• 沒有找到結果。

強健類神經控制理論在機械背軌跡跟隨之應用 黃睿祥、陳昭雄

N/A
N/A
Protected

Academic year: 2022

Share "強健類神經控制理論在機械背軌跡跟隨之應用 黃睿祥、陳昭雄"

Copied!
2
0
0

加載中.... (立即查看全文)

全文

(1)

強健類神經控制理論在機械背軌跡跟隨之應用 黃睿祥、陳昭雄

E-mail: 9419866@mail.dyu.edu.tw

摘 要

兩軸機械手臂是一個多輸入多輸出的非線性系統,常被用來驗證控制理論的成果。本論文推導出一個新的強健類神經網路 控制器於未知非線性動態機械臂系統之軌跡跟隨問題,首先利用類神經網路系統模型化此機械臂未知之非線性動態,再利 用此類神經網路模型設計出控制器,以完成機械臂之軌跡跟隨。本論文應用強健適應控制技術,推導出一適應控制法則調 整類神經網路系統之所有參數,包括神經元之輸出權重值(Output weights)、 中心值(Centers)和寬度值(Widths),

因此降低類神經系統之近似誤差。透過里阿普諾夫(Lyapunov)穩定法則,來證明整體控制系統能夠穩定且機械臂之跟隨誤 差收斂至零。最後,將所發展之強健類神經網路控制器運用在實際兩軸機械手臂之模擬與實驗,以驗證所提方法之有效性

關鍵詞 : 適應性控制 ; 非線性系統 ; 類神經網路系統

目錄

中文摘要 v ABSTRACT vi 誌謝 vii 目錄 viii 表目錄 xiv 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 2 1.4 文章 內容簡介 4 第二章 機械臂硬體架構 6 2.1兩軸機械臂系統硬體架構 6 2.2 Lagrange運動方程式 13 2.3 兩軸機械臂數學模型 15 第三章 路徑規劃 18 3.1 運動學 18 3.2 順向運動學 19 3.3 逆向運動學 22 3.4 機械手臂工作空間 24 3.5 程式的撰寫 25 3.6 機械 臂路徑之規劃 26 第四章 強健類神經控制器之設計 34 4.1 類神經網路理論 34 4.2 人工神經元 35 4.3 類神經網路架構 38 4.4 機械臂控制問題描述 40 4.6 多連桿機器手臂的適應性RBFN控制器 45 第五章 控制系統模擬 53 5.1 PD控制器 53 5.2強健類 神經網路控制器 61 第六章 實驗 70 第七章 結論 81 7.1 結論 81 7.2 未來展望 81 參考文獻 82

參考文獻

[1] J. R. Noriega, and H. Wang, “A direct adaptive neural-network control for unknown nonlinear systems and its application, ” IEEE Transactions on Neural Networks, vol. 9, no. 1, pp. 27-34, 1998.

[2] F. J. Lin, W. J. Hwang, and R. J. Wai, “Ultrasonic motor servo drive with on-line trained neural network model-following controller, ” IEE Proceedings- Electric Power Applications, vol. 145, no. 2, pp. 105-110, 1998.

[3] H. D. Patino, R. Carelli, and B. R. Kuchen, “Neural networks for advanced control of robot manipulators, ” IEEE Transactions on Neural Networks, vol. 13, no. 2, pp. 343-354, 2002.

[4] F. Sun, Z. Sun, and P. Y. Woo, “Neural networks-based adaptive controller design of robotic manipulators with an observer,”

IEEETransactions on Neural Networks, vol. 12, no. 1, pp. 54-67, 2001.

[5] S. J. Huang, and J. S. Lee, “A stable self-organizing fuzzy controller for robotic motion control, ” IEEE Transactions on Industrial Electronics, vol. 47, no. 2, pp. 421-428, 2000.

[6] B. K. Yoo, and W. C. Ham, “Adaptive control of robot manipulator using fuzzy compensator, ” IEEE Transactions on Fuzzy Systems, vol.

8, no. 2, pp. 186-199, 2000.

[7] 鄭佳弘,“非線性多變數系統之適應性模糊最佳控制器設計”,碩士論文,國立台灣大學,電機工程學系, 2002.

[8] 廖義銘,“應用模糊理論於機械手臂混合式位置/力量控制之研究”,碩士論文,國立台灣科技大學,電機工程學系, 2000.

[9] Andreja Rojko and Karel Jezernik, “Adaptive Fuzzy Sliding Mode Motion Control of Robot Manipulator, ” University of Maribor, copyright IFAC, 2002.

[10] L. Behera and K.K. Anand, “Guaranteed tracking and regulatory performance of nonlinear dynamic systems using fuzzy neural networks,

”IEE Proc.-Control Theory Appl. , vol. 146, pp. 484-491. 1999.

[11] C.J. Chien, “A sampled-data iterative learning control using fuzzy network design, ”Internat. J. Control, vol. 73, pp. 902-913. 2000.

[12] C. T. Lin and C.S.G. Lee, “Neural network-based fuzzy logic control and decision system, ” IEEE Trans. Comput, vol.40, pp. 1320-1336.

1991.

[13] 謝冠雲,“多軸機械臂之力量控制與定位追蹤”,碩士論文,元智大學,電機工程學系, 2002.

[14] 陳芳雄,“機械手臂之非線性遞回步階控制設計”,碩士論文,暨南國際大學,電機工程學系, 2004.

[15] 沈奇聰,“平面雙機械臂之順滑控制法”,碩士論文,國立中興大學,機械工程學系, 2003.

(2)

[16] 張斐章、張麗秋、黃浩倫,“類神經網路理論與實務”,東華書局, 2003.

[17] Z. Qu and D.M. Dawson, “Robust tracking control of robot manipulators, ” Piscataway, NJ:IEEE, 1996.

[18] J. Park and I.W. Sandberg, “Universal approximation using radial basis-function networks, ” Neural Computation, vol. 3, pp 246-257, 1991.

[19] R.M. Sanner and J.-J. E. Slotine, “Gaussian networks for direct adaptive control, ” IEEE Transactions on Neural Networks, vol.3, no. 6, pp 837-863, 1992.

[20] H. Han, C.Y. Su, and Y. Stepanenko, “Adaptive control of a class of nonlinear systems with nonlinearly parameterized fuzzy approximators,

” IEEE Transactions on fuzzy systems, vol.9, no. 2, pp 315-323, 2001.

[21] R. C. HIBBELER,“Engineering Mechanics:Dynamics, ”,Prentice Hall, 1997.

參考文獻

相關文件

Wang, Solving pseudomonotone variational inequalities and pseudo- convex optimization problems using the projection neural network, IEEE Transactions on Neural Network,

Qi (2001), Solving nonlinear complementarity problems with neural networks: a reformulation method approach, Journal of Computational and Applied Mathematics, vol. Pedrycz,

SG is simple and effective, but sometimes not robust (e.g., selecting the learning rate may be difficult) Is it possible to consider other methods.. In this work, we investigate

for training

Random Forest: Theory and Practice Neural Network Motivation.. Neural Network Hypothesis Neural Network Training Deep

They are suitable for different types of problems While deep learning is hot, it’s not always better than other learning methods.. For example, fully-connected

Attack is easy in both black-box and white-box settings back-door attack, one-pixel attack, · · ·. Defense

Wang, and Chun Hu (2005), “Analytic Hierarchy Process With Fuzzy Scoring in Evaluating Multidisciplinary R&D Projects in China”, IEEE Transactions on Engineering management,