, ReLU | Convolution | Kernel: , channel: 24, ReLU | Convolution | Kernel: , channel: 48, ReLU | Fully connected | , ReLU | Fully connected | , ReLU | Output | |
|
|