Abstract
Traditional maintenance approaches are under-optimized. 20% savings on total
maintenance costs and improvements of Overall Equipment Effectiveness (OEE) are
achievable. Most of the predictive maintenance solutions only offer analytics
capabilities. Operators have to assert themselves the maintenance action to
implement and to manually balance between multiple variables to decide on the
optimal implementation time. The UPTIME solution is built upon the predictive
maintenance and four integrated technological pillars, i.e. Industrial Internet,
IoT, Big Data and Proactive Computing. The collect and aggregation of data is
supported by the use of technological standards as the semantic web standards.
UPTIME is a fully adaptable, open and modular end-to-end predictive maintenance
solution for industry, from sensor data collection to optimal planning. Through
advanced prognostic algorithms and on-line failure mode analysis, it predicts
upcoming failures. Then, decision algorithms recommend the best action to
optimize maintenance and to improve OEE. UPTIME can be implemented in any
industry regardless of its processes, products and physical models. UPTIME is
being implemented for 3 first industrial use cases: Mobile assets for
aeronautics, white goods production system and cold rolling mill lines.
The presentation will include a show case to highlight the features and benefits
of UPTIME: Health assessment through measured data will be simulated according
various scenarios, the data will be computed by UPTIME, which will propose
maintenance possible actions ordered according different criteria.
#### Références
Uptime WebSite: https://www.uptime-h2020.eu/
#### Auteurs/Autrices
**Yves Keraron**, Founder and CEO of ISADEUS (Innovation Standards And Digital
Engineering Using Semantics), has continuously worked for innovation, first in
nuclear engineering, then in information systems for technical data and
documentation to support the activities of the lifecycle of complex products or
production systems. ISADEUS has been recently involved in European H2020
projects for the Factory of the Future, using new technological standards,
especially web standards for industry : FALCON and UPTIME. He is an expert in
the National Commission IDMI (Ingénierie des Données et de Modèles pour
l’Industrie) of AFNOR.
He is active in the Industrial Internet through the use of advanced web standards
to satisfy the needs of industry to manage the growing volume of data.
He is graduated of Ecole Centrale des Arts et Manufactures (Ecole Centrale Paris)
and completed a PhD on the impact of digital technologies on the relationships
between Technical, information and human systems
Karl Hribernik studied Computer Science at the University of Bremen. He is
manager of the department Intelligent ICT for Co-operative Production at
BIBA. His research focus is on the semantic interoperability of heterogeneous
and dynamic data sources in closed-loop and item-level Product Lifecycle
Management. He is currently the coordinator of the H2020 Factories of the Future
project UPTIME – Unified Predicitive Maintenance System.
Ntalaperas Dimitris was born in Athens, Greece in 1980. He received his BSc and
MSc from the Computer Engineering and Informatics Department of the Polytechnic
School of the University of Patras. His Master Thesis was in simulation of
quantum computers implemented in doped semiconducting materials. He conducted
research and worked in the areas quantum computing, simulation of physical
system, boundary element method, big data, text processing, data anonymization
and semantic web. He held a number of positions as a researcher or software
engineer in various institutions and companies (RACTI 2005-2008, BemSands
2008-2010, Technological Educational Institute of Patras 2009-2010, University
of Patras 2008-2010, Ubitech 2012-). He participated in a number of EC and
National co-funded projects in the areas of e-Health (Linked2Safety, DISYS,
CAREPATHS, GRANATUM) being involved mainly in the tasks of Data Anonymization,
Named Entity Recognition and Rule based Decision Support Systems. In the context
of Marie Curie Actions, he also participated in the SAGE-CARE Project during
which he seconded Hochschule Darmstadt and Università degli Studi di Napoli
Federico II and was trained in the areas of Semantic Web and High Performance
Computing.