Machine Learning for Process-X: A Taxonomy

  • Felix Reinhart
  • Sebastian von Enzberg
  • Arno Kühn
  • Roman Dumitrescu
Conference paper
Part of the Technologien für die intelligente Automation book series (TIA, volume 11)


Application of machine learning techniques for data-driven modeling of value-creating processes promises significant economic benefits. These applications include process monitoring, process configuration, process control and process optimization (process-X). However, similarities and distinguishing features between established approaches to process-X compared to machine learning are often unclear. This paper sheds light on this issue by deriving a taxonomy of process-X approaches that sharpens the role of machine learning in these applications. Moreover, the taxonomy and discussion identifies future research directions for applied machine learning in cyber-physical systems.


Machine Learning Data Analytics Statistical Process Control Control Theory Virtual Sensors Expert systems 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1. J.S. Oakland. Statistical Process Control. Butterworth-Heinemann, 1986.Google Scholar
  2. 2. G.E.P. Box and K.B. Wilson. On the experimental attainment of optimum conditions. J. R. Stat. Soc., 13(1):1–45, 1951.MathSciNetzbMATHGoogle Scholar
  3. 3. D.R. Jones. A taxonomy of global optimization methods based on response surfaces. Journal of Global Optimization, 21(4):345–383, 2001.MathSciNetCrossRefGoogle Scholar
  4. 4. D.C. Montgomery. Design and Analysis of Experiments: Response surface method and designs. John Wiley & Sons, 2005.Google Scholar
  5. 5. K. Steenstrup, R.L. Sallam, L. Eriksen, and S.F. Jacobson. Industrial Analytics Revolutionizes Big Data in the Digital Business. Technical report, 2014.Google Scholar
  6. 6. K.L. Lueth, C. Patsioura, Z.D. Williams, and Z.Z. Kermani. Industrial Analytics – The current state of data analytics usage in industrial companies, 2016.Google Scholar
  7. 7. A. Mangal and N. Kumar. Using big data to enhance the bosch production line performance: A Kaggle challenge. In IEEE Intern. Conf. on Big Data, pages 2029–2035, 2016.Google Scholar
  8. 8. A. Unger, W. Sextro, S. Althoff, T. Meyer, K. Neumann, R.F. Reinhart, M. Broekelmann, K. Guth, and D. Bolowski. Data-driven Modeling of the Ultrasonic Softening Effect for Robust Copper Wire Bonding. In Intern. Conf. on Integrated Power Systems, 2014.Google Scholar
  9. 9. C. Atkinson, M. Traver, T. Long, and E. Hanzevack. Predicting smoke. InTech, pages 32–35, 2002.Google Scholar
  10. 10. F. Gustafsson, M. Drevö, U. Forssell, M. Löfgren, N. Persson, and H. Quicklund. Virtual Sensors of Tire Pressure and Road Friction. Technical report, 2001.Google Scholar
  11. 11. L. Fortuna, S. Graziani, A. Rizzo, and M.G. Xibilia. Soft Sensors for Monitoring and Control of Industrial Processes. Springer, 2007.Google Scholar
  12. 12. S. Wrede, C. Emmerich, R. Grünberg, A. Nordmann, A. Swadzba, and J. Steil. A user study on kinesthetic teaching of redundant robots in task and configuration space. Journal of Human-Robot Interaction, 2(1):56–81, 2013.CrossRefGoogle Scholar
  13. 13. S.K. Lahiri and N.M. Khalfe. Soft sensor development and optimization of a commercial petro-chemical plant integrating support vector regression and genetic algorithm. Chemical Industry & Chemical Engineering, 15(3):175–187, 2009.CrossRefGoogle Scholar
  14. 14. T. Meyer, A. Unger, S. Althoff, W. Sextro, M. Broekelmann, M. Hunstig, and K. Guth. Reliable manufacturing of heavy copper wire bonds using online parameter adaptation. In IEEE Electronic Components and Technology Conference, pages 622–628, 2016.Google Scholar
  15. 15. W. Aswolinskiy, R.F. Reinhart, and J.J. Steil. Modelling of parametrized processes via regression in the model space of neural networks. Neurocomputing, 2017.Google Scholar
