Engineers at the University of Illinois at Urbana-Champaign (UIUC) and Apple have developed physics-informed neural networking artificial intelligence to predict the performance of three-dimensionally-printed objects.
The researchers employed the Texas Advanced Computing Center's Frontera and Stampede2 supercomputers to replicate the dynamics of benchmark experiments involving one-dimensional solidification of solid and liquid metals, and laser beam melting tests.
UIUC's Qiming Zhu said, "This is the first time that neural networks have been applied to metal additive manufacturing process modeling. We showed that physics-informed machine learning, as a perfect platform to seamlessly incorporate data and physics, has big potential in the additive manufacturing field."
From Texas Advanced Computing Center
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found