English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27454/39300
Visitors : 2535158      Online Users : 24
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/35689

Title: 最佳化演算法結合類神經網路控制器於飛機降落系統之應用
Applications of Optimization Algorithms and Neural Network Controllers to Aircraft Landing System
Authors: Cheng-Yen Yu
余政彥
Contributors: NTOU:Department of Communications Navigation and Control Engineering
國立臺灣海洋大學:通訊與導航工程學系
Keywords: 細菌覓食演算法;渾沌粒子群演算法;細菌群演算法
Date: 2012
Issue Date: 2013-10-07T02:57:54Z
Abstract: 飛機在起飛以及降落的時候一直都是飛航安全意外事故中最重要的一部分。航機在進場或落地階段,因為在高度不高及速度不快的情況下,一但遇到剪風或亂流等大氣的劇烈變化,會造成飛機航向及下滑軌跡的偏移,嚴重影響飛航安全。現今大部分的飛機上都已安裝有自動降落系統,能夠在正常的飛航環境中安全地幫助飛行器自動降落,並明顯的減輕飛行員的工作負擔。傳統的自動著陸系統所採用的控制理論為增益預定或傳統適應控制的技術,一旦飛行條件或風擾強度超出系統所能適應之範圍,飛行員就必須關閉自動著陸系統改由手動駕駛接管飛機著陸程序。本論文應用小腦模型控制器以及資源分配網路於飛機著陸控制,結合細菌覓食演算法、粒子群演算法、渾沌粒子群演算法和細菌群演算法調整俯仰角自動導航系統的控制參數,並利用李亞普諾夫理論去推導出最佳化學習律。本文進一步以TMS320C6713 DSP 開發工具,連結JTAG,利用CCS編譯完成的程式碼載入至DSP的快閃記憶體,實現浮點DSP控制器的即時自動著陸系統。
Aircraft takeoff and landing has always been the most important part of aviation safety. In the approach or landing stage, aircraft altitude and speed are low, dramatic changes of atmosphere, such as the wind shear or turbulence, will cause the aircraft off heading and glide path, and seriously affect the flight safety. Nowadays most aircraft have been installed automatic landing system. In the normal environment, aircraft automatic landing system can significantly reduce the pilot's workload. Conventional automatic landing systems are designed by the use of gain scheduling or traditional adaptive control techniques, once the flight conditions or wind disturbance intensity is beyond the limits of the system, the pilot must turn off the automatic landing system and take over the aircraft landing procedures manually. In this thesis, CMAC controller and RAN are applied to aircraft landing control, combined with bacterial foraging algorithm, particle swarm algorithm, chaotic particle swarm algorithm and bacteria swarm algorithm which are used to adjust control parameters of the pitch autopilot. Lyapunov theory is utilized to derive the optimal learning rule. Furthermore, the TMS320C6713 DSP development tools, links, JTAG, CCS compiled code flash memory are applied to achieve real-time automatic landing system by the floating-point DSP controller.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0019967005
http://ntour.ntou.edu.tw/handle/987654321/35689
Appears in Collections:[通訊與導航工程學系] 博碩士論文

Files in This Item:

File Description SizeFormat
index.html0KbHTML92View/Open


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