Results from using an Automl Tool for Error Analysis in Manufacturing

Alexander Gerling, Alexander Gerling, Alexander Gerling, Oliver Kamper, Christian Seiffer, Holger Ziekow, Ulf Schreier, Andreas Hess, Djaffar Abdeslam, Djaffar Abdeslam

2022

Abstract

Machine learning (ML) is increasingly used by various user groups to analyze product errors with data recorded during production. Quality engineers and production engineers as well as data scientists are the main users of ML in this area. Finding a product error is not a trivial task due to the complexity of today’s production processes. Products have often many features to check and they are tested in various stages in the production line. ML is a promising technology to analyze production errors. However, a key challenge for applying ML in quality management is the usability of ML tools and the incorporation of domain knowledge for non-experts. In this paper, we show results from using our AutoML tool for manufacturing. This tool makes the use of domain knowledge in combination with ML easy to use for non-experts. We present findings obtained with this approach along with five sample cases with different products and production lines. Within these cases, we discuss the occurred error origins that were found and show the benefit of a supporting AutoML tool.

Paper Citation

in Harvard Style

Gerling A., Kamper O., Seiffer C., Ziekow H., Schreier U., Hess A. and Abdeslam D. (2022). Results from using an Automl Tool for Error Analysis in Manufacturing. In Proceedings of the 24th International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 978-989-758-569-2, pages 100-111. DOI: 10.5220/0010998100003179

in Bibtex Style

@conference{iceis22,
author={Alexander Gerling and Oliver Kamper and Christian Seiffer and Holger Ziekow and Ulf Schreier and Andreas Hess and Djaffar Abdeslam},
title={Results from using an Automl Tool for Error Analysis in Manufacturing},
booktitle={Proceedings of the 24th International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2022},
pages={100-111},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010998100003179},
isbn={978-989-758-569-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 24th International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - Results from using an Automl Tool for Error Analysis in Manufacturing
SN - 978-989-758-569-2
AU - Gerling A.
AU - Kamper O.
AU - Seiffer C.
AU - Ziekow H.
AU - Schreier U.
AU - Hess A.
AU - Abdeslam D.
PY - 2022
SP - 100
EP - 111
DO - 10.5220/0010998100003179