<div class="csl-bib-body">
<div class="csl-entry">Şen, K. Ö. (2018). <i>Implementation of sensor based intelligent measurement and digitalization of monitoring in food production</i> [Dissertation, Technische Universität Wien]. reposiTUm. http://hdl.handle.net/20.500.12708/78695</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/78695
-
dc.description.abstract
Abstract: In the road paved by the Industry 4.0 vision, information communication technologies (ICT) have been integrated not only into production processes, but into quality management systems (TQM) as well. Within the scope of this thesis study, a TQM system that is reinforced with contemporary ICT (IoT, fog computing, cloud computing and web based monitoring) and statistical forecasting models (sliding ARIMA and cumulative ARIMA) has been realized. As for the place of thesis implementation, a food production facility in possession of ISO 9001, BRC, IFS and HACCP certifications has been selected. In accordance with these specifications, areas in the production line which are more likely to be adversely affected due to environmental risks have been selected and environmental conditions governing these areas have been measured using sensor based intelligent measurement nodes. Thus, existing environmental conditions are monitored by means of these measurements so as to trigger an alarm mechanism in the event that an undesirable condition should occur (Fog computing). Environmental data collected condition through the nodes is sent to the cloud, where it is stored, processed and published to the users over the web server in the form of momentary status upgrade. In addition to this, by processing the same data with statistical forecasting methods, general status of the nodes are determined in order to generate output which is in compliance with M2M structure. Owing to these statistical forecasting methods, it is possible to correctly forecast the environmental conditions 15 minutes in advance with over 90% accuracy and to take the necessary steps to prevent any risks to the quality of the product. The statistical forecasting models used in this study have especially been designed for the IoT structure. Furthermore, as these models can flawlessly run on a Raspberry Pi like development kits, there is no need for a custom-designed high-power computer or a motherboard. By integrating these ARIMA models into sensor based intelligent measurement nodes, it is possible to construct a system that not only operates uninterruptedly, but one that can take quick preventative action. This structure contributes to reinforced total quality management, longer shelf life of products and lower losses in production process. It has been assessed that the proposed model can benefit not just food production facilities, but all other manufacturing facilities by reducing production losses and increasing efficiency, provided that the data obtained from quality control processes and risk assessment specific to that production is integrated into it. This will give companies the advantage of cost effectiveness and reduce wastage, which will inevitably increase their competitive power.
en
dc.format
xiii, 218 Blätter
-
dc.language
English
-
dc.language.iso
en
-
dc.subject
Industry 4.0
en
dc.subject
Internet of Things
en
dc.subject
Fog Calculation
en
dc.subject
Cloud Calculation
en
dc.subject
ARIMA
en
dc.subject
Web-based Environmental Monitoring
en
dc.subject
TQM
en
dc.title
Implementation of sensor based intelligent measurement and digitalization of monitoring in food production
en
dc.type
Thesis
en
dc.type
Hochschulschrift
de
dc.contributor.affiliation
TU Wien, Österreich
-
dc.publisher.place
Wien
-
tuw.thesisinformation
Technische Universität Wien
-
tuw.publication.orgunit
E311 - Institut für Fertigungstechnik und Hochleistungslasertechnik