Publication | ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference 2022
Material Prediction For Design Automation Using Graph Representation Learning
Presentation of this project at the 2022 IDETC-CIE Conference (Design Automation Track).
Following the Assembly Graph project, the paper represents CAD data with graphs in order to leverage Graph Neural Networks for a material prediction task of each part in the assemblies of the Fusion Gallery Dataset.
Download publicationAbstract
Material Prediction For Design Automation Using Graph Representation Learning
Shijie Bian, Daniele Grandi, Kaveh Hassani, Bingbing Li
ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference 2022
Successful material selection is critical in designing and manufacturing products for design automation. Designers leverage their knowledge and experience to create high-quality designs by selecting the most appropriate materials through performance, manufacturability, and sustainability evaluation. Intelligent tools can help designers with varying expertise by providing recommendations learned from prior designs. To enable this, we introduce a graph representation learning framework that supports the material prediction of bodies in assemblies. We formulate the material selection task as a node-level prediction task over the assembly graph representation of CAD models and tackle it using Graph Neural Networks (GNNs). Evaluations over three experimental protocols performed on the Fusion 360 Gallery dataset indicate the feasibility of our approach, achieving a 0.75 top-3 micro-F1 score. The proposed framework can scale to large datasets and incorporate designers’ knowledge into the learning process. These capabilities allow the framework to serve as a recommendation system for design automation and a baseline for future work, narrowing the gap between human designers and intelligent design agents.
As illustrated in Figure 1, the proposed framework consists of three main modules: feature encoding, graph construction, and learning framework.
Associated Researchers
Shijie Bian
University of California
Kaveh Hassani
Autodesk Research
Elliot Sadler
California State University, Northridge
Bodia Borijin
California State University, Northridge
Axel Fernandes
California State University, Northridge
Andrew Wang
Portola High School
Thomas Lu
Jet Propulsion Laboratory
Richard Otis
Jet Propulsion Laboratory
Nhut Ho
California State University, Northridge
Bingbing Li
California State University, Northridge
Related Resources
2024
A hyperreduced reduced basis element method for reduced-order modeling of component-based nonlinear systemsThis method balances accuracy and computational speed through adaptive…
2024
PlotMap: Automated Layout Design for Building Game WorldsThis research presents novel AI methods for mapping stories to maps in…
2017
Practical Aspects of the DesignDEVS Simulation EnvironmentDesignDEVS is a simulation development environment based on the…
2016
Faster Command Selection on Touchscreen WatchesSmall touchscreens worn on the wrist are becoming increasingly common,…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us