Skip to main content
SpringerLink
Log in

Approximate Feedback Linearisation Using Multilayer Neural Networks

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

In this paper we introduce the approximate feedback linearisation using multilayer feedforward neural networks. We propose to approximate a basis of the one-dimensional codistribution of an affine nonlinear system with the derivative of a multilayer neural network [6] and form a change of coordinates with n multilayer neural networks [5]. In this paper we will prove that the transformation can define a local diffeomorphism, with which a local stabilising feedback law can be designed for a kind of non-linearisable nonlinear systems.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. A. Isidori, Nonlinear Control Systems: An Introduction, Springer-Verlag: Berlin, 1989.

    Google Scholar 

  2. R. Unbehauen, Systemtheorie 2, R. Oldenburg Verlag: Muenchen, 1998.

    Google Scholar 

  3. B. Kolman and W.F. Trench, Elementary Multivariable Calculus, Academic Press: New York, 1972.

    Google Scholar 

  4. A. Cichocki and R. Unbehauen, Neural Networks for Optimisation and Signal Processing, New York: John Whiley and Sons, 1993.

    Google Scholar 

  5. S. He, K. Reif and R. Unbehauen, “A neural approach for control of nonlinear system with feedback linearisation”, IEEE Trans. on Neural Networks, 1997, submitted.

  6. S. He, K. Reif and R. Unbehauen, “Multilayer neural networks for solving a kind of partial differential equations”, Neural Networks, 1997, submitted.

  7. J. Hauser, “Nonlinear control via uniform system approximation”, System and Control Letters, Vol. 17, pp. 145–154, North-Holland, 1991.

    Google Scholar 

  8. A. Banaszuk and J. Hause, “Approximate feedback linearisation: Homotopy operator approach”, SIAM Journal of Control and Optimisation, Vol. 34, pp. 1533–1554, 1996.

    Google Scholar 

  9. K. Hornik, M. Stinchcombe and H. White, “Universal approximation of an unknown mapping and its derivative using multilayer feedforward networks”, Neural Networks, Vol. 3, pp. 551–560, 1990.

    Google Scholar 

  10. E.D. Sontag, “Feedback stabilisation using two-hidden-layer nets”, Technical Report SYCON–90–11, Rutgers Centre for Systems and Control, Rutgers, USA, Oct. 1990.

    Google Scholar 

  11. M.T. Hagan and M.B. Manhaj, “Training Feedback Networks with the Marquardt Algorithm”, IEEE Trans. on Neural Networks, Vol. 5, No. 6, pp. 989–993, Nov. 1994.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Fellow, IEEE, Denmark

    Shouling He & Rolf Unbehauen

Authors
  1. Shouling He
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rolf Unbehauen
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

He, S., Unbehauen, R. Approximate Feedback Linearisation Using Multilayer Neural Networks. Neural Processing Letters 8, 131–144 (1998). https://doi.org/10.1023/A:1009644612275

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1009644612275

Search

Navigation