Parallel Model Predictive Control of Nonlinear Time-delay Systems Based on Recurrent Neural Network

Author

Wang, Dongqing ; Xu, Shuhua

Author_Institution

Qingdao Univ., Qingdao

fYear

2008

fDate

6-8 April 2008

Firstpage

677

Lastpage

680

Abstract

With regards to the nonlinear time-delay systems, d-step-ahead predictive model of neural network predictive control is adopted. This paper realizes the RTRL (real time recurrent learning) algorithm of parallel model of neural network predictive control for nonlinear time-delay systems for the first time. It describes advantages of RTRL algorithm of parallel model, compared with BP algorithm of series-parallel model. Simulation verified that RTRL algorithm of parallel model is better than BP algorithm of series-parallel model in performance and in disturbance rejection.

Keywords

backpropagation; delay systems; neurocontrollers; nonlinear control systems; predictive control; recurrent neural nets; BP algorithm; disturbance rejection; nonlinear time-delay system; parallel model predictive control; real time recurrent learning; recurrent neural network; series-parallel model; Control system synthesis; Control systems; Educational institutions; Neural networks; Nonlinear control systems; Predictive control; Predictive models; Real time systems; Recurrent neural networks; Switches; RTRL (real time recurrent learning) algorithm; parallel model; predictive control; series-parallel model;

fLanguage

English

Publisher

ieee

Conference_Titel

Networking, Sensing and Control, 2008. ICNSC 2008. IEEE International Conference on

Conference_Location

Sanya

Print_ISBN

978-1-4244-1685-1

Electronic_ISBN

978-1-4244-1686-8

Type

conf

DOI

10.1109/ICNSC.2008.4525302

Filename

4525302