簡易檢索 / 詳目顯示

研究生: 曹建和
Chien Ho Tsao
論文名稱: 具殘差修正之模糊小腦模型控制器設計及其應用研究
A Study of Improving the accuracy of Fuzzy CMAC using Residual Theory Design and Its Application
指導教授: 洪欽銘
Shi, Chun-Xie
許全守
Hau, Chuan-Shou
學位類別: 碩士
Master
系所名稱: 工業教育學系
Department of Industrial Education
論文出版年: 2003
畢業學年度: 91
語文別: 中文
中文關鍵詞: PID控制器模糊控制小腦模型控制器殘差修正之模糊小腦模型控制器線性壓電陶瓷馬達
英文關鍵詞: PID controller, Fuzzy control, CMAC, RFCMAC, LPCM
論文種類: 學術論文
相關次數: 點閱:251下載:13
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 傳統工業程序控制中,PID控制器使用及應用最為普遍。雖然PID控制法則簡單,但它們個別的增益參數無法隨著受控系統變化而自動調整。為了改善此一缺點,於是有著名的Ziegler-Nichols參數設定方法、模糊邏輯參數設定方法及利用生物本質為理論基礎的人工智慧控制理論等,其控制方法特色是模擬人的智能行為,不需要精確的數學模型,能夠解決許多傳統控制技術中複雜的、不確定性的、非線性的自動化控制問題。
    傳統CMAC感應場中使用的是二值方盒型基礎函數,它無法儲存網路輸出入間微分之訊息,因而限制了系統參數的調整,再者,由於CMAC的近似性質及計算機造成之捨入誤差等,也因此限制了實際應用時控制精度的提昇。
    因此,本論文提出將模糊歸屬函數植入傳統CMAC感應場中及新的索引指標連結規則-全連結定址架構,並結合數值分析中殘差法理論,稱為殘差修正之模糊小腦模型控制器(RFCMAC),除保有傳統小腦模型控制器之優點外,另具備輸出與系統參數之偏微分關係而得以進行參數之動態調整及控制精度的提升。
    最後並將本研究所提之架構應用於線性壓電陶瓷馬達位置追隨(Tracking)控制中,藉以驗證其在實際控制系統中控制精度提昇的效能。
    從實驗結果得知,無論參考模式是步階或是正弦波輸入,本研究所提具殘差修正之模糊小腦模型控制器架構在位置追隨響應上均較傳統之比例微分控制器架構更能貼近追隨於參考模式,並成功地實現本研究所提架構在線性壓電陶瓷馬達位置追隨響應上控制精度之提升。

    For traditional industry process control, the PID controller is the most commonly used. Although the rule of PID control is simple, the main defect of PID control is that the individual gain parameters cannot be automatically adjusted when the controlled system changes. To improve this, the Ziegler-Nichols parameter setting method, the Fuzzy logic parameter setting method, and the Artificial Intelligence control theory are developed hence. The features of these methods are to imitate artificial intelligence, which can solve the problems of complexity, indetermination and nonlinear of traditional control technique, without precise mathematics model needed.
    The receptive field function of conventional CMAC uses the basic function of binary box, which cannot store the differential information between input and output. Also, due to the approximate property of CMAC and computer round-off error, it limits the adjustment of the system parameter and the accuracy of practical application.
    So, this paper presents a new index rule, which fully connects the addressing scheme and receptive field function, called RFCMAC. It not only can keep the advantages of CMAC, but also can store the differential information between input and output, which is able to auto-adjust the system parameter and improve the accuracy.
    Finally, to demonstrate its practical control system capability and performance of improving the accuracy, I apply the proposed structure in the position of tracking of Linear Piezoelectric Ceramic Motor (LPCM).
    From the experimental results, any one input of the reference model of step function or sine wave will do, the position tracking response of moving table can be closely follow the reference model compares RFCMAC with PI structure and has been successfully implemented to control the position tracking of LPCM to achieve improvement the accuracy.

