Research Area:  Internet of Things

Abstract:

Predictive maintenance is one of the most prominent use case of smart manufacturing in Industry4.0. Nevertheless, the development of predictive maintenance systems is still challenging as a result of the need to integrate multiple fragmented data sources, to research and apply advanced predictive analytics, and to close the loop to the field in order to provide actionable intelligence. The paper presents the architecture, design and practical implementation of an end-to-end system that addresses these challenges. The system has been successfully deployed in two factories and is positively evaluated in terms of its ability to reduce unscheduled downtimes and to provide increased Overall Equipment Efficiency (OEE).

Keywords:  

Author(s) Name:  Ioannis T. Christou,Nikos Kefalakis,Andreas Zalonis,John Soldatos,Raimund Bröchler

Publisher name:  Elsevier

DOI:  10.1016/j.ifacol.2020.11.028

Volume Information:  Volume 53, Issue 3, 2020, Pages 173-178

Paper Link:   https://www.sciencedirect.com/science/article/pii/S2405896320301725