A neural network model predictive controller

被引:139
作者
Akesson, Bernt M. [1 ]
Toivonen, Hannu T. [1 ]
机构
[1] Abo Akad Univ, Dept Chem Engn, FIN-20500 Turku, Finland
基金
芬兰科学院;
关键词
model predictive control; neural networks; nonlinear control;
D O I
10.1016/j.jprocont.2006.06.001
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A neural network controller is applied to the optimal model predictive control of constrained nonlinear systems. The control law is represented by a neural network function approximator, which is trained to minimize a control-relevant cost function. The proposed procedure can be applied to construct controllers with arbitrary structures, such as optimal reduced-order controllers and decentralized controllers. (C) 2006 Elsevier Ltd. All rights reserved.
引用
收藏
页码:937 / 946
页数:10
相关论文
共 24 条
[1]   Neural regulator design [J].
Ahmed, MS ;
Al-Dajani, MA .
NEURAL NETWORKS, 1998, 11 (09) :1695-1709
[2]   Neural network approximation of a nonlinear model predictive controller applied to a pH neutralization process [J].
Åkesson, BM ;
Toivonen, HT ;
Waller, JB ;
Nyström, RH .
COMPUTERS & CHEMICAL ENGINEERING, 2005, 29 (02) :323-335
[3]  
Allgower F., 1999, Advances in Control. Highlights of ECC'99, P391
[4]   Neurocontrol: A literature survey [J].
Balakrishnan, SN ;
Weil, RD .
MATHEMATICAL AND COMPUTER MODELLING, 1996, 23 (1-2) :101-117
[5]   The explicit linear quadratic regulator for constrained systems [J].
Bemporad, A ;
Morari, M ;
Dua, V ;
Pistikopoulos, EN .
AUTOMATICA, 2002, 38 (01) :3-20
[6]  
Bertsekas D. P., 1996, Neuro Dynamic Programming, V1st
[7]   Neural network implementation of nonlinear Receding-Horizon control [J].
Cavagnari, L ;
Magni, L ;
Scattolini, R .
NEURAL COMPUTING & APPLICATIONS, 1999, 8 (01) :86-92
[8]  
ENGELL S, 1993, PROCEEDINGS OF THE 1993 AMERICAN CONTROL CONFERENCE, VOLS 1-3, P2941
[9]   MODELING OF PH FOR CONTROL [J].
GUSTAFSSON, TK ;
SKRIFVARS, BO ;
SANDSTROM, KV ;
WALLER, KV .
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 1995, 34 (03) :820-827
[10]   Nonlinear model predictive control: current status and future directions [J].
Henson, MA .
COMPUTERS & CHEMICAL ENGINEERING, 1998, 23 (02) :187-202