Fraunhofer-Institut für Produktionsanlagen und Konstruktionstechnik IPK

Filters

3
Reset filters

Settings
Now showing 1 - 3 of 3
No Thumbnail Available
Publication

Learning Demonstrator for Anomaly Detection in Distributed Energy Generation

2022-04-07 , Pelchen, Timo , Thiele, Gregor , Vick, Axel , Radke, Marcel , Schade, David , Krüger, Jörg

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.

View
No Thumbnail Available
Publication

A practical approach to reduce energy consumption in a serial production environment by shutting down subsystems of a machine tool

2019 , Can, Alperen , Thiele, Gregor , Krüger, Jörg , Fisch, J. , Klemm, C.

Energy efficiency in production is becoming increasingly important for the automotive industry, motivated by political regulations and competitiveness. Many theoretical approaches to achieve an efficient production via advanced control have only been tested in experimental environments. Important for the transfer into serial production is the proof that all requirements (e.g. quantity and quality) will be met. For ensuring production on demand, machine tools (MT) imitate the real production process to keep themselves at operating temperature. All subsystems of a MT operate at full power in this state, disregarding its necessity. Shutting down these subsystems during non-productive periods is a promising approach for saving energy. This paper will present a method for shutting down components during non-productive periods, while ensuring the ability to produce on demand. Successful tests were already performed during live operation in a plant of a car manufacturer in Berlin, Germany.

View
No Thumbnail Available
Publication

Quantification and compensation of systematic errors in pressure measurements applied to oil pipelines

2018 , Thiele, Gregor , Liu, Martin , Chemnitz, Moritz , Krüger, Jörg

The monitoring of pipeline operation is an important research topic, especially for the detection and localization of leaks as well as for an efficient control. For these purposes, physical quantities in pipelines are calculated from measurement data on the basis of a mathematical model. In contrast to static models, adaptive models vary their parameters or even their structure to reach the most probable solution. But in most cases, even the best fit will hold residuals caused by discrepancies between the real system and its model. These residuals allow an estimation of travel-time delays of pressure waves and offsets in pressure values. The basic idea of our approach is to interpret these systematic, time-invariant errors of pressure measurements in pipelines either as sensor displacements or as technical defects. The proposed procedure leads to a hypothesis for a model update, regarding the sensor positions. This displacement compensation as well as a variance analysis was successfully applied to real data from a crude oil pipeline in Europe. A cross validation proves the general capability of the developed method to reduce the uncertainties.

View