Skip to main content
Log in

Smart Factory – Konzeption und Prototyp zum Image Mining und zur Fehlererkennung in der Produktion

Smart Factory – Conception and Prototype of Image Mining for Fault Detection in the Production Environment

  • Schwerpunkt
  • Published:
HMD Praxis der Wirtschaftsinformatik Aims and scope Submit manuscript

Zusammenfassung

Um die Leistungsfähigkeit der Produktion in der Smart Factory effizient zu gestalten, lassen sich durch Sensoren in Echtzeit erhobene Produktionsdaten zur Qualitätsprüfung nutzen. Damit die Daten, die Informationen und letztendlich das durch algorithmische Analyse generierte Wissen über die Qualität rechtzeitig bereitsteht, sind passende Netzwerkarchitekturen, wie beispielsweise die des Edge Computing, notwendig, um einen effizienten Einsatz zu ermöglichen. In diesem Kontext beschäftigt sich der Beitrag mit den Herausforderungen der Analyse von Daten bildgebender Sensoren in der Produktion. Die vorgenommenen Untersuchungen fußen dabei auf der Implementierung einer Image-Mining-Applikation zur Echtzeit-Fehlererkennung in der Produktion, die mittels eines gestaltungsorientierten Forschungsansatzes ergründet wurden. Neben der Identifikation der Herausforderungen in diesem Spannungsfeld, ließen sich Algorithmen ausfindig machen und betrachten, die hierfür eine hohe Prognosegenauigkeit aufweisen. Die erzielten Erkenntnisse bilden dabei eine wichtige Grundlage für den Einsatz von Image-Mining-Applikationen in der Smart Factory.

Abstract

To enable an efficient production in the smart factory, it is necessary to perform quality control in real time. Thereby, the basis is formed by sensors collecting a large amount of data. These data, the resulting information, and also the knowledge generated by algorithmic analysis must be available at the right time. Thus, suitable network architectures like edge computing are necessary for efficient data transfer. In this context, the paper’s contribution deals with challenges of analyzing data collected by imaging sensors in production environments. The consideration based on the implementation of an image mining application for a real time fault detection in production, which was developed as artifact of a design science research approach. In addition to identifying the challenges in this area, algorithms could be recognized and considered having a high accuracy of fit. The results obtained form an important basis for the use of image mining applications in smart factories.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Abb. 1
Abb. 2
Abb. 3
Abb. 4
Abb. 5
Abb. 6
Abb. 7
Abb. 8
Abb. 9

Notes

  1. https://rapidminer.com (Abruf am: 10.09.2018).

  2. https://rapidminer.com (Abruf am: 10.09.2018).

Literatur

  • Anant K, Ghorpade T, Jethani V (2017) Diabetic retinopathy detection through image mining for type 2 diabetes. International Conference on Computer Communication and Informatics, Coimbatore

    Book  Google Scholar 

  • Buchenau M, Suri JF (2000) Experience prototyping. In: Proceedings of the 3rd conference on Designing interactive systems: processes, practices, methods, and techniques, S 424–433

    Google Scholar 

  • Cooper HM (1988) Organizing knowledge syntheses: a taxonomy of literature reviews. Knowl Soc 1(1):104

    Google Scholar 

  • Emam A (2015) Intelligent drowsy eye detection using image mining. Inf Syst Front 17(4):947–960

    Article  Google Scholar 

  • Ennouni A, Filali Y, Sabri MA, Aarab A (2017) A review on image mining. Intelligent Systems and Computer Vision (ISCV) IEEE, S 1–7

    Google Scholar 

  • Felden C (2016a) Klassifikation, statistische Methoden. Enzyklopaedie der Wirtschaftsinformatik. http://www.enzyklopaedie-der-wirtschaftsinformatik.de/lexikon/technologien-methoden/Statistik/Klassifikation/index.html/?searchterm=Klassifikation. Zugegriffen: 13. März 2019

    Google Scholar 

  • Felden C (2016b) Künstliche Intelligenz. Enzyklopaedie der Wirtschaftsinformatik. http://www.enzyklopaedie-der-wirtschaftsinformatik.de/lexikon/technologien-methoden/KI-und-Softcomputing/Kunstliche-Intelligenz/index.html/?searchterm=künstliche%20intelligenz. Zugegriffen: 14. März 2019

