A New Deep Convolutional Domain Adaptation Network for Bearing Fault Diagnosis under Different Working Conditions

<div>The t-SNE visualization of two domains in last layer features by five different methods in the task N1⟶N2. Ten colors represent ten health conditions, S and T denote the classes in the source domain data and target domain data, respectively, and the five network models are (a) CNN, (b) TCA, (c) DDC, (d) DCDAN-WDC, and (e) DCDAN.</div>

Shock and Vibration

fig6

Figure 6

Figure 6: A New Deep Convolutional Domain Adaptation Network for Bearing Fault Diagnosis under Different Working Conditions 