Graph Machine Learning for Assembly Modeling

Carola Gajek, Alexander Schiendorfer, Wolfgang Reif

Abstract: Assembly modeling refers to the design engineering process of composing assemblies (e.g., machines or machine components) from a common catalog of existing parts. There is a natural correspondence of assemblies to graphs which can be exploited for services based on graph machine learning such as part recommendation, clustering/taxonomy creation, or anomaly detection. However, this domain imposes particular challenges such as the treatment of unknown or new parts, ambiguously extracted edges, incomplete information about the design sequence, interaction with design engineers as users, to name a few. Along with open research questions, we present a novel data set.

Type Of Submission: Extended abstract (max 4 main pages).

Agreement: Check this if you are okay with being contacted to participate in an anonymous survey.

Type Of Submission: Extended abstract.