1. Proceedings
  2. I3M
  3. 2018
  4. EMSS
  5. 10.46354/i3m.2018.emss.043

Data modelling approach for physical systems

  • a Stefanie Winkler   ,
  • b Andreas Körner  ,
  • c Felix Breitenecker  
  • a, b, c Institute for Analysis and Scientific Computing, TU Wien
Cite as
Winkler S., Körner A., Breitenecker F. (2018). Data modelling approach for physical systems. Proceedings of the 30th European Modeling & Simulation Symposium (EMSS 2018), pp. 310-315. DOI: https://doi.org/10.46354/i3m.2018.emss.043

Abstract

This contribution deals with the possible applications of neural networks for hybrid models. After a basic introduction to neural networks and hybrid modelling some applications are discussed. On the one hand, the substitutability of hybrid models is up for debate. On the other hand, the possibility of combining neural networks with physical models, e.g. for determining individual parameters, are focused. In the end the discussed approaches are applied and compared using a fundamental example.

References

  1. Hornik K., 1989. Multilayer Feedforward Networks are Universal Approximators. In: Neural Networks, vol
    2, pp.359-366.
  2. Körner A., Winkler S., Breitenecker F., 2016. Possibilities in State Event Modelling of Hybrid Systems. In: Proceedings of 9th EUROSIM Congress on Modelling and Simulation, pp. 542- 543.
  3. Lu W., Pingping Z.,Ferrari S., 2016. A Hybrid-Adaptive Dynamic Programming Approach for the Model-
    Free Control of Nonlinear Switched Systems. In: IEEE Transactions on automatic control, vol 61, No. 10, pp.3203-3208.
  4. Martinus G., Lampert C.H., 2016. Extrapolation and learning equations. 2016. arXiv preprint
    https://arxiv.org/abs/1610.02995.
  5. Mehlhase A., 2014. A Python framework to create and simulate models with variable structure in common
    simulation environments.In: Mathematical and Computer Modelling of Dynamical Systems 20 (6),
    pp. 566-583
  6. Y., Teel A. R., 2010. Using the Set-Values Bounding Ball for Bounding Zeno Solution of Lagrangian Hybrid Systems. In Proceedings: 8th IFAC Symposium on Nonlinear Control Systems, pp 801-806.
  7. Psichogios D.C., Ungar L.H., 1992. A Hybrid Neural Network-First Principles Approach to Process
    Modeling. In: AIChE Journal vol. 38, No. 10, pp. 1499-1511.
  8. Ziegler B. P., Praehofer H., Kim T.G., 2000 Theory of Moedling and Simulation, 2nd Edition. Academic
    Press.