Basic Search / Detailed Display

Author: 黃聖凱
Thesis Title: 應用模糊類神經法則之球桿平衡控制系統
A Ball-Beam Balance Control System Using Fuzzy-Neural Network Algorithm
Advisor: 曾煥雯
Degree: 碩士
Master
Department: 機電工程學系
Department of Mechatronic Engineering
Thesis Publication Year: 2005
Academic Year: 93
Language: 中文
Number of pages: 64
Keywords (in Chinese): 模糊推論模糊類神經法則球-桿平衡控制系統
Keywords (in English): Fuzzy Inference, Fuzzy-Neural Rule, Ball-Beam Balance Control System
Thesis Type: Academic thesis/ dissertation
Reference times: Clicks: 232Downloads: 0
Share:
School Collection Retrieve National Library Collection Retrieve Error Report
  • 摘要
    使用古典控制理論設計控制器,須先找出受控系統的數學模型。因此控制器的性能與受控系統是否能被精確的描述有密切的關係。想要實現智慧型控制,就必須精確的掌握系統特性。「學習」是達到智慧型控制的第一步,經由「學習」可以降低影響動態性能的不確定因素。
    模糊控制理論利用語意資訊,可以將人類知識和經驗轉換成控制法則,具有較佳的強健性和容錯性。類神經網路仿人腦的平行處理方式,具有學習功能,可應用於系統辨識和估測。
    結合模糊推論和類神經網路之模糊類神經控制理論,則同時包含了類神經網路不受模式限定的學習能力,並可根據模糊邏輯,以萃取方式建構知識,具有補足類神經網路“黑盒子”缺點的能力。本研究即是利用模糊類神經法則之推理、學習之特性,並搭配手動操作裝置,將無法清楚描述的控制行為,以模糊推論方式轉換成語意式的模糊規則,並結合類神經網路之學習能力,以期能建立一個使用較少規則和數學,可以吸收人類知識並具有學習功能之球-桿平衡控制系統。

    關鍵字:模糊推論、模糊類神經法則、球-桿平衡控制系統

    Abstract
    It is necessary to find the mathematic model of the plant when we design the controller by classical control theory. Hence, the controller’s control ability is related to the plant which can be described accurately or not. If we want to make up intelligent control, it is necessary to get the system’s characteristics. Learning is the first step to achieve intelligent control. From learning, it can reduce the uncertain factor which can influence the dynamic system.
    Fuzzy control theory uses linguistic information, and it can transform human being’s knowledge and experiments to control rules. It has the better robustness and fault tolerance. Artificial neural network mimics a human brain’s parallel calculation. It has learning capability and it can be applied to system identification and estimate.
    The control theory combining with fuzzy reasoning system and artificial neural network not only have neural network’s learning capability, but also can build knowledge by extracting information form fuzzy logic. Hence it makes up neural network’s drawback which are always treated like a “black box”. This study utilizes the reasoning and learning ability of Fuzzy-Neural rules, and we will use the Fuzzy inference method to transfer the control behavior which can not be expressed clearly to linguistic Fuzzy rule with manual operation device. We will combine they with Neural Networks to establish a ball-beam balance control system which could assimilate human expertise with less rule and mathematics, and learning capability.

    Keyword: Fuzzy Inference, Fuzzy-Neural Rule, Ball-Beam Balance Control System.

