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

Figure 11

Feature visualization via t-SNE for domain shift of B ⟶ C: feature representations for original test signals, four convolutional layers, and two fully connected layers, respectively. (a) Original signal. (b) Conv1. (c) Conv2. (d) Conv3. (e) Conv4. (f) FC5 (g) FC6.

(a)

(b)

(c)

(d)

(e)

(f)

(g)