An artificial neural network approach for generating high-resolution designs from low-resolution input in topology optimization

Nicholas Napier, Sai Aksharah Sriraman, Huy Trong Tran, Kai A. James

Research output: Contribution to journalArticlepeer-review

Abstract

We address a central issue that arises within element-based topology optimization. To achieve a sufficiently well-defined material interface, one requires a highly refined finite element mesh; however, this leads to an increased computational cost due to the solution of the finite element analysis problem. By generating an optimal structure on a coarse mesh and using an artificial neural network to map this coarse solution to a refined mesh, we can greatly reduce computational time. This approach resulted in time savings of up to 85% for test cases considered. This significant advantage in computational time also preserves the structural integrity when compared with a fine-mesh optimization with limited error. Along with the savings in computational time, the boundary edges become more refined during the process, allowing for a sharp transition from solid to void. This improved boundary edge can be leveraged to improve the manufacturability of the optimized designs.

Original languageEnglish (US)
Article number011402
JournalJournal of Mechanical Design, Transactions of the ASME
Volume142
Issue number1
DOIs
StatePublished - Jan 2020

Keywords

  • Artificial neural networks
  • Design for manufacturing
  • Design visualization
  • Machine learning
  • Topology optimization

ASJC Scopus subject areas

  • Mechanics of Materials
  • Mechanical Engineering
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'An artificial neural network approach for generating high-resolution designs from low-resolution input in topology optimization'. Together they form a unique fingerprint.

Cite this