Bretones Cassoli, Beatriz ; Jourdan, Nicolas ; Metternich, Joachim (2022)
Knowledge Graphs for Data And Knowledge Management in Cyber-Physical Production Systems.
doi: 10.15488/12180
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Cyber-physical production systems are constituted of various sub-systems in a production environment, from machines to logistics networks, that are connected and exchange data in real-time. Every sub-system consumes and generates data. This data has the potential to support decision making and optimization of production processes. To extract valuable information from this data, however, different data sources must be consolidated and analyzed. A Knowledge Graph (KG), also known as a semantic network, represents a net of real-world entities, i.e., machines, sensors, processes, or concepts, and illustrates their relationship. KG allows us to encode the knowledge and data context into a human interpretable form and is amenable to automated analysis and inference. This paper presents the potential of KG in manufacturing and proposes a framework for its implementation. The proposed framework should assist practitioners in integrating raw data from multiple data sources in production, developing a suitable data model, creating the knowledge graph, and using it in a graph application. Although the framework is applicable for different purposes, this work illustrates its use for supporting the quality assessment of products in a discrete manufacturing production line.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Bretones Cassoli, Beatriz ; Jourdan, Nicolas ; Metternich, Joachim |
| Art des Eintrags: | Bibliographie |
| Titel: | Knowledge Graphs for Data And Knowledge Management in Cyber-Physical Production Systems |
| Sprache: | Englisch |
| Publikationsjahr: | 2022 |
| Ort: | Hannover |
| Verlag: | publish-Ing |
| Buchtitel: | Proceedings of the Conference on Production Systems and Logistics: CPSL 2022 |
| DOI: | 10.15488/12180 |
| Kurzbeschreibung (Abstract): | Cyber-physical production systems are constituted of various sub-systems in a production environment, from machines to logistics networks, that are connected and exchange data in real-time. Every sub-system consumes and generates data. This data has the potential to support decision making and optimization of production processes. To extract valuable information from this data, however, different data sources must be consolidated and analyzed. A Knowledge Graph (KG), also known as a semantic network, represents a net of real-world entities, i.e., machines, sensors, processes, or concepts, and illustrates their relationship. KG allows us to encode the knowledge and data context into a human interpretable form and is amenable to automated analysis and inference. This paper presents the potential of KG in manufacturing and proposes a framework for its implementation. The proposed framework should assist practitioners in integrating raw data from multiple data sources in production, developing a suitable data model, creating the knowledge graph, and using it in a graph application. Although the framework is applicable for different purposes, this work illustrates its use for supporting the quality assessment of products in a discrete manufacturing production line. |
| Freie Schlagworte: | Knowledge Graph, Cyber-Physical Production Systems, Knowledge Management, Data Management, Machine learning |
| Fachbereich(e)/-gebiet(e): | 16 Fachbereich Maschinenbau 16 Fachbereich Maschinenbau > Institut für Produktionsmanagement und Werkzeugmaschinen (PTW) 16 Fachbereich Maschinenbau > Institut für Produktionsmanagement und Werkzeugmaschinen (PTW) > CiP Center für industrielle Produktivität 16 Fachbereich Maschinenbau > Institut für Produktionsmanagement und Werkzeugmaschinen (PTW) > Management industrieller Produktion |
| Hinterlegungsdatum: | 17 Apr 2023 07:03 |
| Letzte Änderung: | 17 Apr 2023 07:03 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum