Classifying Component Function in Product Assemblies with Graph Neural Networks

TL;DR

This paper presents a graph neural network approach to automatically classify component functions in product assemblies, improving data fidelity in function-based design repositories and aiding early-stage product design decisions.

Contribution

It introduces a GNN model that leverages structured assembly-flow graphs for automatic function classification, enhancing the accuracy of function assignment in design repositories.

Findings

Achieved a micro-average F1-score of 0.832 for broad functions.

Achieved a micro-average F1-score of 0.756 for intermediate functions.

Achieved a micro-average F1-score of 0.783 for specific functions.

Abstract

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 F${_1}$-score of 0.832 for tier 1 (broad), 0.756 for tier 2, and 0.783 for tier 3 (specific) functions. Given the imbalance of data features, 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.