Journal of Simulation

, Volume 11, Issue 1, pp 38–50 | Cite as

Emulation of control strategies through machine learning in manufacturing simulations



Discrete-event simulation is a well-accepted method for planning, evaluating, and monitoring processes in production and logistics. To reduce time and effort spent on creating simulation models, automatic simulation model generation is an important area in modeling methodology research. When automatically generating a simulation model from existing data sources, the correct reproduction of dynamic behavior of the modeled system is a common challenge. One example is the representation of dispatching and scheduling strategies of production jobs. When generating a model automatically, the underlying rules for these strategies are typically unknown but yet have to be adequately emulated. In this paper, we summarize our work investigating the suitability of various data mining and supervised machine learning methods for emulating job scheduling decisions based on data obtained from production data acquisition. We report on the performance of the algorithms and give recommendations for their application, including suggestions for their integration in simulation systems.


approximation dispatching rules automatic model generation data mining 


Statement of contribution

Paper invited from ASIM 2015 conference.


  1. Altman NS (1992). An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician 46(3): 175–185. doi:10.1080/00031305.1992.10475879.Google Scholar
  2. Becker B, Kohavi R and Sommerfield D (2002). Visualizing the simple Baysian classifier. In: Fayyad U, Grinstein GG and Wierse A (eds) Information Visualization in Data Mining and Knowledge Discovery. Morgan Kaufmann Publishers Inc: San Francisco, CA, USA, pp 237–249.Google Scholar
  3. Bergmann S (2014). Automatische Generierung adaptiver Modelle zur Simulation von Produktionssystemen. Univ.-Verl: Ilmenau.Google Scholar
  4. Bergmann S, Feldkamp N, Hinze U and Straßburger S (2015a). Abbildung von Steuerungslogiken durch maschinelles Lernen für die Simulation von Produktionssystemen. In: Rabe M and Clausen U (eds) Simulation in Production and Logistics 2015. Fraunhofer Verlag: Stuttgart, pp 481–490.Google Scholar
  5. Bergmann S, Feldkamp N and Strassburger S (2015b). Approximation of dispatching rules for manufacturing simulation using data mining methods. In: Yilmaz L, Chan WKV, Moon I, Roeder TMK, Macal C and Rossetti MD (eds) Proceedings of the 2015 Winter Simulation Conference, IEEE: Piscataway, pp 2329–2340.Google Scholar
  6. Bergmann S, Stelzer S and Strassburger S (2011). Initialization of simulation models using CMSD. In: Jain S, Creasey R, Himmelspach J, White KP and Fu MC (eds) Proceedings of the 2011 Winter Simulation Conference, IEEE: Piscataway, pp 2223–2234.Google Scholar
  7. Bergmann S, Stelzer S and Strassburger S (2014). On the use of artificial neural networks in simulation-based manufacturing control. Journal of Simulation 8(1): 76–90. doi:10.1057/jos.2013.6.CrossRefGoogle Scholar
  8. Bergmann S and Strassburger S (2010). Challenges for the automatic generation of simulation models for production systems. In: International Summer Simulation Multiconference 2010. Omni Press: Madison, pp 545–549.Google Scholar
  9. Bishop CM (ed) (2006). Pattern Recognition and Machine Learning. Information Science and Statistics. Springer: New York.Google Scholar
  10. Bishop CM (ed) (2010). Neural Networks for Pattern Recognition, Reprinted. Oxford University Press: Oxford.Google Scholar
  11. Boser BE, Guyon IM and Vapnik VN (1992). A training algorithm for optimal margin classifiers. In: Haussler D (ed) Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pp 144–152.Google Scholar
  12. Breiman L (ed) (1984). Classification and Regression Trees. Chapman & Hall: New York.Google Scholar
  13. El Attar R (ed) (2005). Lecture Notes on Z-Transform. Lulu Com: Raleigh.Google Scholar
  14. Fayyad UM, Piatetsky-Shapiro G and Smyth P (1996). From data mining to knowledge discovery in databases. AI Magazine 17: 37–54.Google Scholar
  15. Feldkamp N and Strassburger S (2014). Automatic generation of route networks for microscopic traffic simulations. In: Tolk A, Diallo SD, Ryzhov IO, Yilmaz L, Buckley S and Miller JA (eds) Proceedings of the 2014 Winter Simulation Conference, IEEE: Piscataway, pp 2848–2859.Google Scholar
