Material Prediction for Design Automation Using Graph Representation Learning

TL;DR

This paper presents a graph neural network-based framework for predicting suitable materials in assembly design, enhancing automated design processes by learning from existing CAD models and supporting scalable, knowledge-informed recommendations.

Contribution

It introduces a novel graph representation learning approach for material prediction in assemblies, leveraging GNNs to improve design automation tools.

Findings

Achieved a 0.75 top-3 micro-f1 score on the Fusion 360 dataset.

Demonstrated scalability to large datasets and integration of designer knowledge.

Serves as a baseline for future intelligent design recommendation systems.

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.