Nonlinear model predictive control using a recurrent neural network

Author

Pan, Yunpeng ; Wang, Jun

Author_Institution

Dept. of Mech. & Autom. Eng., Chinese Univ. of Hong Kong, Shatin

fYear

2008

fDate

1-8 June 2008

Firstpage

2296

Lastpage

2301

Abstract

As linear model predictive control (MPC) becomes a standard technology, nonlinear MPC (NMPC) approach is debuting both in academia and industry. In this paper, the NMPC problem is formulated as a convex quadratic programming problem based on nonlinear model prediction and linearization. A recurrent neural network for NMPC is then applied for solving the quadratic programming problem. The proposed network is globally convergent to the optimal solution of the NMPC problem. Simulation results are presented to show the effectiveness and performance of the neural network approach.

Keywords

convex programming; neurocontrollers; nonlinear control systems; predictive control; quadratic programming; recurrent neural nets; NMPC problem; convex quadratic programming problem; global convergence; neural network approach; nonlinear model linearization; nonlinear model prediction; nonlinear model predictive control; recurrent neural network; Biological neural networks; Electrical equipment industry; Industrial control; Neural networks; Optimization methods; Predictive control; Predictive models; Process control; Quadratic programming; Recurrent neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on

Conference_Location

Hong Kong

ISSN

1098-7576

Print_ISBN

978-1-4244-1820-6

Electronic_ISBN

1098-7576

Type

conf

DOI

10.1109/IJCNN.2008.4634115

Filename

4634115