Classifying Component Function in Product Assemblies With Graph Neural Networks

This paper describes a method for representing design assembly data with relational assembly graphs, to enable learning via graph neural networks (GNN). The research focused on predicting the ‘function’ of parts in an assembly, for the purpose of providing more context in today’s design tools around the design intent of the designer. Our efforts in this paper can be a starting point for more sophisticated applications in knowledge-based CAD systems and Design-for-X consideration in function-based design, while supporting efforts such as Product Information Modeling.

This work was a collaboration between Autodesk Research Industry Futures and AI Lab groups, Oregon State University, and NIST.

Abstract

Classifying Component Function in Product Assemblies With Graph Neural Networks

Vincenzo Ferrero, Bryony DuPont, Kaveh Hassani, Daniele Grandi

Journal of Mechanical Design 2021

Function is defined as the ensemble of tasks that enable the product to complete the designed purpose. Functional tools, such as functional modeling, offer decision guidance in the early phase of product design, where explicit design decisions are yet to be made. Function-based design data is often sparse and grounded in individual interpretation. As such, function-based design tools can benefit from automatic function classification to increase data fidelity and provide function representation models that enable function-based intelligent design agents. Function-based design data is commonly stored in manually generated design repositories. These design repositories are a collection of expert knowledge and interpretations of function in product design bounded by function-flow and component taxonomies. In this work, we represent a structured taxonomy-based design repository as assembly-flow graphs, then leverage a graph neural network (GNN) model to perform automatic function classification. We support automated function classification by learning from repository data to establish the ground truth of component function assignment. Experimental results show that our GNN model achieves a micro-average F1-score of 0.617 for tier 1 (broad), 0.624 for tier 2, and 0.415 for tier 3 (specific) functions. Given the imbalance of data features and the subjectivity in the definition of product function, the results are encouraging. Our efforts in this paper can be a starting point for more sophisticated applications in knowledge-based CAD systems and Design-for-X consideration in function-based design.