Semantic Machine Twins: Use Cases, Concepts, Prototype

Jäckle, Michael (2019) Semantic Machine Twins: Use Cases, Concepts, Prototype. Masters thesis, Ulm University.

This is the latest version of this item.

[thumbnail of MA_Michael_Jaeckle.pdf] PDF - Repository staff only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB)

Abstract

Today, Industry 4.0 leads to massive data collection and analysis in order to improve product quality and applicability. Suitable approaches have already been conceptualized, e.g., Condition Monitoring and Predictive Maintenance. While IoT and Cloud Computing concepts contribute to managing the enormous amounts of data, the analysis turns out to be a significant challenge. To map the actual condition of a machine, the measurements must be recorded together with their interrelations and dependencies. This additional information is currently hardly considered, whereby the data lose meaning and do not represent a sufficient basis for decision-making. Conflicts of interest further complicate the data presentation. On the one side, a manufacturer-independent representation should enable interoperability, on the other side, the data should be enriched by domain-specific knowledge. So far, experts have unconsciously concluded such meanings from their expertise.

This work introduces a progressive approach to represent machine-readable knowledge with Semantic Web technologies to increase the meaning of machine data. Therefore, concepts are introduced which enable to express knowledge on a domain and cross-domain abstraction level. Requirements are obtained by analyzing machine models and current challenging business use cases of two machine manufacturers. Consequently, a prototype is shown, which integrates a semantic representation for typical IoT scenarios.

Item Type: Thesis (Masters)
Subjects: DBIS Research > Master and Phd-Thesis
Divisions: Faculty of Engineering, Electronics and Computer Science > Institute of Databases and Informations Systems > DBIS Research and Teaching > DBIS Research > Master and Phd-Thesis
Depositing User: Klaus Kammerer
Date Deposited: 04 Sep 2020 16:57
Last Modified: 04 Sep 2020 16:57
URI: http://dbis.eprints.uni-ulm.de/id/eprint/1932

Available Versions of this Item

Actions (login required)

View Item
View Item