An integral-plus-state adaptive neural control of mechanical system

Author

Baruch, Ieroham S. ; Martinez, Alfredo Del Carmen ; Thomas, Federico ; Garrido, Ruben

Author_Institution

Bulgarian Acad. of Sci., Sofia, Bulgaria

Volume

2

fYear

2003

fDate

23-25 June 2003

Firstpage

813

Abstract

Two integral-plus-state (IPS) direct adaptive neural control schemes (with one or two I-terms), appropriate for mechanical systems applications, are proposed. Both schemes contain recurrent trainable neural network (RTNN-1) as a plant parameter identificator and state estimator, and a neural controller (RTNN-2) with one or two additional I-terms, so to form the IPS action. Simulation results, obtained with a 1-DOF mechanical plant with friction, corrupted by noise, confirmed the good dynamic performance of both schemes.

Keywords

adaptive control; neurocontrollers; parameter estimation; recurrent neural nets; state estimation; 1-DOF mechanical plant; RTNN; dynamic control performance; friction; high precision motion control systems; integral-plus-state adaptive neural control; mechanical system; neural controller; noise corruption; plant parameter identificator; recurrent trainable neural network; state estimator; Adaptive control; Automatic control; Backpropagation; Control systems; Friction; Mechanical systems; Neural networks; Programmable control; Recurrent neural networks; Three-term control;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Applications, 2003. CCA 2003. Proceedings of 2003 IEEE Conference on

Print_ISBN

0-7803-7729-X

Type

conf

DOI

10.1109/CCA.2003.1223114

Filename

1223114