Abstract
This paper presents a procedure to add the nonlinear system dynamics to the Levenberg-Marquardt algorithm. This algorithm is used to train a Neural Network Controller without the whole knowledge of the system to be controlled. Simulation results show a correct online training of the NN Controller.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Norgaard, M., Ravn, O., Poulsen, N., Hansen, L.: Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook. Springer, Heidelberg (2003)
Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the marquardt algorithm. IEEE Trans. on Neural Networks 5(6), 989–993 (1994)
Irigoyen, E., Galván, J., Pérez-Ilzarbe, M.: Neural networks for constrained optimal control of nonlinear systems. In: Neural Computing: New Challenges and Perspectives for the New Millennium, vol. 4, pp. 299–304 (2000)
Galván, J.: Tuning of optimal neural controllers. In: Proc. Int. Conf. on Engineering of Intelligent Systems, pp. 213–219 (1998)
Fujinaka, T., Kishida, Y., Yoshioka, M., Omatu, S.: Stabilization of double inverted pendulum with self-tuning neuro-pid. In: Proc. of the IJCNN, vol. 4, pp. 345–348 (2000)
Pirabakaran, K., Becerra, V.: Pid autotuning using neural networks and model reference adaptive control. In: IFAC World Congress (2002)
Narendra, K.S., Parthasarathy, K.: Identification and control of dynamical systems using neural networks. IEEE Trans. on Neural Networks 1(1), 427 (1990)
Irigoyen, E., Pinzolas, M.: Numerical bounds to assure initial local stability of narx multilayer perceptrons and radial basis functions. Neurocomputing 72(1-3), 539–547 (2008)
Irigoyen, E., Galván, J.B., Pérez-Ilzarbe, M.J.: A neuro predictive controller for constrained nonlinear systems. In: IASTED Int. Conf. Artificial Intelligence and Applications, pp. 569–574 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Larrea, M., Irigoyen, E., Gómez, V. (2010). Adding Nonlinear System Dynamics to Levenberg-Marquardt Algorithm for Neural Network Control. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds) Artificial Neural Networks – ICANN 2010. ICANN 2010. Lecture Notes in Computer Science, vol 6354. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15825-4_47
Download citation
DOI: https://doi.org/10.1007/978-3-642-15825-4_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15824-7
Online ISBN: 978-3-642-15825-4
eBook Packages: Computer ScienceComputer Science (R0)