    Google Scholar 

  • Heaton J (2018) Ian goodfellow, yoshua bengio, and aaron courville: deep learning. Genet Program Evolable Mach 19(1–2):305–307

    Article  Google Scholar 

  • Hevner A, Chatterjee S (2010) Design research in information systems: theory and practice. Springer, Berlin Heidelberg

    Book  Google Scholar 

  • Hofmann M, Klinkenberg R (2014) RapidMiner: Data mining use cases and business analytics applications. CRC Press, Boca Raton

    Google Scholar 

  • Joshi DP (2015) Combination of multiple image features along with KNN classifier for classification of Marathi Barakhadi. Computing Communication Control and Automation (ICCUBEA), International Conference, S 607–610

    Google Scholar 

  • Klinkenberg R, Schlunder P, Klapic E, Lacker T (2018) Zukunftsweisende Informations- und Kommunikations-Technologien. Industrie 4.0 für die Praxis. Springer Gabler, Wiesbaden, S 129–146

    Book  Google Scholar 

  • Krizhevskky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. In Advances in neural information processing systems 25(2):1097–1105. https://doi.org/10.1145/3065386

    Article  Google Scholar 

  • Kumar B, Selvi R (2015) Feature extraction using image mining techniques to identify brain tumors. International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS), International Conference on IEEE, S 1–6

    Google Scholar 

  • Liaw A, Wiener M (2002) Classification and regression by randomForest. R News 2(3):18–22

    Google Scholar 

  • Merz SL, Siepmann D (2016) Industrie 4.0–Vorgehensmodell für die Einführung. In: Einführung und Umsetzung von Industrie 4.0. Springer Gabler, Berlin, Heidelberg, S 83–132

    Chapter  Google Scholar 

  • Mohanty A, Senapati M, Lenka S (2013) A novel image mining technique for classification of mammograms using hybrid feature selection. Neural Comput Appl 6(22):1151–1161

    Article  Google Scholar 

  • Parihar VR, Nage RS, Dahane AS (2017) Image analysis and image mining techniques: a review. J Image Process Artif Intell 3(2):3

    Google Scholar 

  • Peres RS, Rocha AD, Coelho A, Oliveira JB (2017) A highly flexible, distributed data analysis framework for industry 4.0 manufacturing systems. In: Service orientation in Holonic and multi-agent manufacturing. Springer, Cham, S 373–381

    Chapter  Google Scholar 

  • Pierson L (2015) Data science for dummies. John Wiley & Sons, Inc. Hoboken, New Jersey

    Google Scholar 

  • Runkler TA (2013) Information Mining: Methoden, Algorithmen und Anwendungen intelligenter Datenanalyse. Springer, Berlin Heidelberg

    MATH  Google Scholar 

  • Shi W, Cao J, Zhang Q, Li Y, Xu L (2016) Edge computing: vision and challenges. IEEE Internet Things J 3(1):637–646

    Article  Google Scholar 

  • Syed K, Srinivasu SV (2017) A review of web image mining tools, techniques and applications. Int J Comput Trends Technol 49(1):36–43

    Article  Google Scholar 

  • Trinks S (2018) A classification of real time analytics methods—an outlook for the use within the smart factory. Scientific papers of Silesian University of Technology, Organization and Management Series, Bd. 119, S 313–329

    Google Scholar 

  • Trinks S, Felden C (2018) Edge computing architectures to support real time analytic applications—a state of the art within the application area of smart factory and industry 4.0. IEEE International Conference on Big Data, S 2930–2939

    Google Scholar 

  • Zhang E, Zhang Y (2009) F‑Measure. In: Liu L, Özsu MT (Hrsg) Encyclopedia of database systems. Springer, Boston

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Sebastian Trinks.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Trinks, S., Felden, C. Smart Factory – Konzeption und Prototyp zum Image Mining und zur Fehlererkennung in der Produktion. HMD 56, 1017–1040 (2019). https://doi.org/10.1365/s40702-019-00529-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1365/s40702-019-00529-2

Schlüsselwörter

Keywords

Navigation