Hsiuping University of Science and Technology Institutional Repository : Item 310993100/1603

English | 正體中文 | 简体中文 | Items with full text/Total items : 4334/7631
Visitors : 3196394 Online Users : 436

RC Version 3.2 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

Scope Adv. Search

Login ‧ Upload ‧ Help ‧ About ‧ Administer

HUSTIR > College of Engineering > Department of Electrical Engineering & Graduate Institute > Journal > Item 310993100/1603

Please use this identifier to cite or link to this item: http://ir.hust.edu.tw/dspace/handle/310993100/1603

Title:	Discrete-time neural predictive controller design
Authors:	Chi-Huang Lu
Keywords:	generalized predictive control recurrent neural network nonlinear system
Date:	2009-03
Issue Date:	2009-05-24T04:06:26Z
Abstract:	This paper presents a design methodology for generalized predictive control (GPC) using recurrent neural network (RNN). A discrete-time mathematical model using RNN is constructed and a learning algorithm adopting an adaptive learning rate (ALR) approach is employed to identify the unknown parameters in the recurrent neural network model (RNNM). The neural predictive controller (NPC) is obtained via a generalized predictive performance criterion, and the convergence of the NPC including the adaptive optimal rate (AOR) by the Lyapunov stability theorem is presented. The illustrative process system is used to demonstrate the effectiveness of the proposed strategy. Results from numerical simulations show that the proposed method is capable of controlling nonlinear system with satisfactory performance under setpoint and load changes.
Relation:	修平學報 18, 27-38
Appears in Collections:	[Department of Electrical Engineering & Graduate Institute] Journal

Files in This Item:

File	Description	Size	Format
18-03.pdf		169Kb	Adobe PDF	2637	View/Open