    總目錄 中文摘要…………………………………………………………...……….I 英文摘要……………………………………………………………...…...II 總目錄………………………………………………………………….....III 圖目錄………………………………………………………...…………..VI 表目錄…………………………………………………………………….IX 第一章 緒論…………………………………..………………...…………1 1.1 研究背景與動機………………………………….…………...………1 1.2 研究目的………………………………………….……………...……4 1.3 研究範圍與限制………………………………………….………...…4 1.4 研究方法………………………………………………….…………...5 1.5 研究步驟………………………………………………….…………...5 第二章 文獻探討…………………………………………………..……...8 2.1 模糊理論簡介…………………………………………………….…...8 2.2 模糊集合……………………………………...…………………….…9 2.2.1模糊集合之基本性質…………………………..………………10 2.2.2模糊集合之基本運算..…………………………………………12 2.3 模糊推論………………….………………………………………….14 2.3.1模糊推論方式…………………………………………..………15 2.4 模糊控制………………….………………………………………….16 2.5 類神經網路簡介……………………………………………….…….21 2.6 位置判斷-影像……………………………………………………….24 2.6.1 影像二值化……………………………………………………24 2.6.2 移動物體偵測…………………………………………………25 2.6.3 影像型態學……………………………………………………29 第三章 系統架構設計……………………………………………..…….31 3.1 系統建構………………………………………………………….….31 3.1.1 硬體設備………………………………………………………31 3.1.2 系統配備說明…………………………………………………33 3.1.3 系統軟體………………………………………………………35 3.2 系統設計………………………………………………………….….36 3.2.1系統說明……………….……………………………………….25 3.2.2 模糊類神經網路..………………………………………….….27 3.3 控制器設計……………………………………………………….….28第四章 實驗步驟與結果…………………………………………..…….41 4.1 系統測試………………………………………………………….….41 4.2 測試設計………………………………………………………….….44 4.2.1 操控者控制結果…………………………………………...….44 4.2.2 建立模糊規則…………………………………………………50 4.3 模擬結果………………………………………………………….….54 4.4 實際運轉情形…………………………………………………….….56 第五章 結論與討論……………………………………………………...59 5.1 結論…………………………………………………………………..60 5.2 討論…………………………………………………………………..60 參考文獻………………………………………………………………….62 圖目錄 圖 1-1 研究步驟流程圖……………………………………………...…..7 圖 2-1 模糊集合基本性質之示意圖…………………………………...11 圖 2-2 車速的歸屬函數圖……………………………………………...11 圖 2-3 直接推論法的演算過程………………………………………...15 圖 2-4 模糊邏輯控制器方塊圖………………………………………...16 圖 2-5 Delta Learning Rule示意圖………………………………….….22 圖 2-6 二值化影像……………………..……………………………….24 圖 2-7 差值影像(一)…………………………………………………….26 圖 2-8 差值影像(二)…………………………………………………….26 圖 2-9 移動物體檢測流程………………………………………………27 圖 2-10 移動物體檢測……………………………………………….….27 圖 2-11 3X3影像………………………………………………………...28 圖 2-12 Sobel邊緣影像………………………………………………….28 圖 3-1 CCD………………………………………………………………31 圖 3-2 影像擷取卡……………….………………………………….….31 圖 3-3 AD/DA卡…………………………………………………….….32 圖 3-4 搖桿……………………………………………………………...32 圖 3-5 馬達驅動器……………………………………………………...32 圖 3-6 直流馬達………………………………………………………...32 圖 3-7 實體架構……………………….…………………………….….33 圖3-8 滑台-桿平衡系統機構正視圖…………………………………..33 圖 3-9 系統架構示意圖…………………………………………………36 圖 3-10 滑台-桿平衡控制架構…………………………………………36 圖 3-11 模糊類神經架構……………………………………...………...38 圖 3-12 神經元示意圖…………………………………………...……...38 圖 4-1 金屬滑台…………………………………………………………41 圖4-2 搖桿位置訊號與電壓轉換關係圖…………………………...…..42 圖 4-3 搖桿控制訊號(一)……………………………………………….44 圖 4-4 電位計輸出電壓(一)…………………………………………….45 圖 4-5 目標物收斂情形(一)…………………………………………….45 圖 4-6搖桿控制訊號(二)………………………………………………..46 圖 4-7 電位計輸出電壓(二)…………………………………………….46 圖 4-8 目標物收斂情形(二)…………………………………………….47 圖 4-9搖桿控制訊號(三)………………………………………………..47 圖 4-10 電位計輸出電壓(三)…………………………………………...48 圖 4-11目標物收斂情形(三)…………………………………………….48 圖 4-12搖桿控制訊號(四)………………………..……………………..49 圖 4-13 電位計輸出電壓(四)……………………………………...……49 圖 4-14 目標物收斂情形(四)…………………………………………...50 圖 4-15 系統操控示意圖…………………………………………….….50 圖 4-16 輸入參數與輸出結果之歸屬函數...…….……………………52 圖 4-17 系統模糊規則...………………………………………………...54 圖 4-18 電位計輸出電壓……………………...………………………...54 圖 4-19 目標物收斂情形…………………………………………….….55 圖 4-20 電位計輸出電壓…………………………………………….….55 圖 4-21 目標物收斂情形…………………………………………….….56 圖 4-22 模糊類神經學習結果(一)……………………………..……….56 圖 4-23 模糊類神經學習結果(二)……………………………………...57 圖 4-24 系統運轉測試(由左到中)…………………….………………..58 圖 4-25系統運轉測試(由右到中)…..…………………..………………59 表目錄 表 2-1 常用之三角範數(norm)….……………………………………12 表 2-2 常用之反三角範數(norm).……………………………………13 表 2-3 廣義的肯定前件論式…………………………………………14 表 2-4 廣義的否定後件論式…………………………………………14 表 4-1 12 bits解析度之DA電壓與數值轉換表………………………42 表 4-2 12 bits解析度之AD電壓與數值轉換表……………………....43 表 4-3 電位計電壓輸出值與角度對應關係……………………….…44

