RBF neural networks base on particle swarm optimization and its application in control system of flatness and gauge

Author

Ji, Yang ; Zhou, Wuneng ; Yu, Luwei

Author_Institution

Coll. of Inf. Sci. & Technol., Donghua Univ., Shanghai, China

fYear

2012

fDate

29-31 May 2012

Firstpage

312

Lastpage

315

Abstract

The automatic flatness control and automatic gauge control (AFC-AGC) is a complex system with strong nonlinear coupling and large time delay. With the requirement of further enhancement of product quality, putting forward decoupling control of strip shape and thickness is urgent. So in this paper, the decoupling control based on adaptability of the Radical is Basis Function (RBF) neural network, together with an on-line learning algorithm based on process optimum are proposed with good performances of decoupling and robustness.

Keywords

large-scale systems; neurocontrollers; particle swarm optimisation; product quality; radial basis function networks; rolling mills; RBF neural network; RBF neural networks; automatic flatness control; automatic gauge control; complex system; decoupling control; nonlinear coupling; online learning algorithm; particle swarm optimization; product quality enhancement; Approximation methods; Biological neural networks; Mathematical model; Radial basis function networks; Training; Vectors; Particle swarm optimization (PSO); RBF network; decouple AFC-AGC complex system;

fLanguage

English

Publisher

ieee

Conference_Titel

Natural Computation (ICNC), 2012 Eighth International Conference on

Conference_Location

Chongqing

ISSN

2157-9555

Print_ISBN

978-1-4577-2130-4

Type

conf

DOI

10.1109/ICNC.2012.6234693

Filename

6234693