Kofler, M., Lee, J., Zwar, J. M., & Elgeti, S. (2024, January 26). Microstructured Geometry Creation Using Deep Neural Networks [Poster Presentation]. TU Wien Science Day, Wien, Austria.
E317 - Institut für Leichtbau und Struktur-Biomechanik
-
Date (published):
26-Jan-2024
-
Event name:
TU Wien Science Day
en
Event date:
21-Feb-2024
-
Event place:
Wien, Austria
-
Keywords:
Variational Autoencoder; Microstructured Geometries; Signed Distance Function; Generative Design
en
Abstract:
Microstructured geometries, commonly found in natural materials like cork, honeycombs, or bone structures, can mimic complex material properties on the macroscale that homogeneous materials cannot achieve. However, optimizing these structures is challenging due to the one-to-many mapping from macroscale material properties to microscale geometries and the large difference in scale. Neural networks can improve this optimization process by reducing the complex design space to a low-dimensional and continuous latent space, thus making the design exploration more efficient.
en
Additional information:
Poster über die Erzeugung von mikrostrukturierten Geometrien mithilfe von neuronalen Netzen.
-
Research Areas:
Modeling and Simulation: 75% Computational Materials Science: 25%