Scalable anomaly detection in manufacturing systems using an interpretable deep learning approach

Schlegl, T; Schlegl, S; West, N; Deuse, J

Scalable anomaly detection in manufacturing systems using an interpretable deep learning approach

Schlegl, T Schlegl, S West, N Deuse, J

Permalink

Publisher:: Elsevier
Publication Type:: Conference Proceeding
Citation:: Procedia CIRP, 2021, 104, pp. 1547-1552
Issue Date:: 2021-01-01

Recently Added

	Filename	Description	Size
	1-s2.0-S2212827121011598-main.pdf	Published version	604.69 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is new to OPUS and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Schlegl, T
dc.contributor.author	Schlegl, S
dc.contributor.author	West, N
dc.contributor.author	Deuse, J https://orcid.org/0000-0003-4066-4357
dc.date	2021-09-22
dc.date.accessioned	2022-02-22T01:28:25Z
dc.date.available	2022-02-22T01:28:25Z
dc.date.issued	2021-01-01
dc.identifier.citation	Procedia CIRP, 2021, 104, pp. 1547-1552
dc.identifier.issn	2212-8271
dc.identifier.uri	http://hdl.handle.net/10453/154757
dc.description.abstract	Anomaly detection in manufacturing systems has great potential for the prevention of critical quality faults. In recent years, unsupervised deep learning has shown to frequently outperform conventional methods for anomaly detection. However, tuning, deploying and debugging deep learning models is a time-consuming task, limiting their practical applicability in manufacturing systems. We approach this problem by developing a deep learning model that learns interpretable shapes that can be used for anomaly detection in temporal process data. Application of the model to assembly tightening processes in the automotive industry shows a significant improvement in model interpretability and scalability.
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Procedia CIRP
dc.relation.ispartof	Conference on Manufacturing Systems
dc.relation.isbasedon	10.1016/j.procir.2021.11.261
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.rights	This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the 54th CIRP Conference on Manufacturing System 10.1016/j.procir.2021.11.261
dc.title	Scalable anomaly detection in manufacturing systems using an interpretable deep learning approach
dc.type	Conference Proceeding
utslib.citation.volume	104
utslib.location.activity	Athens, Greece
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
utslib.copyright.status	recently_added	*
pubs.consider-herdc	false
dc.date.updated	2022-02-22T01:28:24Z
pubs.finish-date	2021-09-24
pubs.place-of-publication	The Netherlands
pubs.publication-status	Published
pubs.start-date	2021-09-22
pubs.volume	104
dc.location	The Netherlands

Abstract:

Anomaly detection in manufacturing systems has great potential for the prevention of critical quality faults. In recent years, unsupervised deep learning has shown to frequently outperform conventional methods for anomaly detection. However, tuning, deploying and debugging deep learning models is a time-consuming task, limiting their practical applicability in manufacturing systems. We approach this problem by developing a deep learning model that learns interpretable shapes that can be used for anomaly detection in temporal process data. Application of the model to assembly tightening processes in the automotive industry shows a significant improvement in model interpretability and scalability.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/154757