Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A hybrid cloud-to-edge predictive maintenance platform

 
: Marguglio, Angelo; Veneziano, Giuseppe; Greco, Pietro; Jung, Sven; Siegburg, Robert; Schmitt, Robert H.; Monaco, Simone; Apiletti, Daniele; Nikolakis, Nikolaos; Cerquitelli, Tania; Macii, Enrico

:

Cerquitelli, Tania:
Predictive Maintenance in Smart Factories. Architectures, Methodologies, and Use-cases
Singapore: Springer Nature Singapore, 2021 (Information Fusion and Data Science)
ISBN: 978-981-16-2939-6 (Print)
ISBN: 978-981-16-2940-2 (Online)
ISBN: 978-981-16-2941-9
ISBN: 978-981-16-2941-9
pp.19-37
European Commission EC
H2020; 767561; SERENA
VerSatilE plug-and-play platform enabling remote pREdictive mainteNAnce
English
Book Article
Fraunhofer IPT ()
IoT; predictive maintenance; edge; cloud

Abstract
The role of maintenance in the industry has been shown to improve companies productivity and profitability. Industry 4.0 revolutionised this field by exploiting emergent cloud technologies and IoT to enable predictive maintenance. Predictive maintenance can reveal valuable insights into the manufacturing processes, by taking advantage of historical data and Industrial IoT streams, combined with high and distributed computing power. Many approaches have been proposed for predictive maintenance solutions in the industry. Typically, the processing and storage of enormous amounts of data can be effectively performed cloud-side (e.g., training complex predictive models), minimising infrastructure costs and maintenance. On the other hand, raw data collected on the shop floor can be successfully processed locally at the edge, without necessarily being transferred to the cloud. In this way, peripheral computational resources are exploited, and network loads are reduced. This work aims to investigate these approaches and integrate the advantages of each solution into a novel flexible ecosystem. As a result, a new unified solution, named SERENA Cloud Platform, is proposed, addressing many challenges of the current state-of-the-art architectures for predictive maintenance, from hybrid cloud-to-edge solutions, to intermodal collaboration, heterogeneous data management, services orchestration, and security.

: http://publica.fraunhofer.de/documents/N-640636.html