Zustandsdiagnose von Maschinen im Kontext von Industrie 4.0 unter Einsatz von Data-Mining Methoden
DFX 2016: Proceedings of the 27th Symposium Design for X, 5-6 October 2016, Jesteburg, Germany
Year: 2016
Editor: Dieter Krause, Kristin Paetzold, Sandro Wartzack
Author: Küstner(1), Christof; Mitsch(1), Jürgen; Hegwein(1), Matthias; Fröhlich(2), Moritz; Meintker(2), Nico; Mönks(2), Konrad; Wartzack(1), Sandro
Series: DfX
Institution: Friedrich-Alexander-Universität Erlangen-Nürnberg(1), GE Jenbacher GmbH & Co OG(2)
Section: Industrie 4.0
Page(s): 169-180
ISBN: 978-3-946094-09-8
Abstract
Today, the machine industry offers a range of After-Sales-Services, including the installation and commissioning of the purchased products, the provision of spare parts, inspections or comprehensive maintenance contracts. Studies prove that After-Sales-Services often generate revenues that are several times higher than the original purchase price, which is why these services significantly contribute to a company's balance sheet. Worldwide operation of machines could lead to long machine downtimes before service technicians reach the operating site. Therefore, companies are interested in machine prognostics and predictive maintenance techniques. To accomplish this, an approach for condition-based maintenance in context of the internet of things and the use of data mining is presented in this contribution.
Keywords: condition-based maintenance, machine prognostics, internet of things, data mining