Big data in production

Nine pillars of industrial smart data analysis

Authors

  • Emanuel Trunzer TU München
  • Iris Weiß TU München
  • Thorsten Pötter Bayer
  • Christian Vermum Evonik Technology & Infrastructure
  • Matthias Odenweller Evonik Technology & Infrastructure
  • Stefan Unland Samson AG
  • Daniel Schütz Gefasoft
  • Birgit Vogel-Heuser TU München

DOI:

https://doi.org/10.17560/atp.v61i1-2.2394

Keywords:

data analysis, Industry 4.0, smart data

Abstract

With the digitalization of machines, increasing amounts of data are recorded in production environments. Data-driven methods are available to benefit from these amounts of data. However, these methods often fail due to the specific boundary conditions in production. The solution for such environments is to combine datadriven
methods with the existing expert knowledge. In this article, the requirements needed for successful data analysis in production as well as an industrial data analysis process are described, using the SIDAP project as an example.

References

TU München, Lehrstuhl für Automatisierung und Informationstechnik. (2018). SIDAP: Skalierbares Integrationskonzept zur Datenaggregation, -analyse, -aufbereitung von großen Datenmengen in der Prozessindustrie. Abgerufen von: www.sidap.de.

Trunzer, E., Weiß, I., Folmer, J., Schrüfer, C., Vogel-Heuser, B., Erben, S., ... & Vermum, C. (2017, December). Failure mode classification for control valves for supporting data-driven fault detection. In Industrial Engineering and Engineering Management (IEEM), 2017 IEEE International Conference on (pp. 2346-2350). IEEE.

Temmen, H., Argast, U., Welke, R., Theissen, M., & Wiedau, M. (2016). Intelligenter R&I-Austausch. atp magazin, 58(03), 54-65.

Trunzer, E., Kirchen, I., Folmer, J., Koltun, G., & Vogel-Heuser, B. (2017, March). A flexible architecture for data mining from heterogeneous data sources in automated production systems. In Industrial technology (ICIT), 2017 IEEE international conference on (pp. 1106-1111). IEEE.

Klettner, C., Tauchnitz, T., Epple, U., Nothdurft, L., Diedrich, C., Schröder, T., ... & Urbas, L. (2017). Namur Open Architecture. atp magazin, 59(01-02), 20-37.

Weiß, I., & Vogel-Heuser, B. (2018). Assessment of variance & distribution in data for effective use of statistical methods for product quality prediction. at-Automatisierungstechnik, 66(4), 344-355.

Trunzer, E., Wu, C., Guo, K., Vermum, C., & Vogel-Heuser, B. (2018, October). Data-Driven Approach to Support Experts in the Identification of Operational States in Industrial Process Plants. In IECON 2018-44th Annual Conference of the IEEE Industrial Electronics Society (pp. 3096-3101). IEEE.

Vogel-Heuser, B., Karaseva, V., Folmer, J., & Kirchen, I. (2017). Operator knowledge inclusion in data-mining approaches for product quality assurance using cause-effect graphs. IFAC-PapersOnLine, 50(1), 1358-1365.

Vermum, C., Unland, S. (2018). Schadensfallklassifikation von Ventilen und Retrofitting von bestehenden Anlagen: Anwendung für die Ventilfehlerdiagnose. In Produktions- und Verfügbarkeitsoptimierung mit Smart Data Ansätzen: Automation Symposium 2018, B. Vogel-Heuser, Ed., Göttingen: Sierke VERLAG, 2018, pp. 29–37.

Folmer, J., Kirchen, I., Trunzer, E., Vogel-Heuser, B., Pötter, T., Graube, M., ... & Arnu, D. (2017). Big und Smart Data-Herausforderungen in der Prozessindustrie. Automatisierungstechnische Praxis (atp), 1(59), 58-69.

Schleinitz, P., Steffen, M. (2018). Das SIDAP-Cloud-Konzept für Smart Data-Anwendungen in der Prozessindustrie. In Produktions- und Verfügbarkeitsoptimierung mit Smart Data Ansätzen: Automation Symposium 2018, B. Vogel-Heuser, Ed., Göttingen: Sierke VERLAG, 2018, pp. 93–107.

Venables, W.N., Smith, D.M. (2018). An Introduction to R: Notes on R: A Programming Environment for Data Analysis and Graphics, Version 3.5.1. Abgerufen von: https://cran.r-project.org/doc/manuals/r-release/R-intro.pdf

Shearer, C. (2000). The CRISP-DM model: the new blueprint for data mining. Journal of data warehousing, 5(4), 13-22.

Kirchen, I., Schütz, D., Folmer, J., & Vogel-Heuser, B. (2017, July). Metrics for the evaluation of data quality of signal data in industrial processes. In Industrial Informatics (INDIN), 2017 IEEE 15th International Conference on (pp. 819-826). IEEE.

Downloads

Published

2019-02-13

Issue

Section

Article / Peer Review

Most read articles by the same author(s)

1 2 3 4 > >>