Geometric Deep Learning as an Enabler for Data Consistency and Interoperability in Manufacturing

Bründl P, Scheffler B, Straub C, Nguyen HG, Stoidner M, Franke J (2025)

Publication Status: Submitted

Publication Type: Unpublished / Preprint

Future Publication Type: Journal article

Publication year: 2025

Abstract

Skilled labor shortages and the growing trend for customized products are increasing the complexity of manufacturing systems. Automation is often proposed to address these challenges, but industries operating under the engineer-to-order, lot-size-one production model often face significant limitations due to the lack of relevant data. This study investigates a laser-based optical worker assistance system in control cabinet manufacturing to demonstrate how geometric deep learning can enable the digitization and automation of complex manufacturing processes. An approach is presented for the extraction of assembly-relevant information, using only vendor-independent STEP files, and the integration and validation of these information in an industrial use case. This approach improves data quality and facilitates data transferability to components not listed in leading ECAD databases, suggesting broader potential for generalization across different components and use cases. In addition, an end-to-end inference pipeline without proprietary formats ensures high data integrity while approximating the surface of the underlying topology, making it suitable for small and medium-sized companies with limited computing resources. The study not only achieves the accuracy required for full automation, but also introduces the Spherical Boundary Score (SBS), a metric for evaluating the quality of assembly-relevant information and its application in real-world scenarios.

Authors with CRIS profile

Patrick Bründl Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik Benedikt Scheffler Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik Huong Giang Nguyen Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik Micha Stoidner Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik Jörg Franke Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik

Involved external institutions

Universität Bayreuth

Germany (DE)

How to cite

APA:

Bründl, P., Scheffler, B., Straub, C., Nguyen, H.G., Stoidner, M., & Franke, J. (2025). Geometric Deep Learning as an Enabler for Data Consistency and Interoperability in Manufacturing. (Unpublished, Submitted).

MLA:

Bründl, Patrick, et al. Geometric Deep Learning as an Enabler for Data Consistency and Interoperability in Manufacturing. Unpublished, Submitted. 2025.

BibTeX: Download