De-homogenization using convolutional neural networks

DOI10.1016/j.cma.2021.114197OpenAlexW3209318200MaRDI QIDQ2060089

Niels Aage, Jakob Andreas Bærentzen, Ole Sigmund, Martin Ohrt Elingaard

Publication date: 13 December 2021

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.04232

zbMATH Keywords

topology optimizationconvolutional neural networksdeep learningde-homogenization

Mathematics Subject Classification ID

Topological methods for optimization problems in solid mechanics (74P15) Compliance or weight optimization in solid mechanics (74P05)

Related Items

Compliance minimisation of smoothly varying multiscale structures using asymptotic analysis and machine learning ⋮ Topology optimization via implicit neural representations ⋮ Phasor noise for dehomogenisation in 2D multiscale topology optimisation

Cites Work

• Unnamed Item
• Unnamed Item
• On projection methods, convergence and robust formulations in topology optimization
• Generating optimal topologies in structural design using a homogenization method
• Material interpolation schemes in topology optimization
• Topology optimization of modulated and oriented periodic microstructures by the homogenization method
• Deep generative modeling for mechanistic-based learning and design of metamaterial systems
• Universal machine learning for topology optimization
• Homogenization-based stiffness optimization and projection of 2D coated structures with orthotropic infill
• De-homogenization of optimal multi-scale 3D topologies
• A Post-Treatment of the Homogenization Method for Shape Optimization
• Advanced Lectures on Machine Learning