GA-BASED ADAPTIVE NEURAL NETWORK CONTROLLERS FOR NONLINEAR SYSTEMS

NCUIR > Engineering College > Department of Civil Engineering > journal & Dissertation > Item 987654321/49793

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/49793

Title:	GA-BASED ADAPTIVE NEURAL NETWORK CONTROLLERS FOR NONLINEAR SYSTEMS
Authors:	Chen,CW;Chen,PC
Contributors:	土木工程學系
Keywords:	FEEDFORWARD NETWORKS;FUZZY CONTROL;TIME;APPROXIMATION;BACKPROPAGATION;STABILITY;ALGORITHM;DISCRETE;DESIGN
Date:	2010
Issue Date:	2012-03-27 16:16:52 (UTC+8)
Publisher:	國立中央大學
Abstract:	In this study, we propose a method of stability analysis for a GA-Based reference ANNC which is capable of handling these types of problems in a nonlinear system. First of all, radial basis function networks are utilized to well approximate an uncertain and nonlinear plant, for the tracking of a reference trajectory. Next, the initial values of the consequent parameter vector are decided via a genetic algorithm (GA), after a modified adaptive law is derived based on Lyapunov stability theory for the purpose of controlling the nonlinear system which is used for tracking a user-defined reference model. The requirement of the Kalman-Yacubovich lemma is fulfilled. A boundary-layer function is introduced into these updating laws to cover parameter and modeling errors, and to guarantee that the state errors converge within a specified error bound. After this, an adaptive neural network controller (ANNC) is derived to simultaneously stabilize and control the system. Finally, a numerical simulation is carried out. The simulation results show the rapidity and efficiency with which the control methodology can control nonlinear systems.
Relation:	INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL
Appears in Collections:	[Department of Civil Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	428	View/Open

社群 sharing

Loading...