本研究之目的是針對機械手臂之循軌控制提出適應性神經網路滑動模式控制方法。於系統模型部份已知的情況下，運用極點配置法來設計標稱控制器指定機械手臂之理想動態，並透過滑動模式干擾估測器及適應性神經網路補償器將系統的不確定性及外部干擾予以補償，以實現指定的理想動態。
系統控制架構中之滑動模式干擾估測器用於提昇整體控制架構之初始性能，並對於未知的干擾給予快速有效的補償，以提升系統的強健性能。相對於適應性神經網路控制器透過自訂的適應性法則，將未知干擾建模於神經網路規則庫；當建模完成便可依據系統之狀態，查得目前的系統干擾，以達到即時的干擾補償，可進一步改善滑動模式干擾估測器補償的相位落後問題。
本文實驗平台方面，採用美國德州儀器公司(Texas Instruments Incorporated, TI)所生產之TMS320C6713 DSP搭配具FPGA之自製擴充子板為控制器核心。在FPGA方面，以硬體描述語言(VHDL)撰寫Encoder, ADC與DAC等週邊界面程式；在控制法則實現上，利用TI所提供的Code Composer Studio (CCS)發展環境，以C/C++撰寫控制器程式並下載到DSP上執行。藉由本實驗室自製的雙軸機器手臂實驗平台進行追圓軌跡控制，結果顯示能有效提升循軌的表現及降低循軌誤差。

A scheme of adaptive neural network sliding-mode control is proposed in this paper to deal with highly nonlinear dynamics of robotic manipulators for trajectory tracking. By using a simplified model, a nominal controller is obtained by pole placement design to specify ideal closed-loop dynamics. Then, an adaptive neural network compensator augmented with a sliding-mode disturbance observer (SDOB) compensator for system uncertainties and external disturbances.
The SDOB ensures well transient performance and compensates well for unknown perturbation. In addition, the adaptive neural network compensator is used to model an unknown perturbation according to the proposed adaptive law. When the perturbation has been well modeled, the control system can efficiently compensate for the perturbation, avoiding the phase-lag problem associated with the SDOB.
The experimental system consists of a two-link robotic manipulator and a DSP/FPGA system, that is the control kernel. We employ the C language and VHSIC hardware description language (VHDL) as tools for developing a servo control system. The experimental results of tracking a circular trajectory show that the proposed scheme improves the tracking performance and decreases the tracking error.

摘 要 I
ABSTRACT II
誌 謝 III
圖目錄 VI
表目錄 XI
第一章 緒論 1
1.1 前言 1
1.2 文獻回顧 2
1.3 論文架構 5
第二章 系統描述 6
2.1 實體系統系統架構 6
2.1.1 系統架構簡介 6
2.1.2 硬體設備 7
2.1.3 系統之位置與速度回授 10
2.2 系統模型描述 11
2.3 系統輸出入檢測 14
2.4 系統鑑別 16
第三章 雙軸機械手臂之適應性神經網路滑動模式控制架構 20
3.1 神經網路控制器架構說明 20
3.1.1 神經網路控制器—輻狀基底類神經網路(Radial basis function ANN)的組成 20
3.1.2輻狀基底類神經網路控制器設計 21
3.2 適應性神經網路滑動模式 24
3.3 LYAPUNOV穩定性證明 27



第四章 實驗方法與結果 30
4.1 軌跡命令方式 30
4.2 定義輻狀基底類神經網路補償器之神經元高斯函數寬度 32
4.3 實驗方式 33
4.4實驗結果 36
4.4.1 ANSMC之隱藏層個數設計 36
4.4.2標稱控制器、標稱控制器和SDOB組合控制器與ANSMC比較 39
4.4.3標稱控制器極點大小比較 45
4.4.4 NSDOB控制模式 48
4.4.5標稱控制器極點加大、NSDOB之動態頻寬加大與ANSMC比較 51
4.4.6 ANSMC之有無切換訊號情形的學習模式比較 57
4.4.7 ANSMC於無切換訊號但保留 中 參數之比較 65
4.4.8 ANSMC於有切換訊號但 控制器並且加入步階干擾之比較 75
4.4.9不同負載下之ANSMC控制情況與加入步階干擾後的補償行為 83
第五章 結論 84
5.1 結論 84
5.2 未來展望 85
參考文獻 86

[1] http://news.cts.com.tw/udn/money/201208/201208301084294.html
[2] http://blog.cnyes.com/My/JengYen/article923266
[3] 簡銘志，“工業機械臂之適應控制理論的發展”，智慧型機器人產業情報 報告，no.50，pp. 11-21，2011。
[4] http://en.wikipedia.org/wiki/Frank_Rosenblatt
[5] M. Olazaran, “A Sociological Study of the Official History of the Perceptrons Controversy,” Social Studies of Science, vol. 26, no. 3, pp. 611-659, 1996
[6] http://www.docin.com/p-224163685.html
[7] S. B. Choi and J. S. Kim, “A Fuzzy-Sliding Mode Controller for Robust Tracking of Robotic Manipulators,” Mechatronics, vol. 7, no. 2, pp. 199-216, 1997.
[8] N. Yagiz and Y. Hacioglu, “Robust Control of a Spatial Robot Using Fuzzy Sliding Modes,” Mathematical and Computer Modelling, vol. 49, no. 1-2, pp. 114-127, 2009.
[9] Y. W. Cho and K. S. Seo and H. J. Lee “A Direct Adaptive Fuzzy Control of Nonlinear Systems with Application to Robot Manipulator Tracking Control,” International Journal of Control, Automation, and Systems, vol. 5, no. 6, pp. 630-642, 2007.
[10] M. O. Efe, “Fractional Fuzzy Adaptive Sliding-Mode Control of a 2-DOF Direct-Drive Robot Arm,” IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics, vol. 38, no. 6, pp. 1561-1570, 2008.
[11] C. G. Kang, “Variable Structure Fuzzy Control Using Three Input Variables for Reducing Motion Tracking Errors,” Journal of Mechanical Science and Technology, vol. 23, no. 5, pp. 1354-1364, 2009.
[12] S. Huang, K. S. Huang, K. C. Chiou, “Development and application of a novel radial basis function sliding mode controller,” Mechatronics, Vol. 13, no. 4, pp. 313-329, 2003
[13] 王炫文，高性能加速規之研製與無刷伺服系統之速度估測與干擾補償，國立雲林科技大學機械工程學系研究所碩士論文，2007。
[14] 鄭兆閔，無刷伺服馬達之改良型PID控制與干擾補償，國立雲林科技 大學機械工程學系研究所碩士論文，2003。
[15] 鄒家弘，雙軸機器手臂之模糊控制，國立雲林科技學機械工程學系研究所碩士論文，2009。
[16] M. Jin, S. H. Kang, and P. H. Chang, “Robust compliant motion control of robot with nonlinear friction using time-delay estimation,” IEEE Trans. Ind. Electron., Daejeon, vol. 55, no. 1, pp. 258–269, 2008.
[17] E.A. Feilat and E.K. Maaitah, “Identification and Control of DC Motors Using RBF Neural Network Approach,” in proceedings of the International Conference on Communication, Computer and Power(ICCCP 09), MUSCAT, pp. 258-264, 2009.
[18] S. Elanayar and Y. C. Shin, “Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems,” IEEE Trans. on Neural Networks, Beijing, China, vol. 5, no. 4, pp. 594-603, 1994.

[19] L. K. Qiu, Y. Z. Zhao, and Y. X. Zhang, “Adaptive Friction Identification and Compensation Based on RBF Neural Network for the Linear Inverted Pendulum,” International Conference on, Electronic and Mechanical Engineering and Information Technology (EMEIT), Harbin, Heilongjiang, China, vol. 1, pp. 385-388, 2011.
[20] 周晏玲，應用動態模糊系統於旋轉式倒單擺系統之分析與控制，大葉大學機電自動化研究所碩士班碩士論文，2004。