Neural generalized predictive controller stability analysis

Author

Abdel-Ghaffar, Hesham ; Shoukry, Yasser ; Hassan, Ahmed ; Hammad, Sherif ; Abbas, Hazem

Author_Institution

Invensys Eng. Excellence Centers, Cairo, Egypt

fYear

2011

fDate

14-16 Oct. 2011

Firstpage

1

Lastpage

6

Abstract

This paper emphasizes on the stability analysis of the Neural Generalized Predictive Controller (NGPC) algorithm using Lyapunov methods. NGPC is a hybrid combination between the well known GPC algorithm and a Feed Forward Multi Layer Perceptron (FF MLP) neural network model identifier. This combination leads to a better stability characteristics in the closed loop systems in the presence of high nonlinearities in the process. In this paper, we prove the stability characteristics of NGPC and then present simulation results showing the efficiency of using NGPC over ordinary GPC.

Keywords

Lyapunov methods; closed loop systems; control nonlinearities; feedforward neural nets; multilayer perceptrons; neurocontrollers; predictive control; stability; GPC algorithm; Lyapunov method; NGPC; closed loop system; feedforward multi layer perceptron neural network model identifier; neural generalized predictive controller stability analysis; Algorithm design and analysis; Biological neural networks; Cost function; Matrices; Prediction algorithms; Stability analysis; Symmetric matrices; Lyapunov Stability; Neural Generalized Predictive Controller; Neural Identifier; Newton-Raphson;

fLanguage

English

Publisher

ieee

Conference_Titel

System Theory, Control, and Computing (ICSTCC), 2011 15th International Conference on

Conference_Location

Sinaia

Print_ISBN

978-1-4577-1173-2

Type

conf

Filename

6085666