Discrete Cosine Transformation and Temporal Adjacent Convolutional Neural Network-Based Remaining Useful Life Estimation of Bearings

<div>Architecture of sparse TACNN for RUL estimation. This architecture consists of three convolution layers and two fully connected layers. Detailed descriptions are given in the text.</div>

Shock and Vibration

fig4

Figure 4

Figure 4: Discrete Cosine Transformation and Temporal Adjacent Convolutional Neural Network-Based Remaining Useful Life Estimation of Bearings 