Anomaly detection in the metal-textile industry for the reduction of the cognitive load of quality control workers

This paper presents an approach for reducing the cognitive load for humans working in quality control (QC) for production processes that adhere to the 6σ -methodology. While 100% QC requires every part to be inspected, this task can be reduced when a human-in-the-loop QC process gets supported by an anomaly detection system that only presents those parts for manual inspection that have a significant likelihood of being defective. This approach shows good results when applied to image-based QC for metal textile products.

Metadaten
Verfasserangaben:	Tobias Arndt, Max Conzen ORCiD, Ingo Elsen ORCiD, Alexander Ferrein ORCiD, Oskar Galla, Hakan Köse, Stefan Schiffer, Matteo Tschesche
DOI:	https://doi.org/10.1145/3594806.3596558
ISBN:	9798400700699
Titel des übergeordneten Werkes (Englisch):	PETRA '23: Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments
Verlag:	ACM
Dokumentart:	Konferenzveröffentlichung
Sprache:	Englisch
Erscheinungsjahr:	2023
Datum der Publikation (Server):	11.09.2023
Freies Schlagwort / Tag:	Anomaly detection; Datasets; Neural networks; Process optimization; Quality control
Erste Seite:	535
Letzte Seite:	542
Bemerkung:	PETRA '23: Proceedings of the 16th International Conference on Pervasive Technologies Related to Assistive Environments, Corfu Greece, July 5 - 7, 2023.
Link:	https://doi.org/10.1145/3594806.3596558
Zugriffsart:	campus
Fachbereiche und Einrichtungen:	FH Aachen / Fachbereich Elektrotechnik und Informationstechnik
collections:	Verlag / ACM

Open Access