Neural network model adaptation and its application to process control

被引：22

作者：

Chang, TK ^{[1
]}

Yu, DL ^{[1
]}

Yu, DW ^{[1
]}

机构：

[1] Liverpool John Moores Univ, Dept Engn, Control Syst Res Grp, Liverpool L3 3AF, Merseyside, England

来源：

ADVANCED ENGINEERING INFORMATICS | 2004年 / 18卷 / 01期

关键词：

adaptive neural networks; extended Kalman filter; model inversion; continuous-stirred tank reactor processes;

D O I：

10.1016/j.aei.2004.01.001

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A multi-layer perceptron network is made adaptive by weight updating using the extended Kalman filter (EKF). When the network is used as a model for a non-linear plant, the model can be on-line adapted with input/output, data to capture system time-varying dynamics and consequently used in adaptive control. The paper describes how the EKF algorithm is used to update the network model and gives the implementation procedure. The developed adaptive model is evaluated for on-line modelling and model inversion control of a simulated continuous-stirred tank reactor. The modelling and control results show the effectiveness of model adaptation to system disturbance and a global tracking control. (C) 2004 Elsevier Ltd. All rights reserved.

引用

页码：1 / 8

页数：8

共 20 条

[1] [Anonymous], 1990, IEEE T NEURAL NETWOR
[2] [Anonymous], P IFAC SAF PROC
[3] CHANG TK, P UKACC INT C CONTR
[4] RECURSIVE HYBRID ALGORITHM FOR NONLINEAR-SYSTEM IDENTIFICATION USING RADIAL BASIS FUNCTION NETWORKS
CHEN, S
BILLINGS, SA
GRANT, PM
[J]. INTERNATIONAL JOURNAL OF CONTROL, 1992, 55 (05) : 1051 - 1070
[5] REPRESENTATIONS OF NON-LINEAR SYSTEMS - THE NARMAX MODEL
CHEN, S
BILLINGS, SA
[J]. INTERNATIONAL JOURNAL OF CONTROL, 1989, 49 (03) : 1013 - 1032
[6] Linear control of nonlinear systems: Interplay between nonlinearity and feedback
Eker, SA
Nikolaou, M
[J]. AICHE JOURNAL, 2002, 48 (09) : 1957 - 1980
[7] Dynamic structure neural networks for stable adaptive control of nonlinear systems
Fabri, S
Kadirkamanathan, V
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (05): : 1151 - 1167
[8] ITERATIVE INVERSION OF NEURAL NETWORKS AND ITS APPLICATION TO ADAPTIVE-CONTROL
HOSKINS, DA
HWANG, JN
VAGNERS, J
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (02): : 292 - 301
[9] NEURAL NETWORKS FOR NONLINEAR INTERNAL MODEL CONTROL
HUNT, KJ
SBARBARO, D
[J]. IEE PROCEEDINGS-D CONTROL THEORY AND APPLICATIONS, 1991, 138 (05): : 431 - 438
[10] JACOBS OLR, 1983, INTRO CONTROL THEORY

← 1 2 →