Neural network model based predictive control for multivariable nonlinear systems

DOI

10.2991/iske.2007.101How to use a DOI?

Keywords

Neural networks, Model predictive control, Nonlinear systems, ARX model

Abstract

A nonlinear model predictive control (NMPC) algorithm based on a BP-ARX combination model is proposed for multivariable nonlinear systems whose static nonlinearity between inputs and outputs could be obtained. The dynamic behavior of the system is described by a parameter varying ARX model, whose parameters are estimated on-line with recursive least-squares algorithm and rescaled properly according to a BP neural network representing the system static nonlinearity. The construction of the BP-ARX model and a constrained NMPC algorithm based on the BP-ARX model are elaborated. The effectiveness of the proposed method is demonstrated by simulation on a multivariable chemical reactor system

Copyright

© 2007, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jixin Qian
AU  - Yang Jianfeng
AU  - Zhao Jun
AU  - Niu Jian
PY  - 2007/10
DA  - 2007/10
TI  - Neural network model based predictive control for multivariable nonlinear systems
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 591
EP  - 597
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.101
DO  - 10.2991/iske.2007.101
ID  - Qian2007/10
ER  -