Toward Automated Topology Optimization: Identification of Non-Design Features of CAD Models Using Graph Neural Networks

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

This paper presents an automated identification of non-design features of CAD models for topology optimization using learning-based segmentation. The CAD files are taken from a large database of industry-relevant components. Based on the geometry and topology of the components, a graph structure is created and processed by a deep neural network. The results show good match with real cases and can be continuously improved by training with additional data.
Original languageEnglish
Title of host publicationIndustrializing Additive Manufacturing : Proceedings of AMPA2023
EditorsChristoph Klahn, Mirko Meboldt, Julian Ferchow
Number of pages13
Place of PublicationCham
PublisherSpringer International Publishing AG
Publication date2024
Pages267-279
ISBN (print)978-3-031-42982-8
ISBN (electronic)978-3-031-42983-5
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event3th International Conference on Additive Manufacturing in Products and Applications - AMPA 2023 - ETH Zürich, Zürich, Switzerland
Duration: 12.09.202314.09.2023
Conference number: 3
https://ampa.ethz.ch/

Bibliographical note

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

    Research areas

  • Engineering - Design Automation, Topology Optimization, Graph Neural Networks