  16. 16. Z.-S. Hou and Z. Wang. From model-based control to data-driven control: Survey, classification and perspective. Information Sciences, 235:3–35, 2013.MathSciNetCrossRefGoogle Scholar
  17. 17. I. Bratko. Modelling operator’s skill by machine learning. In International Conference on Information Technology Interfaces, pages 23–30, 2000.Google Scholar
  18. 18. F. Oestersötebier, P. Traphöner, R.F. Reinhart, S. Wessels, and A. Trächtler. Design and implementation of intelligent control software for a dough kneader. Procedia Technology, 26:473–482, 2016.CrossRefGoogle Scholar
  19. M. Borzykh, U. Damerow, C. Henke, A. Trächtler, and W. Homberg. Model-Based Approach for Self-correcting Strategy Design for Manufacturing of Small Metal Parts. In Digital Product and Process Development, pages 320–329, 2013.Google Scholar
  20. 20. J.J.E. Slotine and W. Li. Applied Nonlinear Control. Prentice Hall, 1991.Google Scholar
  21. 21. Hassan K. Khalil. Nonlinear Systems. Macmillan Publishing Company, 1992.Google Scholar
  22. 22. K. J. Astrom. Adaptive control around 1960. In IEEE Conference on Decision and Control, volume 3, pages 2784–2789 vol.3, 1995.Google Scholar
  23. 23. Jun Nakanishi and Stefan Schaal. Feedback error learning and nonlinear adaptive control. Neural Networks, 17(10):1453–1465, 2004.CrossRefGoogle Scholar
  24. 24. D.A. Bristow, M. Tharayil, and A.G. Alleyne. A survey of iterative learning control. IEEE Control Systems, 26(3):96–114, 2006.Google Scholar
  25. 25. J.F. Queisser, K. Neumann, M. Rolf, R.F. Reinhart, and J.J. Steil. An active compliant control mode for interaction with a pneumatic soft robot. In IEEE/RSJ Intern. Conf. on Intelligent Robots and Systems, pages 573–579, 2014.Google Scholar
  26. 26. R.F. Reinhart, Z. Shareef, and J.J. Steil. Hybrid analytical and data-driven modeling for feed-forward robot control. Sensors, 17(2), 2017.CrossRefGoogle Scholar
  27. 27. M. Rolf, J.J. Steil, and M. Gienger. Online goal babbling for rapid bootstrapping of inverse models in high dimensions. In IEEE Intern. Conf. on Development and Learning, pages 1–8, 2011.Google Scholar
  28. 28. R.F. Reinhart. Autonomous exploration of motor skills by skill babbling. Autonomous Robots, (7):1–17, 2017.CrossRefGoogle Scholar
  29. 29. R.S. Sutton, A.G. Barto, and R.J. Williams. Reinforcement learning is direct adaptive optimal control. IEEE Control Systems, 12(2):19–22, 1992.Google Scholar
  30. 30. S. Bhasin. Reinforcement Learning and Optimal Control Methods for Uncertain Nonlinear Systems. PhD thesis, University of Florida, 2011.Google Scholar
  31. 31. E.L. Snelson. Flexible and efficient Gaussian process models for machine learning. PhD thesis, University College London, 2007.Google Scholar
  32. 32. L. Paninski. Design of experiments via information theory. In Advances in Neural Information Processing Systems, pages 1319–1326, 2004.Google Scholar
  33. 33. D.A. Cohn, Z. Ghahramani, and M.I. Jordan. Active learning with statistical models. Journal of Artificial Intelligence Research, (4):129–145, 1996.CrossRefGoogle Scholar
  34. 34. P. Jackson. Introduction to expert systems. Addison-Wesley, 1986.Google Scholar
  35. 35. R.F. Reinhart. Industrial Data Science – Data Science in der industriellen Anwendung. Industrie 4.0 Management, (32):27–30, 2016.Google Scholar
  36. 36. R.F. Reinhart, A. Kühn, and R. Dumitrescu. Schichtenmodell für die Entwicklung von Data Science Anwendungen im Maschinen- und Anlagenbau. In Wissenschaftsforum Intelligente Technische Systeme, pages 321–334, 2017.Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2020

Authors and Affiliations

  • Felix Reinhart
    • 1
  • Sebastian von Enzberg
    • 1
  • Arno Kühn
    • 1
  • Roman Dumitrescu
    • 1
  1. 1.Fraunhofer IEM Institute for Mechatronic Systems DesignPaderbornGermany

Personalised recommendations