Fatigue cracks are an inherent part in the lightweight design of engineering structures subjected to non-constant loads. Particularly important for airframe structures are accurate design data for crack initiation, stable fatigue crack propagation (FGP) and its rapid increase until ultimate failure. Non-straight crack paths are difficult or time-consuming to detect and monitor in laboratory experiments as well as in service using traditional techniques such as direct current potential drop (DCPD) or dye penetrant inspection.

We implemented a deep convolutional neural network (CNN) to detect crack paths and especially their crack tips based on full-field displacement data obtained by 3D digital image correlation (DIC). To this purpose, fatigue crack propagation experiments were performed for AA2024-T3 rolled sheet materials using 160 mm and 950 mm wide MT specimens. During the experiments, several hundred datasets were acquired by DIC and labelled by optical analysis. A part of the displacement data from one of the specimens was then used to train the neural network. The results show that the method can accurately detect the shape and evolution of cracks in all specimens based on the x and y displacements.