  16. Guyon I and Elisseeff A (2003). An introduction to variable and feature selection. Journal of Machine Learning Research 3: 1157–1182.Google Scholar
  17. Han J, Kamber M and Pei J (2012). Data Mining Concepts and Techniques. The Morgan Kaufmann Series in Data Management Systems. 3rd edn, Elsevier/Morgan Kaufmann: Amsterdam.Google Scholar
  18. Jensen S (2007). Eine Methodik zur teilautomatisierten Generierungvon Simulationsmodellen aus Produktionsdatensystemen am Beispiel einer Job Shop Fertigung. Dissertation, Universität Kassel.Google Scholar
  19. Li X and Olafsson S (2005). Discovering dispatching rules using data mining. Journal of Scheduling 8(6): 515–527. doi:10.1007/s10951-005-4781-0.CrossRefGoogle Scholar
  20. Lorenz P and Schulze T (1995). Layout based model generation. In: Alexopoulos C, Kang K, Lilegdon WR and Goldsman D (eds) Proceedings of the 1995 Winter Simulation Conference, IEEE: Piscataway, pp 728–735.Google Scholar
  21. MathWorks (2016a). Introducing MATLAB Engine API for C/C++ and Fortran – MATLAB & Simulink., accessed 21st January 2016.
  22. MathWorks (2016b). MATLAB – The Language of Technical Computing., accessed 21st January 2016.
  23. Milberg J and Selke C (2003). Automatic generation of simulation models for production planning and control. Annals of the German Academic Society for Production Engineering 10(1): 115–118.Google Scholar
  24. Mueller-Sommer H (2012). Wirtschaftliche Generierung von Belieferungssimulationen unter Verwendung rechnerunterstützter Plausibilisierungsmethoden für die Bewertung der Eingangsdaten. Univ.-Verl: Ilmenau.Google Scholar
  25. Pinedo M (ed) (2012). Scheduling: Theory, Algorithms, and Systems. 4th edn, Springer: New York.CrossRefGoogle Scholar
  26. Reinhart G and Gyger T (2008). Identification of implicit strategies in production control. In: IEEE International Conference on Industrial Engineering and Engineering Management, IEEE: Piscataway, pp 302–306.Google Scholar
  27. Reinhart G and Selke C (2002). Information becomes knowledge – Automatic building of simulation models. In: Proceedings of the 35th CIRP International Seminar on Manufacturing Systems, Seoul, pp 414–418.Google Scholar
  28. Rennie JD, Shih L, Teevan J and Karger DR (2003). Tackling the poor assumptions of Naive Bayes text classifiers. In: Proceedings of the Twentieth International Conference on Machine Learning, AAAI Press: Menlo Park, pp 616–623.Google Scholar
  29. Rooks T (2009). Rechnergestützte Simulationsmodellgenerierung zur dynamischen Absicherung der Montagelogistikplanung bei der Fahrzeugneutypplanung im Rahmen der digitalen Fabrik. Shaker: Aachen.Google Scholar
  30. Selke C (2005). Entwicklung von Methoden zur automatischen Simulationsmodellgenerierung. Utz: München.Google Scholar
  31. Siemens Product Lifecycle Management Software (2016). Plant Simulation., accessed 21st January 2016.
  32. Simulation Interoperability Standards Organization (2010). Standard for: Core Manufacturing Simulation Data – UML Model (SISO-STD-008-2010).
  33. Splanemann R (1995). Teilautomatische Generierung von Simulationsmodellen aus systemneutral definierten Unternehmensdaten. Disstertation, Universität Bremen.Google Scholar
  34. Strassburger S, Bergmann S and Mueller-Sommer H (2010). Modellgenerierung im Kontext der Digitalen Fabrik – Stand der Technik und Herausforderungen. In: Zuelch G and Stock P (eds) Tagungsband der 14. ASIM-Fachtagung Simulation in Produktion und Logistik – Integrationsaspekte der Simulation: Technik, Organisation und Personal. KIT Scientific Publ: Karlsruhe, pp 37–44.Google Scholar
  35. Verein Deutscher Ingenieure (2014). Simulation of systems in materials handling, logistics and production – Fundamentals VDI 3633-1(VDI 3633-1).Google Scholar
  36. Wnek J and Michalski RS (1994). Hypothesis-driven constructive induction in AQ17-HCI: A method and experiments. Machine Learning 14(2): 139–168. doi:10.1023/A:1022622132310.CrossRefGoogle Scholar
  37. Zell A (2003). Simulation neuronaler Netze. Oldenbourg: München.Google Scholar

Copyright information

© The Operational Research Society 2016

Authors and Affiliations

  1. 1.Department for Industrial Information Systems, School of Economic Sciences and MediaIlmenau University of TechnologyIlmenauGermany

Personalised recommendations