TU Darmstadt / ULB / TUbiblio

Development of an Optical Object Detection Solution for Defect Prevention in a Learning Factory

Wiech, Michael and Böllhoff, Jörg and Metternich, Joachim (2017):
Development of an Optical Object Detection Solution for Defect Prevention in a Learning Factory.
In: Procedia Manufacturing, 7th Conference on Learning Factories, Darmstadt, Elsevier B.V., pp. 190-197, 9, ISSN 2351-9789,
[Online-Edition: https://doi.org/10.1016/j.promfg.2017.04.037],
[Article]

Abstract

This article investigates a potential application of low cost computer hardware and open source software in machining areas of Learning Factories. Based on the implementation of an optical object detection to discover human errors in the setup process of a milling machine, the paper presents an example of how value stream improvements in Learning Factories can be achieved by student projects. Therefore, the process of identifying possible solutions which are suitable for solving a problem in the value stream of a Learning Factory is described. In the presented case, this is an IT-solution to establish a Poka-Yoke system for depositing a work piece in a milling machine correctly. A solution, which uses a Raspberry Pi, is developed and integrated in the process. Furthermore, the ability of low cost hardware components and simple algorithms resting upon freely available software libraries to fulfil the requirements of modern manufacturing is demonstrated. Finally, this study illustrates that the implementation of in-house low cost digitalization rather rests on a profound understanding of the affected manufacturing process than on previous knowledge of programming or electronics.

Item Type: Article
Erschienen: 2017
Creators: Wiech, Michael and Böllhoff, Jörg and Metternich, Joachim
Title: Development of an Optical Object Detection Solution for Defect Prevention in a Learning Factory
Language: English
Abstract:

This article investigates a potential application of low cost computer hardware and open source software in machining areas of Learning Factories. Based on the implementation of an optical object detection to discover human errors in the setup process of a milling machine, the paper presents an example of how value stream improvements in Learning Factories can be achieved by student projects. Therefore, the process of identifying possible solutions which are suitable for solving a problem in the value stream of a Learning Factory is described. In the presented case, this is an IT-solution to establish a Poka-Yoke system for depositing a work piece in a milling machine correctly. A solution, which uses a Raspberry Pi, is developed and integrated in the process. Furthermore, the ability of low cost hardware components and simple algorithms resting upon freely available software libraries to fulfil the requirements of modern manufacturing is demonstrated. Finally, this study illustrates that the implementation of in-house low cost digitalization rather rests on a profound understanding of the affected manufacturing process than on previous knowledge of programming or electronics.

Journal or Publication Title: Procedia Manufacturing, 7th Conference on Learning Factories, Darmstadt, Elsevier B.V.
Volume: 9
Uncontrolled Keywords: Learning Factory, Industrie 4.0, Digitaliziaton, Object Detection, Error Detection, Poka-Yoke, Raspberry Pi, Low Cost Automation
Divisions: 16 Department of Mechanical Engineering
16 Department of Mechanical Engineering > Institute of Production Management, Technology and Machine Tools (PTW)
16 Department of Mechanical Engineering > Institute of Production Management, Technology and Machine Tools (PTW) > CiP Center for industrial Productivity
Date Deposited: 01 Sep 2017 11:30
Official URL: https://doi.org/10.1016/j.promfg.2017.04.037
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item