    中文摘要…………………………………………………………………...I 英文摘要…………………………………………………………………..II 總目錄………………………………………………………………….…III 圖目錄………………………………………………………………….VII 表目錄…………………………………………………………………...X 第一章 緒論……………………………………………………………….1 1.1研究背景與動機…………………………………………………….1 1.2研究目的…………………………………………………………….3 1.3研究範圍與限制…………………………………………………….3 1.4研究方法…………………………………………………………….4 1.5研究步驟…………………………………………………………….4 第二章 小腦模型控制器理論…………………………………………….7 2.1 小腦模型控制器之相關研究…………………………………….7 2.1.1小腦模型控制器之優缺點………..……………………….7 2.1.2小腦模型控制器之記憶體的改善.….….………………….8 2.1.3小腦模型控制器之精度的改善..……….….………..…….9 2.1.4小腦模型控制器的應用……………………...……………9 2.1.5 具微分特性之小腦模型控制器...…………..……………..10 2.2 小腦模型控制器之基本架構...………..….……………………12 2.3小腦模型控制器之記憶體分割方式.…………………………13 2.3.1一維小腦模型控制器之記憶體分割方式.……..….………13 2.3.2二維小腦模型控制器之記憶體分割方式.……..….………15 2.4 小腦模型控制器數學表示法………………………………….16 2.5 小腦模型控制器學習演算法………………………………….17 第三章 模糊理論………….……………………………….…………..19 3.1模糊理論之歷史發展…………………….………………….19 3.2 模糊集合……………………………….………….….………20 3.2.1 歸屬函數之表示法……..……………..………….……….20 3.2.2模糊集合之表示法….……..……..………………………22 3.3模糊集合之運算……….……..…………….…….…………22 3.4 模糊控制…………………………………..…..…….………24 3.4.1 輸入量模糊化……………………………………..………25 3.4.2 知識庫…………………………...………..……....…..…26 3.4.3 模糊推論引擎…………………………...….……....…..…26 3.4.4 解模糊化………………………….....….……..…....…..…26 3.5 模糊系統學習與參數調整….………………..…..…….………27 3.5.1 最陡梯度下降法…………………………………..………27 3.5.2 模糊系統參數之調整…………………………....………30 第四章 具殘差修正之模糊小腦模型控制器設計……………………...34 4.1導論………………….……………….………….……..……34 4.2 FCMAC之基本架構…………………..…..……..…………36 4.3 FCMAC之定址模式………….………………..……………38 4.4 FCMAC輸出及學習演算法…….………..…..……………40 4.4.1 模糊推論及輸出產生………………………………….…..43 4.4.2 FCMAC學習演算法….………………..…………………43 4.4.3 FCMAC之使用程序……..……………………….………44 4.5 殘差法理論…….…….….….…..………………..……………45 4.6 具殘差修正之FCMAC…….…..………………..……………48 4.7 CMAC與FCMAC及RFCMAC學習性能比較…..……………49 4.8 FCMAC之微分特性探討………..….……..……………55 4.8.1 FCMAC輸出/輸入間微分特性探討…..…………….…..56 4.8.2鐘形感應場函數之特性探討….………..…………………57 4.8.3 DCMAC與FCMAC微分特性之比較…..…………………59 4.9 RFCMAC控制系統之設計……….……….……..……………62 4.9.1 PIRFCMAC控制系統架構…….….…..…………….…..62 4.9.2比例積分控制器設計….…….…..……….…..………63 4.9.3 RFCMAC控制器設計….…….….…….…..………63 4.9.3.1控制器參數設定….…….….…….…..………63 4.9.3.2控制器之回想演算法….…….….…..………64 4.9.3.3控制器之學習演算法….…….….…..………65 第五章 線性壓電陶瓷馬達控制系統實驗……….………………...66 5.1系統硬體規劃………………………….……….……..……66 5.2 系統元件功能簡介………………………..…..……………68 5.2.1 編碼器…….….……..….……..…...…………….…..68 5.2.2 HR4超音波馬達….…….…..…...…………….…..69 5.2.3 AB1驅動器….……..……………..…...…………….…..70 5.2.4 AD/DA卡….……..….……..……..…...…………….…..70 5.3 線性壓電陶瓷馬達………………………..…..……………71 5.3.1 超音波馬達之發展歷史….……..…...…………….…..72 5.3.2 壓電效應…….….……..….……..…...…………….…..73 5.3.3線性壓電陶瓷馬達之特點.……..…...…………….…..73 5.3.4相關線性壓電陶瓷馬達控制系統之研究..……….…..75 5.4 控制實驗之設計………….……………..…..……………75 5.5 實驗結果………….……………………..…..……………78 第六章 研究結論與建議……………………….…..………..……103 6.1研究結論………………………….……….……..…..…103 6.2研究建議………………………….……….……….……103 參考文獻……………………………………………….…………105 作者簡介……………………………………………….…………110

    英文部分
    [1] Ziegler, Nichols,“Optimum settings for automatic controllers”, Trans. ASME, 64, 1942, pp. 759-768.
