Towards a Hierarchical Approach for Outlier Detection inIndustrial Production Settings

Hoppenstedt, Burkhard and Reichert, Manfred and Kammerer, Klaus and Spiliopoulou, Myra and Pryss, Rüdiger (2019) Towards a Hierarchical Approach for Outlier Detection inIndustrial Production Settings. In: EDBT/ICDT 2019 Workshops, 26 March 2019, Lisbon.

[img] PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://ceur-ws.org/Vol-2322/


In the context of Industry 4.0, the degree of cross-linking be-tween machines, sensors, and production lines increases rapidly.However, this trend also offers the potential for the improve-ment of outlier scores, especially by combining outlier detectioninformation between different production levels. The latter, inturn, offer various other useful aspects like different time seriesresolutions or context variables. When utilizing these aspects,valuable outlier information can be extracted, which can be thenused for condition-based monitoring, alert management, or pre-dictive maintenance. In this work, we compare different typesof outlier detection methods and scores in the light of the afore-mentioned production levels with the goal to develop a modelfor outlier detection that incorporates these production levels.The proposed model, in turn, is basically inspired by a use casefrom the field of additive manufacturing, which is also known asindustrial 3D-printing. Altogether, our model shall improve thedetection of outliers by the use of a hierarchical structure thatutilizes production levels in industrial scenarios.

Item Type:Conference or Workshop Item (Paper)
Subjects:DBIS Research > Publications
ID Code:1749
Deposited By: Herr Burkhard Hoppenstedt
BibTex Export:BibTeX
Deposited On:08 Mar 2019 13:43
Last Modified:25 Apr 2019 15:44

Repository Staff Only: item control page