Sustainable Data Management for Manufacturing

The impact of Industry 4.0 will result in more automatic connected assembly lines, which are designed for manufacturing individual and customised products on demand. To enable this capability, the need for information-driven services were introduced, with the ambition that all physical, virtual and human entities shall be able to communicate among each other. This approach will provide much more elaborate production systems with vast amounts of information to transfer. The arising additional data integration challenges have to be solved.This paper motivates the need for the interoperability on the data level, to enable the unified input and output of artificial intelligence (AI) algorithms. Therefore, the approach containing an information model and corresponding translation processes are presented. In doing so, a semantic mediator will be used as a middle layer for gathering all data and provide unified data to AI methods - here, an expert system (ES).Finally, an extracted use case is shown where an ES will optimise the energy efficiency of a running production process by providing the relevant data. By intervening in the actual process, it shows the importance of converting the required input data into one unified format for an AI system.

[1]  Michael Schweitzer,et al.  SemOPC-UA: Introducing Semantics to OPC-UA Application Specific Methods , 2018 .

[2]  Craig Schlenoff,et al.  The Process Specification Language (PSL) Overview and Version 1.0 Specification , 2000 .

[3]  Peng Wang,et al.  An ontology modeling and application for an assembly line of manufacturing system , 2017, IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society.

[4]  Michele Dassisti,et al.  ONTOLOGY-BASED MODEL FOR PRODUCTION-CONTROL SYSTEMS INTEROPERABILITY , 2008 .

[5]  Alon Y. Halevy,et al.  Principles of Data Integration , 2012 .

[6]  Theodoros Rekatsinas,et al.  Data Integration and Machine Learning: A Natural Synergy , 2018, Proc. VLDB Endow..

[7]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[8]  Nicola Guarino,et al.  Formal Ontology in Information Systems , 1998 .

[9]  Peter Norvig,et al.  The Unreasonable Effectiveness of Data , 2009, IEEE Intelligent Systems.

[10]  Cecilia Zanni-Merk,et al.  Ontologies for Manufacturing Process Modeling: A Survey , 2018, Sustainable Design and Manufacturing 2018.

[11]  Klaus-Dieter Thoben,et al.  A Semantic Mediator for Data Integration in Autonomous Logistics Processes , 2010, I-ESA.

[12]  Qihui Wu,et al.  A survey of machine learning for big data processing , 2016, EURASIP Journal on Advances in Signal Processing.

[13]  Colette Rolland,et al.  A Comprehensive View of Process Engineering , 1998, CAiSE.

[14]  Kristo Karjust,et al.  SELECTING THE RIGHT KPIs FOR SMEs PRODUCTION WITH THE SUPPORT OF PMS AND PLM , 2013 .