Publication

Material Prediction For Design Automation Using Graph Representation Learning

Presentation of this project at the 2022 IDETC-CIE Conference (Design Automation Track).

Abstract

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.

Download publication

Leveraging the expressive power of graphs in capturing multi-modal information, we propose a framework in which material prediction is posed as a node prediction task and is tackled through learning representations using graph neural networks. Motivated by the importance of material selection to support design automation, this unified framework can help designers select appropriate materials by providing part-level material suggestions given a product assembly.

As illustrated in Figure 1, the proposed framework consists of three main modules: feature encoding, graph construction, and learning framework.

Related Resources

Publication

01/01/2010

Making Shapes from Modules by Magnification

We present a distributed algorithm for creating a modular shape by…

Publication

01/01/2013

Community Enhanced Tutorials: Improving Tutorials with Multiple Demonstrations

Web-based tutorials are a popular help resource for learning how to…

Publication

01/01/2014

Wasserstein propagation for semi-supervised learning

Probability distributions and histograms are natural representations…

Article

02/17/2023

Research Conversations with Fope Bademosi

Fope Bademosi, Circular Economy and Construction Researcher, shares…

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