應用動態結構模糊神經網路於機械臂適應控制研究 謝昇峰、陳昭雄
E-mail: [email protected]
摘 要
機械手臂為高度非線性系統，並且需要承受系統參數的變動和外力的干擾，因此，本文將提出一動態結構模糊類神經網 路(Dynamic Structure Neural-Fuzzy Networks)控制系統於機械臂系統之軌跡跟隨。首先使用類神經模糊網路系統學習機械臂 之未知動態，並以此類神經模糊網路系統設計出強健的控制器，此類神經模糊網路可以線上調整網路的參數與結構以得到 最佳的近似效果。再依據里阿普諾夫(Lyapunov)的穩定法則，我們發展一混合式控制器(hybrid controller)，其設計一個調節 函數來切換自適應性控制器與順滑控制器來確保整個控制系統的穩定及收斂。硬體方面，以個人電腦為基礎，並結合研華 的PCI-1784 Encoder卡和PCI-1720U D/A卡，並應用Borland C++ Builder 6.0來撰寫系統的控制軟體。最後以一實際的兩軸 機械臂，透過各種實驗，來驗證本文所提方法的有效性。
關鍵詞 : 類神經模糊網路、機械臂控制、非線性系統、適應性控制 目錄
中文摘要...iv 英文摘要...v 致謝...vi 目 錄...vii 圖目錄...ix 表目錄...xii 第一章 緒
論...1 1.1 研究動機...1 1.2 研究目的...2 1.3 文獻回顧...3 1.4 論文 架構...5 第二章 系統架構介紹...6 2.1兩軸機械臂系統硬體架構...6 2.2兩軸機械手臂系統 數學模型...14 2.2.1拉格朗日運動方程式...16 2.2.2兩軸機械手臂數學模型...16 第三章 軌跡跟隨與控制器設 計...22 3.1機械手臂控制問題描述...22 3.2類神經模糊網路系統...25 3.3自適應性類神經模糊網路 控制器...39 3.4動態結構類神經模糊網路控制系統...39 第四章 控制系統模擬與實驗...51 4.1兩軸機械臂模 擬系統...51 4.2控制器介紹...53 4.3模擬結果...55 4.3.1 CASE1的模擬結果...55 4.3.2 CASE2的模擬結果...65 4.4實驗結果...75 4.4.1 CASE1的實驗結果...75 4.4.2 CASE2的實驗結果...84 第五章 結論...93 參考文獻...94
參考文獻
[1] J. P. Hwang and E. Kim, “Robust tracking control of an electrically driven robot: Adaptive fuzzy logic approach,” IEEE Trans. Fuzzy Syst., vol. 14,no. 2, pp. 232–247, Apr. 2006.
[2] A. Rubaai, A. R. Ofoli, and D. Cobbinah, “DSP-based real-time implementationof a hybrid H∞ adaptive fuzzy tracking controller for servo motor drives,” IEEE Trans. Ind. Appl., vol. 43, no. 2, pp. 476–484,Mar./Apr. 2007.
[3] W. Gueaieb, F. Karray, and S. Al-Sharhan, “A robust hybrid intelligent position/force control scheme for cooperative manipulators,”
IEEE/ASME Trans. Mechatronics, vol. 12, no. 2, pp. 109–125, Apr. 2007.
[4]B.S Chen., H.J Uang., and C.S Tseng., Robust tracking enhancement of robot systems including motor dynamics: a fuzzy-based dynamic game approach. IEEE Trans. Fuzzy systems, November 1998, 6(4), 538-552.
[5]J.P Hwang. and E. Kim, Robust tracking control of an electrically driven robot: adaptive fuzzy logic approach. IEEE Trans. Fuzzy Systems, April 2006, 14(2), 232-247.
[6]R.J. Wai and P.C. Chen, Robust neural-fuzzy-network control for robot manipulator including actuator dynamics. IEEE Trans. Ind. Electron. , August 2006, 53(4), 1328-1349.
[7]S.J. Lee and C.L. Hou, A neural-fuzzy system for congestion control in ATM networks. IEEE Trans. Syst. Man, Cybern., February 2000, 30(1), 2-9.