    [2] L.A. Zadeh, “Fuzzy sets” , Inf. Control 8, 1965, pp.338-353.
    [3] F.H. Glanz; W.T. Miller and L.G. Kraft, “ An overview of the CMAC neural network”, IEEE Conf., Neural Networks for Ocean Engineering, pp. 301 -308, 1991.
    [4] M. Brown and C.J.Harris, “The modelling abilities of the binary CMAC” , IEEE Conf. Neural Networks, vol. 3, 1994, pp. 1335 -1339.
    [5] P.E. An; S. Aslam-Mir; M. Brown; C.J.Harris and D. McLean, “Theoretical aspects of the CMAC and its application to high-dimensional aerospace modelling problems”, IEE Conf. Control, vol. 2, 1994, pp. 1466 -1471.
    [6] Zi-Qin Wang; J.L Schiano and M. Ginsberg, “Hash-coding in CMAC neural networks”, IEEE Proc. Neural Networks, vol. 3, 1996, pp. 1698 -1703.
    [7] Luo Zhong; Zhao Zhongming and Zhu Chongguang, “The unfavorable effects of hash coding on CMAC convergence and compensatory measure”, IEEE Proc. ICIPS, vol. 1, 1997, pp.419-422.
    [8] Jianjuen Hu; J. Pratt and G. Pratt, “Stable adaptive control of a bipedal walking; robot with CMAC neural networks”, IEEE Proc. Robotics and Automation, vol. 2, 1999, pp. 1050 -1056.(2-09)
    [9] J. S. Albus, “Data Storage in the Cerebellar Model Articulation Controller (CMAC)1”, Trans. ASME. Sept, 1975, pp.228-233.(1-01)
    [10] P.E. An; S. Aslam-Mir; M. Brown; C.J.Harris and D. McLean, “Theoretical aspects of the CMAC and its application to high-dimensional aerospace modelling problems”, IEE Conf. Control, vol. 2, 1994, pp. 1466 -1471.
    [11] Chun-Shin Lin and Chien-Kuo Li, “A low-dimensional-CMAC-base neural network”, IEEE Proc. Systems, Man and Cybernetics, vol. 2, 1996, pp.1297-1302.
    [12] A. Menozzi and M.-Y Chow, “On the training of a multi-resolution CMAC neural network”, IEEE Proc. ISIE, vol. 3, 1997, pp.1201-1205.(1-07)
    [13] C. S. Lin and C. K. Li, “A Sum-of-Product Neural Network (SOPNN),” Neurocomputing, Vol.30, 2000, pp.273-291.
    [14] King-Lung Huang; Shu-Cheng Hsieh and Hsin-Chia Fu, “Cascade-CMAC neural network applications on the color scanner to printer calibration”, IEEE Conf. Neural Networks, vol. 1, 1997, pp. 10 -15.
    [15] F. Gonzalez-Serrano, A. Figueiras-Vidal and A. Artes-Rodriguez, “Generalizing CMAC Architecture and Training”, IEEE Trans. Neural Networks, Vol.9, No.6, 1998, pp.1509-1514.
    [16] J. Pallotta and L.G. Kraft, “Two dimensional function learning using CMAC neural network with optimized weight smoothing”, Proc., American Control Conference, vol. 1, 1999, pp. 373 -377.
    [17] L.G. Kraft and J. Pallotta, “Vibration control using CMAC neural networks with optimized weight smoothing”, Proc., American Control Conference, vol. 2, 1999, pp. 1181 -1185.(2-08)
    [18] J. S. Albus, “A New Approach to Manipulator Control: The Cerebellar model articulation controller (CMAC)”, J. Dynamic Syst., Meas., Contr., Trans. ASME, Series G, Vol.97, No.3, 1975, pp.220-227.
