Neural network control for large scale systems with faults and perturbations

Author

Atig, Asma ; Druaux, Fabrice ; Lefebvre, Dimitri ; Abderrahim, Kamel ; Ben Abdennour, Ridha

Author_Institution

GREAH, Univ. du Havre, Le Havre, France

fYear

2010

fDate

6-8 Oct. 2010

Firstpage

305

Lastpage

310

Abstract

This paper provides an adaptation algorithm for the control of complex system via recurrent neural networks. The proposed method is derived from RTRL algorithm. Neural emulator and neural controller parameters are one-line updated independently. To illustrate the tracking and the disturbance rejection capabilities of the real time control algorithm and the efficiency of the networks parameters relaxation, an application to the large scale process: Tennessee Eastman Challenge Process (TECP) is presented.

Keywords

adaptive control; chemical industry; large-scale systems; neurocontrollers; perturbation techniques; recurrent neural nets; RTRL algorithm; Tennessee Eastman challenge process; adaptation algorithm; complex system; disturbance rejection capabilities; large scale systems; network parameter relaxation; neural controller; neural emulator; real time control algorithm; recurrent neural network control; Artificial neural networks; Cooling; Inductors; Neurons; Particle separators; Process control; Valves;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Fault-Tolerant Systems (SysTol), 2010 Conference on

Conference_Location

Nice

Print_ISBN

978-1-4244-8153-8

Type

conf

DOI

10.1109/SYSTOL.2010.5675946

Filename

5675946