English  |  正體中文  |  简体中文  |  Items with full text/Total items : 28588/40619
Visitors : 4199088      Online Users : 51
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/13839

Title: 類神經網路應用於磁浮系統之控制研究
Apply a Neural Network to Control a Magnetic Levitation System
Authors: Chien-Lin Chen
Contributors: NTOU:Department of Mechanical and Mechatronic Engineering
Keywords: 類神經控制;倒傳遞網路
Neural Network control;BPNN;NARMA-L2
Date: 2009
Issue Date: 2011-06-30T07:28:41Z
Abstract: 摘要 本研究主要探討類神經網路控制器於磁浮系統(Magnetic Levitation System)之應用。這裡所使用的磁浮系統屬於吸引型。許多的控制理論需經過四個步驟:(1)建立模型,(2)系統數學描述,(3)控制系統的分析,(4)控制系統的設計。建立傳統數學模型的困難在於面對複雜、非線性的問題時,必須經由一些假設、簡化環境之後才能建構物理模式或數學方程式。且在設計上仍有許多參數需小心調整才能改善響應性能。類神經網路在處理複雜的工作時,不需要針對問題定義複雜的數學模式。可藉由學習來面對複雜的問題與不確定性的環境。所以本研究嚐試使用類神經網路控制器來控制磁浮系統。本研究使用類神經網路NARMA-L2(Nonlinear Auto-Regressive Moving Average, NARMA)的控制理論,類神經網路結構使用三層式(輸入層隱藏層輸出層)倒傳遞類神經網路(Back-Propagation Neural Network, BPNN),模擬結果顯示是可控制成功的。
Abstract In this research about a neural network controller is applied to Magnetic Levitation System. Here the Magnetic Levitation System is attraction type. It is extremely nonlinear and unstable. The control theory usually has four steps: (1) model building, (2) system mathematics describes, (3) the controlled system is analyzed, (4) the controlled system is designed. The mathematical model must be assumed and simplified before the physical model or mathematical equation of mathematical model is constructed. But system has many parameters must be carefully adjusted, which can improve the response performance. Neural network need not be defined any complex mathematical equation. Neural network can learn, so neural network can be applied complex question and uncertain environment. Therefore in this research a neural network controller is used to control magnetic levitation system. In this research the NARMA-L2 (Nonlinear Auto-Regressive Moving Average, NARMA) control theory of neural network is used, Three layers type (input layer hidden layer output layer) back-propagation neural network (BPNN) is used the structure of neural network. The simulate result can be control successfully.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0M96720060
Appears in Collections:[機械與機電工程學系] 博碩士論文

Files in This Item:

File Description SizeFormat

All items in NTOUR are protected by copyright, with all rights reserved.


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback