Comparative Study on Different Methods to Generate Synthetic Data for the Classification of THT Solder Joints

Thielen N, Rachinger B, Schröder F, Preitschaft A, Meier S, Seidel R, Reinhardt A, Franke J (2024)

Publication Type: Conference contribution

Publication year: 2024

Publisher: IEEE

City/Town: New York City

Conference Proceedings Title: 2024 1st International Conference on Production Technologies and Systems for E-Mobility (EPTS)

Event location: Bamberg DE

DOI: 10.1109/EPTS61482.2024.10586740

Abstract

Automated Optical Inspection (AOI) is still one of the major tools for the quality control of solder joints; especially, if the requirements for the solder joints' mechanical and electrical properties are high. This is the case for products in the automotive sector, e.g. air bags or brake systems. Conventional test routines are time-consuming to define and not flexible regarding quality limits and lead to a high amount of manual reinspection. Thus, Artificial Intelligence offers the potential to address these disadvantages. Artificial Intelligence, on the other hand, suffers from highly imbalanced datasets resulting from the low amount of defects on solder joint level. One possibility to face this challenge is the utilization of synthetic data. This work compares different methods to generate data using both conventional data augmentation and deep generative models as well as virtual world rendering in order to enhance dataset quality in general. These are applied to an industrial dataset of THT solder joints. All tested approaches lead to an improvement in model quality. The best results are achieved with synthetic images from a Generative Adversarial Network, relatively increasing performance by around 6 % while minimizing error slip.

Authors with CRIS profile

Nils Thielen Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik Ben Rachinger Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik Anja Preitschaft Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik Sven Meier Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik Reinhardt Seidel Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik Andreas Reinhardt Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik Jörg Franke Lehrstuhl für Fertigungsautomatisierung und Produktionssystematik

Additional Organisation(s)

Institute Materials for Electronics and Energy Technology (i-MEET)

How to cite

APA:

Thielen, N., Rachinger, B., Schröder, F., Preitschaft, A., Meier, S., Seidel, R.,... Franke, J. (2024). Comparative Study on Different Methods to Generate Synthetic Data for the Classification of THT Solder Joints. In 2024 1st International Conference on Production Technologies and Systems for E-Mobility (EPTS). Bamberg, DE: New York City: IEEE.

MLA:

Thielen, Nils, et al. "Comparative Study on Different Methods to Generate Synthetic Data for the Classification of THT Solder Joints." Proceedings of the 2024 1st International Conference on Production Technologies and Systems for E-Mobility, Bamberg New York City: IEEE, 2024.

BibTeX: Download