Human-based segmentation of tomographic images can be a tedious time-consuming task. Deep learning algorithms and, particularly, convolutional neural networks have become state of the art techniques for pattern recognition in digital images that can replace human-based image segmentation. However, their use in materials science is beginning to be explored and their application needs to be adapted to the specific needs of this field. In the present work, a convolutional neural network is trained to segment the microstructural components of an Al-Si cast alloy imaged using synchrotron X-ray tomography. A pixel-wise weighted error function is implemented to account for microstructural features which are hard to identify in the tomographs and that play a relevant role for the correct description of the 3D architecture of the alloy investigated. The results show that the total operation time for the segmentation using the trained convolutional neural network was reduced to <1% of the time needed with human-based segmentation.
The occurrence of fatigue cracks is an inherent part of the design of engineering structures subjected to nonconstant loads. Thus, the accurate description of cracks in terms of location and evolution during service conditions is mandatory to fulfill safety‐relevant criteria. In the present work, we implement a deep convolutional neural network to detect crack paths together with their crack tips based on displacement fields obtained using digital image correlation. To this purpose, fatigue crack propagation experiments were performed for AA2024‐T3 rolled sheets using specimens with different geometries. Several hundred datasets were acquired by digital image correlation during the experiments. 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 the cracks in all specimens. Adding synthetic data generated by finite element analyses to the training step improved the accuracy for cracks with stress intensity factors that exceeded the range of the original training data.
Data-driven models based on deep learning have led to tremendous breakthroughs in classical computer vision tasks and have recently made their way into natural sciences. However, the absence of domain knowledge in their inherent design significantly hinders the understanding and acceptance of these models. Nevertheless, explainability is crucial to justify the use of deep learning tools in safety-relevant applications such as aircraft component design, service and inspection. In this work, we train convolutional neural networks for crack tip detection in fatigue crack growth experiments using full-field displacement data obtained by digital image correlation. For this, we introduce the novel architecture ParallelNets—a network which combines segmentation and regression of the crack tip coordinates—and compare it with a classical U-Net-based architecture. Aiming for explainability, we use the Grad-CAM interpretability method to visualize the neural attention of several models. Attention heatmaps show that ParallelNets is able to focus on physically relevant areas like the crack tip field, which explains its superior performance in terms of accuracy, robustness, and stability.
Digital image correlation (DIC) is a technique in experimental mechanics to acquire full-field measurement data of displacements and deformations from the surface of specimens or components. Especially for the investigations of cracks it provides additional benefits. The actually present deformation field in the vicinity of the crack tip can be obtained which directly reflects for example crack closure effects or plasticity. Against this background the paper summarizes a procedure to compute the J integral and the stress intensity factors K I and K II based on DIC data. For this purpose the J and interaction integral are computed as line and domain integrals. Through experiments it is shown that the domain integral is less affected by scatter of the DIC data. Furthermore, the specific domain, facet sizes and facet distances slightly influence the results.
Fatigue crack growth in 1.6-mm-thick sheets of aluminium alloy AA2024-T3 was investigated under very high-stress conditions using 950-mm-wide middle tension (MT) specimens. Experiments were conducted by applying uniaxial load ratios R (0.1, 0.3 and 0.5) with the maximum nominal stress of 120 MPa following conditions relevant for aircraft fuselage structures. The experiments were conducted with digital image correlation to determine loading conditions acting on the crack tip. Stable crack growth rates of up to da/dN > 4 mm/cycle and ΔK > 100 MPa√m were reached, and final crack lengths 2a > 500 mm were obtained. High-stress intensity factors cause plastic zone sizes that extend up to approximately 100 mm from the crack tip. The da/dN-ΔK data obtained in this study provide crucial information about the fatigue crack growth and damage tolerance of very long cracks under high-stress conditions in thin lightweight structures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.