A New Adaptive Control Scheme Using Dynamic Neural Networks
Khaled Nouri*, Rached Dhaouadi**, and Naceur Benhadj Braiek*
*Laboratoire d’Etude et Commande Automatique de Processus, Ecole Polytechnique de Tunisie, BP, 748 La Marsa, 2078 Tunisie
**Department of Electrical Engineering, School of Engineering, American University of Sharjah, P.O. Box 26666, Sharjah, UAE
A new adaptive neuro-control structure is proposed for the speed control of a nonlinear motor drive system and the compensation of the nonlinearities. A dynamic artificial neural network is used for the on-line adaptive control of the nonlinear motor drive system with high static and Coulomb friction. The neural network is first trained off-line to learn the inverse dynamics of the motor drive system using a layer decoupled extended Kalman filter algorithm. The proposed control scheme is validated experimentally on a dc motor drive system using a standard personal computer. The results obtained confirm the excellent tracking performance and disturbance rejection properties of the system.
-  G. L. Plett, “Adaptive inverse control of linear and nonlinear systems using dynamic neural networks,” IEEE Trans. on Neural Networks, 14, pp. 360-376, 2003.
-  S. H. Lane and R. F. Stengel, “Flight control design using nonlinear inverse dynamics,” Automatica, 24, pp. 471-483, 1988.
-  X. M. Ren, A. B. Rad, P. T. Chan, and W. L. Lo, “Identification and control of continuous-time nonlinear systems via dynamic neural networks,” IEEE Transactions on Industrial Electronics, 50, pp. 478-486, 2003.
-  I. Kanellakopoulos, P. V. Kokotovic, and R. Mariano, “An extended direct scheme for robust adaptive nonlinear control,” Automatica, 34, pp. 247-255, 1991.
-  D. Enns, D. Bugajski, R. Hendrick, and G. Stein, “Dynamic inversion: An evolving methodology for flight control design,” Int. J. Contr., 59, pp. 71-91, 1994.
-  L. Yan and C. J. Li, “Robot learning control based on recurrent neural networks,” Journal of Robot. Syst., 14, pp. 26-33, 1997.
-  G. V. Puskorius and L. A. Feldkamp, “Decoupled extended Kalman filter training of feed-forward layered neural networks,” Proc. IEEE International Joint Conference on Neural Networks, Vol.1, pp. 771-777, 1991.
-  S. Singhal and L. Wu, “Training multi-layer perceptions with the extended Kalman algorithm,” In Advances in Neural Information Proceeding Systems 1, Vol.1, pp. 133-140, 1988.
-  K. Nouri, R. Dhaouadi, and N. B. Braiek, “A dynamic neural network based decoupled extended Kalman filter control applying to motor drive system,” 17ème Congrés Mondial IMACS, Calcul Scientifique, Mathématique Appliquées et Simulation, 2005.
-  P. J. Werbos, “Back propagation through time: what it does and how to do it?,” Proc. of the IEEE, Vol.78, pp. 1550-1560, 1990.
Copyright© 2008 by Fuji Technology Press Ltd. and Japan Society of Mechanical Engineers. All right reserved.