    [19] L.G. Kraft and D.P. Campagna, “Comparison of Convergence Properties of CMAC neural network and Traditional Adaptive Controllers”, IEEE Proc. Decision and Control, vol.2, 1989, pp. 1744 -1745.
    [20] L.G. Kraft and D.P. Campagna, “Comparison of CMAC architectures for neural network based control”, IEEE Conf. Decision and Control, vol.6, 1990 pp. 3267 -3269.
    [21] W. Thomas Miller, Filson H. Glanz and L. Gordon Kraft, “CMAC: An Associative Neural Network Alternative to Backpropagation”, Proceeding of the IEEE, Vol.78, No.10, 1990, pp.1561-1567.
    [22] W. T. Miller, “Real-Time Neural Network Control of A Biped Walking Robot” , IEEE Control Systems Magazine, Vol.141, 1994, pp.41-48.
    [23] H. Shiraishi; S.L. Ipri and; D.-I.D. Cho, “CMAC neural network controller for fuel-injection systems”, IEEE Trans. Control Systems Technology, vol. 3,No. 1,1995, pp. 32 -38.
    [24] Y. Iiguni, “Hierarchical Image Coding via Cerebellar Model Arithmetic Computers,” IEEE Trans. Image Processing, 1996, Vol.5, No.10.
    [25] J. S. Ker, Y. H. Kuo, R. C. Wen and B. D. Liu, “Hardware Implementation of CMAC Neural Network with Reduced Storage Requirement”, IEEE Trans. Neural Network, Vol.8, No.6, 1997, pp.1545-1556.
    [26] S.H. Lane; D.A. Handelman and J.J. Gelfand, “Theory and development of higher-order CMAC neural networks”, IEEE Control Systems Magazine, vol. 12, 1992 , pp. 23 -30.
    [27] Ching-Tsan Chiang and Chun-Shin Lin, “Integration of CMAC and radial basis function techniques”, IEEE Conf. Systems, Man and Cybernetics, vol. 4, 1995, pp. 3263 -3268. (1-23)
    [28] C. C. Jou, “A Fuzzy Cerebellar Model Articulation Controller”, IEEE International Conference on Fuzzy Systems, San Diego, California, March 8-12, 1992, pp.1171-1178.
    [29] H. Xu; C. M. Kwan; L. Haynes and J. D. Pryor, “Real-time adaptive on-line traffic incident detection”, Fuzzy Sets and Systems 93, 1998, pp.173-183.
    [30] D. Xiaolong; Z. Xudong; A. Meio; T. Fukao and N. Adachi, “Optimal Design and Optimal Algorithm of Fuzzy CMAC”, Fuzzy Sets and Systems 93, 1998, pp.173-183.
    [31] K. S. Hwang and C. S. Lin, “A Self-Organizing Fuzzy CMAC For Sliding Mode Control”, IEEE Workshop on Variable Structure Systems, pp.133-138, 1996.
    [32] J. S. Ker; C. C. Hsu; Y. H. Kuo and B. D. Liu, “A fuzzy CMAC model for color reproduction”, Fuzzy Sets and Systems 91, 1997, pp.53-68.
    [33] Chao. He; Yuhe. Zhang and Max. Meng, “Backlash Compensation by Neural-network Online Learning”, Proceedings of 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation, July 29-Auguust 1, 2001, pp.161-165.
    [34] Hung-Ren. Lai and C.C. Wong, “A Fuzzy CMAC Structure and Learning Method for Function Approximation”, IEEE International Fuzzy Systems Conference, 2001, pp.436-439.
    [35] C. Lin; Roger. Xu; C. Kwan and Leonard. Haynes, “Submarine pitch and depth control using FCMAC neural network”, Proceedings of the American Control Conference, Philadelphia, Pennsylvania June, 1998, pp.379-383.
    [36] S. H. Lane; D. A. Handelman and J. J. Gelfand, “Theory and Development of Higher-Order CMAC Neural Networks”, IEEE Contr. Syst., vol. 12, 1992, pp. 23-30.
    [37] C. T. Chiang and C. S. Lin, “Integration of CMAC and Radial Basis Function Techniques”, IEEE International Conference on Intelligent Systems for the 21st, Vol. 4, 1995, pp.3263-3268.
