Hinweis zum Urheberrecht| Allgemeine Informationen | FAQ
Beim Zitieren dieses Dokumentes beziehen Sie sich bitte immer auf folgende URN: urn:nbn:de:hbz:5n-53758

 

Mathematisch-Naturwissenschaftliche Fakultät - Jahrgang 2019

 

Titel A Knowledge Graph Based Integration Approach for Industry 4.0
Autor Irlán Grangel-González
Publikationsform Dissertation
Abstract The fourth industrial revolution, Industry 4.0 (I40) aims at creating smart factories employing among others Cyber-Physical Systems (CPS), Internet of Things (IoT) and Artificial Intelligence (AI). Realizing smart factories according to the I40 vision requires intelligent human-to-machine and machine-to-machine communication. To achieve this communication, CPS along with their data need to be described and interoperability conflicts arising from various representations need to be resolved. For establishing interoperability, industry communities have created standards and standardization frameworks. Standards describe main properties of entities, systems, and processes, as well as interactions among them. Standardization frameworks classify, align, and integrate industrial standards according to their purposes and features. Despite being published by official international organizations, different standards may contain divergent definitions for similar entities. Further, when utilizing the same standard for the design of a CPS, different views can generate interoperability conflicts. Albeit expressive, standardization frameworks may represent divergent categorizations of the same standard to some extent, interoperability conflicts need to be resolved to support effective and efficient communication in smart factories. To achieve interoperability, data need to be semantically integrated and existing conflicts conciliated. This problem has been extensively studied in the literature. Obtained results can be applied to general integration problems. However, current approaches fail to consider specific interoperability conflicts that occur between entities in I40 scenarios. In this thesis, we tackle the problem of semantic data integration in I40 scenarios. A knowledge graphbased approach allowing for the integration of entities in I40 while considering their semantics is presented. To achieve this integration, there are challenges to be addressed on different conceptual levels. Firstly, defining mappings between standards and standardization frameworks; secondly, representing knowledge of entities in I40 scenarios described by standards; thirdly, integrating perspectives of CPS design while solving semantic heterogeneity issues; and finally, determining real industry applications for the presented approach.
We first devise a knowledge-driven approach allowing for the integration of standards and standardization frameworks into an Industry 4.0 knowledge graph (I40KG). The standards ontology is used for representing the main properties of standards and standardization frameworks, as well as relationships among them. The I40KG permits to integrate standards and standardization frameworks while solving specific semantic heterogeneity conflicts in the domain. Further, we semantically describe standards in knowledge graphs. To this end, standards of core importance for I40 scenarios are considered, i.e., the Reference Architectural Model for I40 (RAMI4.0), AutomationML, and the Supply Chain Operation Reference Model (SCOR). In addition, different perspectives of entities describing CPS are integrated into the knowledge graphs. To evaluate the proposed methods, we rely on empirical evaluations as well as on the development of concrete use cases. The attained results provide evidence that a knowledge graph approach enables the effective data integration of entities in I40 scenarios while solving semantic interoperability conflicts, thus empowering the communication in smart factories.
Komplette Version pdf-Dokument (14,5 MB) Hier können Sie den Adobe Acrobat Reader downloaden
© Universitäts- und Landesbibliothek Bonn | Veröffentlicht: 30.04.2019