English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27320/39164
Visitors : 2478673      Online Users : 37
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/987654321/18429

Title: 應用混合式小腦模型神經網路-PID控制於雙旋翼多輸入多輸出系統及FPGA硬體實現
Application of Hybrid CMAC-PID Control to TRMS with FPGA Implementation
Authors: Zong-Ru Yu
游宗儒
Contributors: NTOU:Department of Communications Navigation and Control Engineering
國立臺灣海洋大學:通訊與導航工程系
Keywords: 小腦模型;神經網路;FPGA;雙旋翼多輸入多輸出系統
CMAC;PID;FPGA;TRMS
Date: 2010
Issue Date: 2011-07-04
Abstract: 本論文是針對一實驗用的雙旋翼多輸入多出系統(TRMS),利用混合式智慧型控制對其做定位與追蹤控制,將TRMS的水平和垂直部分做解耦合的控制設計,與對TRMS的耦合情況做控制設計,使解耦合和耦合狀態都可以達到快速且準確的移動到指定的角度。控制器部分是結合CMAC與PID而成的混合式智慧型控制器,PID控制具有結構簡單、穩定性好、工作可靠、調整方便等四項優點,而CMAC是一類聯想記憶神經網路的重要組成部分,它能夠任意學習多維非線性映射。CMAC演算法可有效地用於非線性函數逼近、動態建模、控制系統設計等。CMAC-PID混和控制的功能分別為:PID控制器實現反饋控制,保持系統的穩定性,且抑制擾動;CMAC實現前饋控制,實現被控對象的逆動態模型,系統也不失學習速度快的優點。本研究的目的是在於使實驗模組在耦合的情況下穩定,並完成二自由度的定位與追蹤控制,同時改善系統的輸出誤差。在硬體即時控制部分,應用Altera Quartus 編寫Verilog HDL觸發與接收HCTL-2016晶片的數位訊號,訊號接收後藉由SOPC Builder傳送給Nios II 系統做控制處理,Nios II 系統將訊號處理結果再由SOPC Builder將訊號傳回Altera Quartus,將FPGA傳出的訊號做D/A的處理後再傳到TRMS以控制其運動狀態。
This study applies hybrid intelligent control to an experimental propeller setup which is called the twin rotor multi-input multi-output system (TRMS) in setpoint control and trajectory tracking. The pitch angle and yawing angle are controlled in both decoupled and cross-coupled conditions such that the TRMS can move quickly and accurately to the desired attitudes. The proposed control scheme is the combination of the CMAC and the PID controller. The advantages of PID controller are simple structure, faster response, zero steady state error for setpoint control, and easy adjusting rule. The CMAC is a kind of associative memory network. The CMAC not only has faster self learning rate than normal neural network by quantities with a few adjustments of memory weight, but also has good local generalization ability. CMAC algorithm is effective for nonlinear function approximation, dynamic modeling and control system design. Another advantage of the CMAC is its fast learning process. The advantages of the hybrid CMAC-PID control are that the PID controller uses feedback control to maintain system stability and disturbance rejection and the CMAC is used to achieve feedforward control and realize the inverse dynamic model of controlled plant. In hardware real-time control, Verilog HDL is utilized to encode receiving and trigger signals from HCTL-2016 on Altera Nios II FPGA . The use of SOPC is to pass the signal in CPU to the controller. The processed signals are then transferred into voltage by a D/A converter and are sent to the TRMS to control its movement.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0M97670004
http://ntour.ntou.edu.tw/ir/handle/987654321/18429
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.html0KbHTML275View/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