    參考文獻
    英文部分
    [1] C.C. Lee, ”Fuzzy logic in control systems: Fuzzy logic control - Part I, II, ” IEEE Trans. Syst., Man, Cybern., vol. 20, pp. 404-435, Mar. 1990.
    [2] J. R. Layne, K. M. Passino, and S. Yurkovich, ”Fuzzy learning control for antiskid braking systems,” IEEE Trans. Contr. Syst. Technol., vol. 1, pp122-129, June 1993.
    [3] C.L. Huang and C.Y. Hsieh, “A Neuro-Adaptive Variable Structure Control for Partially Unknown Nonlinear Dynamic System and Its Application.” IEEE Trans. Contr. Syst. Technol., vol. 10, no2, pp263-271, Mar. 2002.
    [4] T. Yamakawa, “A Fuzzy Inference Engine in Nonlinear Analog Mode and Its Application to a Fuzzy Logic Control,” IEEE Transactions on Neural Networks, vol. 4, pp496-522,May 1993.
    [5] J. Bezdek, “Fuzzy Models - what are they, and why?,” IEEE Trans. on Fuzzy Systems, vol. 1, Feb. 1993.
    [6] B. Kosko and S. Isaku, “Fuzzy Logic,” Scientific American, July 1993.
    [7] P. J. Antsaklis and K. M. Passino, eds., An Introduction To Intelligent and Autonomous Control, ch. Fuzzy and Neural Control, pp. 213-236, Norwell Massachusetts: Kluwer Academic Publishers, 1993.
    [8] B.Kosko,Neural Networks and Fuzzy Systems: A Dynamical Approach to Machine Intelligence. Englewood Cliffs, NJ: Prentice Hall, 1991.
    [9] S. I. Gallant, Neural Networks Learning and Expect Systems. Cambridge, Massachusetts: A Bradford Book, The MIT Press, 1993.
    [10] B. Shahian and M Hassul, Control System Design Using Matlab, ch. Ball-on-Beam Balancer, pp. 465-476. Englewood Cliffs, NJ: Prentice Hall, 1994.
    [11] J. A. Franklin and H. Benbrahim, “Ball Balancer,” IEEE Control System, pp. 21-24, Feb. 1994.
    [12] C.M. Higgins and R. M. Goodman, “Fuzzy Rule-Based Networks for Control,” IEEE Trans. On Fuzzy Systems, vol. 2,pp82-88, Feb 1994.
    [13] B. Kosko and S. Isaku, “Fuzzy Logic,” Scientific American, July 1993.
    [14] J. Bezdek, “Fuzzy Models - what are they, and why?,” IEEE Trans. On Fuzzy System, vol. 1, Feb 1993.
    [15] K.C. Ng and M. M. Trivedi, “Fuzzy logic controller and real-time implementation of a ball balancing beam,” in Applications of Fuzzy Logic Technology II, (Orlandor, FL), Apr 1995.
    [16] C.-I. Kao Y.-H. Kuo and J.-J. Chen, “A Fuzzy Neural Network Model and Its Hardware implementation,” IEEE Trans. On Fuzzy Systems, Vol. 1, pp.171-183, Aug 1993.
    [17] H. K. Kwan and Y. Cai, “A Fuzzy Neural Network and its Application to Pattern Recognition,” IEEE Trans. On Fuzzy Systems, Vol. 2, pp.185-193, Aug 1994.
    [18] C.-L. Chen and W.-C. Chen, “Fuzzy Controller Design by Using Neural Network Techniques,” IEEE Trans. On Fuzzy Systems, Vol. 2, pp.235-244, Aug 1994.
