A Deep Learning Framework for Damage Assessment of Composite Sandwich Structures

Figure 12

Experimental damage identified with the proposed CNN-based approach. Normalized damage sizes: (a) 0.09 (Case 1), (b) 0.12 (Case 2), (c) 0.14 and 0.07 (Case 3), and (d) 0.11 and 0.17 (Case 4). The red circles/squares denote the true damage region.

(a)

(b)

(c)

(d)