Learning Demonstrator for Anomaly Detection in Distributed Energy Generation

6 Pages Posted: 7 Apr 2022

See all articles by Timo Pelchen

Timo Pelchen

Fraunhofer IPK

Gregor Thiele

Fraunhofer IPK

Axel Vick

Fraunhofer IPK

David Schade

AUCOTEAM GmbH

Jörg Krüger

Technische Universitat Berlin

Marcel Radke

Fraunhofer IPK

Date Written: April 4, 2022

Abstract

Machine learning based anomaly detection methods on process data can be used to secure critical infrastructure. The design and installation of these methods require detailed understanding of both the facilities and the machine learning methods. Therefore, they are mostly incomprehensible for non-experts and thus acting as a barrier hindering the fast spread of such technologies. This article presents the systematic development of a demonstrator which enables presentations of anomaly detection on the example of a simulated wind farm. The specially designed user-interface allows a comprehensive experience. This article documents the use of the demonstrator for experts experienced in energy systems which are interested in the application of machine learning algorithms.

Keywords: Anomaly Detection, Learning Factories, Distributed Energy Generation, Modelica,Functional Mock-up Interface

Suggested Citation

Pelchen, Timo and Thiele, Gregor and Vick, Axel and Schade, David and Krüger, Jörg and Radke, Marcel, Learning Demonstrator for Anomaly Detection in Distributed Energy Generation (April 4, 2022). 12th Conference on Learning Factories, Proceedings of the 12th Conference on Learning Factories (CLF 2022), Available at SSRN: https://ssrn.com/abstract=4075252

Timo Pelchen

Fraunhofer IPK ( email )

Axel Vick

Fraunhofer IPK ( email )

David Schade

AUCOTEAM GmbH ( email )

Storkower Straße 114
Berlin, DE Berlin 10407
Germany

Jörg Krüger

Technische Universitat Berlin ( email )

Berlin
Germany

Marcel Radke

Fraunhofer IPK ( email )

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
58
Abstract Views
290
Rank
660,138
PlumX Metrics