    [19] K. Hirota and W. Pedrycz, “OR/AND Neuraon in Modeling Fuzzy Set Connectives,” IEEE Trans. On Fuzzy Systems, Vol. 2, pp.151-161, May 1994.
    [20] E. H. Mamdani, “Applications of Fuzzy Algorithms for Simple Dynamic Plant,” Proc. IEEE, Vol.121, No.12, pp.1585-1588, 1974.
    [21] E. H. Mamdani and S.Assilian, “An Experiment in Linguistic Sythesis with a Fuzzy Logic Controller,” Int. Journal of Man Machine Studies, Vol.7, No.1, pp.1-13, 1975.
    [22] W. Z. Qiao and M. Mizumoto, “PID Type Fuzzy Controllers and Parameters Adaptive Method,” Fuzzy Sets and Systems, Vol.78, pp.23-35,1996.
    [23] F. L. Lewis and K. Liu, “Towards a Paradigm for Fuzzy Logic Control,” Automatica, Vol.32, No.2, pp.167-181, 1996.
    [24] C. C. Lee, “Fuzzy Logic in Control Systems : Fuzzy Logic Lontroller – Part I, Part II”, IEEE Trans. on Systems, Man, and Cybernetics, Vol.20 No.2, pp.404-433, 1990.
    [25] H. Ishibuchi and H. Tanaka, “Neural Networks That Learn from Fuzzy If-Then Rules”,IEEE Trans. on Fuzzy Systems, Vol. 1, pp.85-87, May 1993.
    [26] J. X. R.M.H. Cheng and S. LeQuoc, “Neuromorphic controller for AGV steering,” in Proceedings of IEEE Int. Conf. on Robotics and Automation, (Nice, France), Vol. 3, pp.2057-2062, May 1992.
    [27] K. C. Ng and M. M. Trivedi, ”A Neurao-Fuzzy Controller for Mobile Robot Navigation and Multirobot Convoying”, IEEE Trans. On System, Man, and Cybernetics, Vol.28, No. 6, pp.829-840ecember 1998.
    [28] H. Ishibuchi and H. Tanaka, ”Neural Networks That Learn from Fuzzy IF-Then Rules”, IEEE Trans. On Fuzzy Systems, Vol. 1, pp.85-87, May 1993.
    [29] J. X. R.M.H. Cheng and S. LeQuoc, “Neuromorphic controller for AGV steering,” in Proceedings of IEEE Int. Conf. On Robotics and Automation, Vol. 3, pp.2057-2062, May 1992.
    [30] Gabriel Omar Alvarez Zapata, Roberto Kawakami Harrop Galvao, and Takashi Yoneyama,”Extracting Fuzzy Control Rules from Experimental Human Operator Data”,IEEE Trans. On Systems, Man, and Cybernetics, Vol.29, NO.3, pp.398-406. June 1999.
    [31] Li-Xin Wang, and Jerry M. Mendel,“Generating Fuzzy Rule by Learning from Examples”, IEEE Trans. On Systems, Man, and Cybernetics, Vol.22, NO.6,November/December, pp. 1414-1427, 1992.
    中文部分
    [32] 孫宗瀛、楊英魁,“Fuzzy 控制:理論、實作與應用”,全華科技圖書股份有限公司,1997。
    [33] 劉德順,“PID型模糊邏輯控制器之設計與解析”,國立清華大學動力機械工程學系碩士班論文,1998
    [34] 王進德、蕭大全,“類神經網路與模糊控制理論入門”,全華科技圖書股份有限公司,1994。
    [35] 王文俊,“認識Fuzzy-第二版”,全華科技圖書股份有限公司,2001。
    [36] 梁家銘,”應用模糊滑動控制追蹤法於視覺監控之研究”,國立台灣科技大學自動化及控制學程碩士學位論文,2003。

    無法下載圖示 This full text is not authorized to be published.
    QR CODE