Indirect inverse adaptive control based on neural networks using dynamic back propagation for nonlinear dynamic systems

Author

Lesueur, Sébastierz ; Massicotte, Daniel ; Sicard, Pierre

Author_Institution

Dept. of Electr. & Comput. Eng., Quebec Univ., Trois-Rivieres, Que., Canada

Volume

3

fYear

2001

fDate

6-9 May 2001

Firstpage

600

Abstract

In this paper, Dynamic Back Propagation (DBP) is reinvestigated in the context of indirect inverse control of unknown nonlinear dynamic systems using Artificial Neural Networks (ANNs). The overall control scheme includes two networks. The first is used as an approximating model of the unknown nonlinear dynamic behavior of the plant while the second is the controller. The trajectory error is backpropagated through the neural model using DBP algorithm to obtain the control input error. The controller, which is a recurrent ANN, is then adapted also using DBP algorithm. Simulation results obtained with both Standard Back Propagation (SBP) and DBP algorithms for a fourth order nonlinear system clearly show some advantage of DBP

Keywords

adaptive control; backpropagation; neural nets; nonlinear dynamical systems; artificial neural network; dynamic back propagation algorithm; indirect inverse adaptive control; nonlinear dynamic system; Adaptive control; Artificial neural networks; Control systems; Delay effects; Error correction; Multi-layer neural network; Neural networks; Neurocontrollers; Nonlinear control systems; Nonlinear systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2001. ISCAS 2001. The 2001 IEEE International Symposium on

Conference_Location

Sydney, NSW

Print_ISBN

0-7803-6685-9

Type

conf

DOI

10.1109/ISCAS.2001.921382

Filename

921382