Abstract
In this paper, we present an identification method for mechatronic systems consisting of a linear part with unknown parameters and an unknown nonlinearity (systems with an isolated nonlinearity). Based on this identification method we introduce an adaptive state space controller in order to generate an overall linear system behavior. A structured recurrent neural network is used to identify the usknown parameters of the known signal flow chart. The control concept starts from a nonlinear canonical form and takes advantage of the online identified parameters of the plant.
The novelty of this approach is the simultaneous identification of the parameters of the linear part and the nonlinearity, the use of prior structural and parameter knowledge and the ability to completely compensate the nonlinearity.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Brychcy, T. (1997) Vorstrukturierte Verallgemeinerte Rekurrente Neuronale Netze. Interner Bericht, TU-München
Föllinger, O. (1992) Regelungstechnik, Einführung in die Methoden und ihre Anwendung. Hüthigbuch Verlag
Hintz, C., Rau, M., Schröder, D. (2000) Combined Identification of Parameters and Nonlinear Chrachteristics based on Input-Output Data. Proceedings of 6th International Workshop on Advanced Motion Control (AMC2000) Nagoya, Japan, pp. 175–180
Isidori, A. (1989) Nonlinear Control Systems. Springer-Verlag
Lenz, U. (1998) Lernfähige neuronale Beobachter für eine Klasse nichtlinearer dynamischer Systeme und ihre Anwendung zur intelligenten Regelung von Verbrennungsmotoren. Dissertation, Lehrstuhl für Elektrische Antriebssysteme, TU München
Schröder, D. (1999) Intelligent Observer and Control Design for Nonlinear Systems. Springer-Verlag
Schroöder, D. (1995) Elektrische Antriebe 2. Springer-Verlag
Slotine, J., Weiping, L. (1991) Applied Nonlinear Control. Prentice-Hall
Sommer, R. (1979) Entwurf nichtlinearer, zeitvarianter Systeme durch Polvorgabe. Regelungstechnik, Oldenbourg Verlag, Vol. 12, pp. 393–399
Williams, R.J., Zipser, D. (1990) Gradient-Based Learning Algorithms for Recurrent Connectionist Networks. Tech. Rep. NU-CSS90-9, College of Computer Science, Northeastern University, Boston, MA
Zell, A. (1994) Simulation Neuronaler Netze. Addison-Wesley
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2001 Springer-Verlag London Limited
About this paper
Cite this paper
Hintz, C., Rau, M., Schröder, D. (2001). Nonlinear adaptive state space control for 2 class of nonlinear systems with unknown parameters. In: Isidori, A., Lamnabhi-Lagarrigue, F., Respondek, W. (eds) Nonlinear control in the Year 2000. Lecture Notes in Control and Information Sciences, vol 258. Springer, London. https://doi.org/10.1007/BFb0110236
Download citation
DOI: https://doi.org/10.1007/BFb0110236
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-85233-363-8
Online ISBN: 978-1-84628-568-4
eBook Packages: Springer Book Archive