Zobrazit v EDS

Towards a knowledge graph framework for ad hoc analysis in manufacturing.

Uloženo v:
Podrobná bibliografie
Název: Towards a knowledge graph framework for ad hoc analysis in manufacturing.
Autoři: Meyers, Bart, Vangheluwe, Hans, Lietaert, Pieter, Vanderhulst, Geert, Van Noten, Johan, Schaffers, Michel, Maes, Davy, Gadeyne, Klaas
Zdroj: Journal of Intelligent Manufacturing; Dec2024, Vol. 35 Issue 8, p3731-3752, 22p
Témata: KNOWLEDGE graphs, ARTIFICIAL intelligence, ENGINEERS, DATA management, KNOWLEDGE management
Abstrakt: The development of artificial intelligence models for data driven decision making has a lot of potential for the manufacturing sector. Nevertheless, applications in industry are currently limited to the actionable insights one can discover from the available data and knowledge of a manufacturing system. We call the process to obtain such insights "ad hoc analysis". Ad hoc analysis at system level is very complex in an industrial setting due to the inherent heterogeneity of data and existence of data silos, the lack of information and knowledge formalization, and the inability to meaningfully and efficiently reason about the data, information and knowledge. In this paper, we provide and outline a framework for ad hoc analysis in manufacturing based on knowledge graphs and influenced by the metamodelling paradigm. We derive its requirements and key elements from an analysis of several industry application cases. We show how manufacturing data, information and knowledge can be combined and made actionable using this framework. The framework supports workflows and tools for the data consumer (i.e., data scientist), and for the knowledge engineer. Furthermore, we show how the framework is integrated with existing data sources. Then, we discuss how we applied the framework to several application cases. We discuss how the framework contributes when applied, and what challenges still remain. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Intelligent Manufacturing is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáze: Complementary Index
Popis
Abstrakt:The development of artificial intelligence models for data driven decision making has a lot of potential for the manufacturing sector. Nevertheless, applications in industry are currently limited to the actionable insights one can discover from the available data and knowledge of a manufacturing system. We call the process to obtain such insights "ad hoc analysis". Ad hoc analysis at system level is very complex in an industrial setting due to the inherent heterogeneity of data and existence of data silos, the lack of information and knowledge formalization, and the inability to meaningfully and efficiently reason about the data, information and knowledge. In this paper, we provide and outline a framework for ad hoc analysis in manufacturing based on knowledge graphs and influenced by the metamodelling paradigm. We derive its requirements and key elements from an analysis of several industry application cases. We show how manufacturing data, information and knowledge can be combined and made actionable using this framework. The framework supports workflows and tools for the data consumer (i.e., data scientist), and for the knowledge engineer. Furthermore, we show how the framework is integrated with existing data sources. Then, we discuss how we applied the framework to several application cases. We discuss how the framework contributes when applied, and what challenges still remain. [ABSTRACT FROM AUTHOR]
ISSN:09565515
DOI:10.1007/s10845-023-02319-6