Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Evaluation of Model-Based Condition Monitoring Systems in Industrial Application Cases

: Windmann, Stefan; Eickmeyer, Jens; Jungbluth, Florian; Badinger, Johann; Niggemann, Oliver


Niggemann, Oliver (Ed.); Beyerer, Jürgen (Ed.):
Machine Learning for Cyber Physical Systems : Selected papers from the International Conference ML4CPS 2015
Berlin: Springer Vieweg, 2016 (Technologien für die intelligente Automation 1)
ISBN: 978-3-662-48836-2 (print)
ISBN: 978-3-662-48838-6 (online)
Conference on Machine Learning for Cyber Physical Systems and Industry 4.0 (ML4CPS) <1, 2015, Lemgo>
Conference Paper
Fraunhofer IOSB ()

In this paper, model-based condition monitoring methods are investigated. Reliable process monitoring allows costs and risks to be reduced by the early detection of faults and problems in the process behavior and the prevention of component failures or in extreme cases a production stop of the complete plant. The principal of model-based condition monitoring consists of comparing the actual process behavior with the behavior as predicted from process models. For this purpose, a Hidden Markov Model and a method based on principal component analysis are applied. Both methods are evaluated in industrial application cases. In doing so, F-measures of 88:25% and 98:84% are achieved for a wind power station and a glue production plant, respectively.