A design method for adaptive inverse control using NARX neural networks

Author

Liu, Yaqiu ; Ma, Guangfu ; Jiang, Xueyuan

Author_Institution

Dept. of Control Sci. & Eng., Harbin Inst. of Technol., China

Volume

1

fYear

2004

fDate

15-19 June 2004

Firstpage

459

Abstract

According to NARX dynamic network, a learning algorithm of improved RTRL is presented in this paper and applied to adaptive inverse control system, which consists of two NARX neural networks: one is applied to identify the controlled plant; the other approximates inverse transfer function of the plant. The online training method using NARX is also described in detail. Practical simulation results show NARX-based identifier and controller are feasible and the given algorithm is efficient in the application of adaptive inverse control (AIC).

Keywords

adaptive control; autoregressive processes; control system synthesis; identification; learning (artificial intelligence); neurocontrollers; transfer functions; adaptive inverse control system; inverse transfer function; neural networks; nonlinear autoregressive with exogenous input; online training method; plant identification; real time recurrent learning algorithm; Adaptive control; Adaptive systems; Control systems; Design methodology; Electronic mail; Neural networks; Programmable control; Transfer functions;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on

Print_ISBN

0-7803-8273-0

Type

conf

DOI

10.1109/WCICA.2004.1340614

Filename

1340614