    [38] H. L. Stephen; A. H. David and J. G. Jack, “Theory and development of high-order CMAC neural networks”, IEEE Control Systems 12(2), 1992, pp.23-30.
    [39] P. J. Hartley, “Tensor product approximations to data defined on rectangular meshes in N-space”, Comput. J.19, 1974, pp.348-351.
    [40] E. H. Mamdani and S. Assilian “An experiment in linguistic synthesis with a fuzzy logic controller”, Internat. J. Man-Machine Stud. 7, 1975, pp.1-13.
    [41] W. T. Miller; R. H. Hewes; F. H. Glanz, and L. G. Kraft, “Real-time dynamic control of an industrial manipulator using a neural-network-based learning controller”, IEEE Trans. Robot Automation, vol. 6, no. 1, 1990, pp.1-9.
    [42] F. C. Chen and C. H. Chang, “Practical Stability Issues in CMAC Neural Network Control Systems”, IEEE Trans. Control Syst. Technol., Vol.4, No.1, 1996, pp.86-91.
    [43] C. C. Lin and F. C. Chen, “Improved CMAC Neural Network Control Scheme”, Electronics Letters, Vol.35, No.2, pp.157-158, 1999.
    [44] Kim, H. and Lin, C. S. , “Use of adaptive resolution for better CMAC learning Neural Networks”, IJCNN, International Joint Conference on Vol. 1 , pp. 517 - 522, 1992.
    [45] Hahn-Ming Lee; Chih-Ming Chen and Yung-Feng Lu, “A Self-organizing HCMAC Neural Network Classifier”, Neural Networks, 2001. Proceedings , IJCNN’01.International joint Conference on ,Vol.3, pp. 1960-1965, 2001.
    [46] WAI,R.J; LIN, F.J.; DUAN,R.Y.; HSIEH,K.Y., and LEE,J.D.,“Robust fuzzy neural network control for linear ceramic motor drive via backstepping design technique”, IEEE Trans. Fuzzy Syst., 2002, 10,(1),pp.102-112.
    [47] R. J. Wai; C. M. Lin, and Y. F. Peng, “Intelligent hybrid control for linear piezoelectric ceramic motor using CMAC network”, R.O.C. Symposium on Electrical Power Engineering, pp. 430-434, December 2002.
    [48] C.T. CHAO and C.C. TENG..,“ Implementation of fuzzy inference systems using a normalized fuzzy neural network”, Fuzzy Sets and Syst., 1995, Vol.75,pp.17-31.
    [49] F.J. LIN; R.J. WAI and C.C. LEE,“ Fuzzy neural network position controller for ultrasonic motor drive using push-pull DC-DC converter”, IEE Proceeding Control Theory Application., 1999, Vol.146,no.1,pp.99-107.
    [50] F.J. LIN; R.J. WAI and H.H. LIN,“ An adaptive fuzzy-neural-network controller for ultrasonic motor drive using the LLCC resonant technique”, IEEE Trans. On Ultrasonic Ferroelectrics, and Frequency Control., 1999, Vol.46,no.3,pp.715-727.
    [51] Y.C. CHEN and C.C. TENG,“ A model reference control structure using a fuzzy neural network”, 1995, Vol.73,pp.291-312.
    [52] J. Zhang and A.J. MORRIS,“ fuzzy neural networks for nonlinear systems modeling ”, IEE Proceeding Control Theory Application.,1995, Vol.42,no.6.pp.551-556.
    中文部分
    [53] 趙鎮宇,徐用懋,” 模糊理論和神經網路的基礎與應用”,北京清華大學出版社,廣西科學技術出版社,1992。
    [54] 張乃堯,閻平凡,”神經網路與模糊控制”,北京清華大學出版社,1996。
    [55] 林法正,魏榮宗,段柔勇,”超音波馬達之驅動與智慧型控制”,滄海書局,1999。
    [56] 許溢适,”壓電/電歪致動器”,文笙書局,1995。
    [57] 莊華益,許溢适,”超音波電動機基礎”,文笙書局,1995
    [58] 黃昭諺,”間時滑動模式之可微分小腦模型控制器設計”,國立台灣師範大學工業教育研究所碩士論文,2001。
    [59] 張冠文,” 模糊推論積分型滑動模式之小腦模型控制器設計”,國立台灣師範大學工業教育研究所碩士論文,2002。

    QR CODE