[8] F.B. Duh and C.T. Lin, Tracking a maneuvering target using neural fuzzy network. IEEE Trans. Syst. Man, Cybern., February 2004, 34(1), 16-33.
[9] S. J. Lee and C. L. Hou, “A neural-fuzzy system for congestion control in ATM networks,” IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 30,no. 1, pp. 2–9, Feb. 2000.
[10] F. B. Duh and C. T. Lin, “Tracking a maneuvering target using neural fuzzy network,” IEEE Trans. Syst., Man, Cybern. B, Cybern., vol.
34,no. 1, pp. 16–33, Feb. 2004.
[11]aF.C.Sun,H.X.Li,andH.P.Liu,“Neuro-fuzzyadynamic-inversion-based adaptive control for robotic manipulators-discrete time case,” IEEE Trans.Ind. Electron., vol. 54, no. 3, pp. 1342–1351, Jun. 2007 [12] Y.G. Leu, Wang W.Y., and Lee T.T., Robust adaptive fuzzy-neural controllers for uncertain nonlinear systems. IEEE Trans. Robot. Autom., Oct. 1999, 15(5), 805-817.
[13] Z. Qu and D.M. Dawson, Robust tracking control of robot manipulators, 1996 (Piscataway, NJ:IEEE) [14] T. J.Tarn, A. K.Bejcay, X.Yun, and Z. Li, Effect of motor dynamics on nonlinear feedback robot arm control. IEEE Trans. Robot. Automat., 1991, 7, 114–122.
[15] S. Fabri, and V. Kadirkananathan, Dynamic structure neural networks for stable adaptive control of nonlinear systems. IEEE Trans. Neural Networks, 1996, 7 (5), 1151-1167.
[16] L.X. Wang, Adaptive fuzzy systems and control: Design and stability analysis, 1994 (Englewood Cliffs, NJ: Prentice-Hall).
[17] Y. Gao and M.J. Er, Online adaptive fuzzy neural identification and control of a class of MIMO nonlinear systems. IEEE Trans. Fuzzy Systems, 2003, 11 (4), 462-477 [18] H. Han C. Y. Su,and Y. stepanenko Adaptive control of a class of nonlinear systems with nonlinearly parameterized fuzzy approximators. IEEE Trans. Fuzzy systems,2001,9(2),315-323.
[19] S.D. Wang and C.K. Lin, Adaptive tuning of fuzzy controller for robots. Fuzzy Sets and Systems, 2000, 110( 3), 351–363.
[20] S. Sastry and M. Bodson, Adaptive control: stability, convergence and robustness, 1989 ( Englewood Cliffs, NJ: Prentice-Hall).
[21] R. J. Wai and P. C. Chen, “Robust neural-fuzzy-network control for robot manipulator including actuator dynamics,” IEEE Trans. Ind.
Electron.,vol. 53, no. 4, pp. 1328–1349, Aug. 2006 [22] C. S. Chen and W. L. Chen, “Robust model reference adaptive control of nonlinear systems using fuzzy systems,” Int. J. Syst. Sci., vol. 27, no. 12,pp. 1435–1442, 1996.
[23] S. Vasilic and M. Kezunovic, “Fuzzy ART neural network algorithm for classifying the power system faults,” IEEE Trans. Power Del., vol.
20,no. 2, pp. 1306–1314, Apr. 2005.
[24] V. Gazi and K. M. Passino, “Direct adaptive control using dynamic structure fuzzy systems,” in Proc. Amer. Control Conf., Chicago, IL, Jun. 2000,pp. 1954–1958.
[25] C. J. Chien, “A sampled- data iterative learning control using fuzzy network design,” Int. J. Control, vol. 73, no. 10, pp. 902–913, Jul.
2000.
[26] 謝冠雲，多軸機械臂之力量控制及定位追蹤，私立中原大學電機工程學系碩士學位論文，2002。
[27] 秋士豪，機械之拋射路徑規劃與設置，國立成功大學航太工程學系碩士學位論文，2004。
[28] 陳芳雄，機械手臂之非線性遞回部接控制設計，暨南國際大學電機工程學系碩士學位論文，2004。
[29] 沈奇聰，平面之雙機械臂滑順控制法，國立中興大學機械工程學系碩士學位論文，2003。
