De-homogenization using Convolutional Neural Networks

1 code implementation • 10 May 2021 • Martin O. Elingaard, Niels Aage, J. Andreas Bærentzen, Ole Sigmund

This paper presents a deep learning-based de-homogenization method for structural compliance minimization.

3D architected isotropic materials with tunable stiffness and buckling strength

no code implementations • 2 Dec 2020 • Fengwen Wang, Ole Sigmund

This paper presents a class of 3D single-scale isotropic materials with tunable stiffness and buckling strength obtained via topology optimization and subsequent shape optimization.

Numerical Analysis Computational Engineering, Finance, and Science Numerical Analysis Optimization and Control

Infill Optimization for Additive Manufacturing -- Approaching Bone-like Porous Structures

no code implementations • 15 Aug 2016 • Jun Wu, Niels Aage, Ruediger Westermann, Ole Sigmund

Our method builds upon and extends voxel-wise topology optimization.

Graphics