A neural network approach to nonlinear model predictive control

Author

Yan, Zheng ; Wang, Jun

Author_Institution

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

fYear

2011

fDate

7-10 Nov. 2011

Firstpage

2305

Lastpage

2310

Abstract

This paper proposes a neural network approach to nonlinear model predictive control (NMPC). The NMPC problem is formulated as a convex programming problem via Jacobain linearization. The unknown high-order term associated with the linearization is estimated by using a feedforward neural network via supervised learning. The convex optimization problem involved in MPC is solved by using a recurrent neural network. Simulation results are provided to demonstrate the performance of the approach.

Keywords

Jacobian matrices; convex programming; feedforward neural nets; learning (artificial intelligence); nonlinear control systems; predictive control; recurrent neural nets; Jacobain linearization; NMPC; convex programming problem; feedforward neural network; nonlinear model predictive control; recurrent neural network; supervised learning; unknown high-order term; Biological neural networks; Magnetic materials; Optimization; Photonic crystals; Recurrent neural networks; Testing; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

IECON 2011 - 37th Annual Conference on IEEE Industrial Electronics Society

Conference_Location

Melbourne, VIC

ISSN

1553-572X

Print_ISBN

978-1-61284-969-0

Type

conf

DOI

10.1109/IECON.2011.6119669

Filename

6119669

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2876731