Modeling hybrid dynamical systems
We present a modeling scheme for multivariate hybrid dynamical systems. From given time series embedded in appropriate state spaces we predict future outputs by making local linear fits in the neighbourhood of the actual state vectors. In particular, the proposed algorithm can be used online. Thus the quality of the forecast is improved by enclosing new measured data.
KeywordsHybrid dynamical systems chaotic behavior tiled state spaces local linear fits
Unable to display preview. Download preview PDF.
- 1.A. Göllü and P. Varaiya, ”Hybrid dynamical systems,” Proc. 28th Conf. Decision Contr., Tampa, FL, pp. 2708–2712, 1989.Google Scholar
- 2.J. A. Stiver and P. J. Antsaklis, ”A novel discrete event system approach to modeling and analysis of hybrid control systems,” Control Systems Tech. Rep. #71, Dept. of Elect. Eng., Univ. of Notre Dame, IN, 1991.Google Scholar
- 3.P. Peleties and R. Decarlo, ”A modeling strategy for hybrid systems based on event structures,” preprint: School of Elect. Eng., Purdue Univ., West Lafayette, IN.Google Scholar
- 5.J. D. Farmer and J. J. Sidorowich, ”Exploiting chaos to predict the future and reduce noise,” Evolution, Learning and Cognition ed. Lee, Y. C. (World Scientific), 1988.Google Scholar
- 8.T. Schürmann and I. Hoffmann, ”The entropy of “strange” billiards inside n- simplexes,” J. Phys. A 28, pp. 5033–5039, 1995.Google Scholar
- 10.A. Back, J. Guckenheimer and M. Myers, ”A Dynamical Simulation Facility for Hybrid Systems,” Lect. Notes in Comp. Science, Vol. 736, pp. 255–267, 1993.Google Scholar
- 13.R. W. Leven, B.-P. Koch and B. Pompe, ”Chaos In Dissipativen Systemen,” Vieweg & Sohn, Braunschweig, 1989.Google Scholar