Y ixuan Hou

Abstract

Through the combination of voids and micro-sized parts, additively manufactured metal lattice structures have significant advantages in weight reduction, thermal insulation, high specific strength, and energy damping, showing great potential in the aerospace, biomedical, and transportation industries. However, the surface defects, produced by the multiple phenomena during the additive manufacturing process, are the main origins of premature crack initiation and lead to early fatigue failure under cyclic loading. A thorough understanding of the fatigue behaviour for addittively manufactured micro-sized parts requires extensive full-scale fatigue testing, which is costly and time-consuming. This study focuses on estimating the fatigue life scatter of electron beam melting manufactured Ti-6Al-4V micro-sized parts using a combination of machine learning and finite element modelling. To this end, a generative adversarial network is trained to generate 2D surface profiles of the EBM-manufactured Ti-6Al-4V micro-sized parts based on X-ray tomography. Next, the regenerated 2D surface profiles are randomly used to construct 2D Finite Element models to detect the critical notches and get the stress gradients at the hot spot. Finally, Continuous Damage Mechanics and Theory of Critical Distance are implemented to estimate the fatigue lifetime. This way, hundreds of simulations are performed using regenerated surface profiles. The obtained results show that using both a generative adversarial network and finite element simulation makes it possible to numerically reproduce the scattered fatigue data, which is the inherent characteristic of additively manufactured materials.

Session