DL-MSTO+: a deep learning-based multi-scale topology optimization framework via positive definiteness ensured material representation network

DOI10.1016/J.CMA.2023.116276MaRDI QIDQ6096498zbMATH OpenFDO

Authors Minsik Seo, Seungjae Min

Publication date 12 September 2023

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

Full work available at URL https://doi.org/10.1016/J.CMA.2023.116276

zbMATH Keywords

deep learninghomogenizationmulti-scaleneural networkstopology optimization

Mathematics Subject Classification ID

Computer science (68-XX) Mechanics of deformable solids (74-XX)

Recommendations

• Structural topology optimization based on deep learning
• A complete physics-informed neural network-based framework for structural topology optimization
• Concurrent topology optimization of multiscale composites with differentiable microstructures
• Real-time topology optimization via learnable mappings

Cites work

• A review of homogenization and topology optimization I—homogenization theory for media with periodic structure
• A variational approach to the theory of the elastic behaviour of multiphase materials
• Concurrent multi-scale and multi-material topological optimization of vibro-acoustic structures
• Concurrent two-scale topological design of multiple unit cells and structure using combined velocity field level set and density model
• Deep generative modeling for mechanistic-based learning and design of metamaterial systems
• DOLFIN: automated finite element computing
• Generating optimal topologies in structural design using a homogenization method
• Materials with prescribed constitutive parameters: An inverse homogenization problem
• Nonlinear structural design using multiscale topology optimization. Part I: Static formulation
• On projection methods, convergence and robust formulations in topology optimization
• Topology optimization of fluid-structure-interaction problems in poroelasticity
• Visualizing data using t-SNE

Cited in

(4)

• Convolution hierarchical deep-learning neural network tensor decomposition (C-HiDeNN-TD) for high-resolution topology optimization
• A complete physics-informed neural network-based framework for structural topology optimization
• Machine learning in solid mechanics: application to acoustic metamaterial design
• CMA-ES-based topology optimization accelerated by spectral level-set-boundary modeling

This page was built for publication: DL-MSTO+: a deep learning-based multi-scale topology optimization framework via positive definiteness ensured material representation network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6096498)