在非線性系統中，因為存在參數不確定性或內部不穩定性及受到外部干擾影響，而造成追蹤不易，讓系統輸出響應不如預期，甚至使得閉迴路系統不穩定，為此本文提出H∞-類神經滑動綜合控制器來解決此問題。本控制器是利用滑動模式去控制系統，並使用了類神經網路中的倒傳遞演算法去補償系統中未知的不確定項。此外，基於里亞布諾夫穩定性定理，此控制器可使得具有內部不穩定性之系統穩定，亦可讓閉迴路系統中外部干擾對系統輸出的H∞範數壓低至某範圍內，以降低外部干擾對系統輸出的影響。
最後，本文將針對非線性多變數之機械手臂操作系統，作為模擬控制對象，來驗證所設計之H∞-類神經滑動綜合控制器之可行性，且經由模擬結果顯示，本控制器能有效壓低外部干擾對系統輸出的影響，使得系統能達到良好之追蹤性能，並有著不錯的強健性。

In a nonlinear system, the desired performance is difficult to be achieved and the close-loop system may even be unstable because of the presence of plant uncertainties and external disturbances. This research proposes a H∞-neural sliding-mode composite controller to resolve the problems described above. The proposed controller is based on the H∞-control and sliding-mode control skills and the gradient steepest descent method of the artificial neural network; the latter is used to compensate the plant uncertainties. In the proposed H∞-neural sliding-mode composite controller, we utilize the H∞-control methodology, which is resulted from Lyapunov stability formulation, to suppress the H∞-norm of the closed-loop transfer function matrix between the exogenous inputs(d(t)) and the controlled output(z(t)) so as to ensure the system robustness.
Finally, a robot manipulator is studied as an example in this research to verify the feasibility of the proposed H∞-neural sliding-mode composite controller. The computer simulation results reveal that the proposed controller is robust to plant uncertainties and disturbances and is able to achieve good tracking performance.

[1]A. J. van der Schaft, “L2 gain analysis of nonlinear systems and nonlinear H∞ control,” IEEE Trans. Automat. Control, vol. 37, no. 6, pp. 770–784, 1992.

[2]A. J. van der Schaft, “On a state space approach to nonlinear H∞ control,” Syst. Contr. Lett., vol. 16, no. 1 , pp. 1-8, 1991.

[3]Akio Ishiguro, Takeshi Furuhashi, Shigeru Okuma, “A Neural Network Compensator for Uncertainties of Robotics Manipulators,” IEEE Trans. Indus. Electr. , vol. 39, no. 6, pp. 565 – 570, December 1992.

[4]C.N. Hwang, “Formulation of H2 and H∞ Optimal Control Problems – A Variational Approach,” Journal of the Chinese Institute of Engineering’s, vol. 16, no. 6, pp. 853-866, 1993.

[5]C.N. Hwang, “Synthesis Procedure for Nonlinear Systems”, Proc. Natl. Sci. Counc. ROC(A) vol. 17 ,no. 4, pp. 279-294 ,1993.

[6]C.N. Hwang, “Design of Robust Controllers for Manipulators”, Journal of the National Cheng-Kung University, vol.26. ,Sci.Eng.&Med.Section, pp. 213-234,1991.

[7]C.N. Hwang, “Tracking of controllers for robot manipulators”, Master Dissertation, Michigan state University, 1986.

[8]C.S. Shieh, Ming-Rong Lee, “A study of a robust fuzzy controller for perturbed nonlinear systems,” Circuit System Signal Processing, vol. 25, no. 6, pp. 715-727, 2006.

[9]C.S. Shieh,"Robust H-infinity control of uncertain systems with time-varying state and control input delays,"IMA Journal of Mathematical Control and Information, vol.19, no.3, pp.353-361, 2002.

[10]C. T. Li, Y. H. Tan, “Neural sliding mode control for systems with hysteresis” ,Proceedings of the 2005 IEEE International Symposium on Intelligent Control , pp. 467-472, 2005.

[11]Hui Hu, Peng-Yung Woo, “Fuzzy supervisory sliding-mode and neural-network control for robotic manipulators”, IEEE Transactions on Industrial Electronics, vol. 53 , no.3, pp. 929 – 940, 2006.

[12]J.J. Slotine and W. Li , “Applied Nonlinear Control”, Prentice Hall, Englewood Cliffs, NJ, 1991.

[13]J. J. Slotine, “Sliding controller design for non-linear systems,” Int. J. Contr., vol. 40, pp. 421 – 434, 1984.

[14]J.J. Slotine and S.S. Sastry, “Tracking Control of Nonlinear Systems Using Sliding Surfaces, with Application to Robot Manipulators”, Int. J. Control, vol. 38, no. 2, pp.465-492, 1983.

[15]John C. Doyle, Keith Glover, Pramod P. Khargoner and Bruce A.Francis, “State-Space Solution To Standard and Control Problem”, IEEE Trans. Automatic Control, vol. 34, no. 8, pp. 831 -847 ,1989.

[16]Kang-Bark Park, Teruo Tsuji Terminal, “sliding mode control of second-order nonlinear uncertain systems”, International Journal of Robust and Nonlinear Control ,vol. 9, Issue 11, pp. 769–780, 1999.

[17]Mu Xiaojiang, Chen Yangzhou, “Neural sliding mode control for multi-link robots”, Control and Decision Conference, pp. 3513- 3517 , 2008.

[18]Mu Xiaojiang, Chen Yangzhou, “Decoupling neural sliding mode control for multi-link robots”, The International Federation of Automatic Control, pp. 6-11, 2008.

[19]M.-Y. Shieh and Tzuu-Hseng S. Li, 1995. “Implementation of integrated fuzzy logic controller for servomotor system,” in Proc. of FUZZ-IEEE/IFES’95, pp. 1755-1762, March 1995.

[20]Rosenblatt,F., ”Principles of Neurodynamics : Perceptrons and The Theory of Brain Mechanisms Spartan ” , New York,1962.

[21] Rumelhart ,D.E. ,G.E.Hinton and R.J.Williams ,” Lreaing representations by back-propagation errors.” ,Nature (London),vol. 323,pp. 533-536 , 1986.

[22]Tsai, H. Chung, and F. Yu, “Neuro-sliding mode control with its applications to seesaw systems”, IEEE Trans. Neural Networks, vol.15, pp.124-134, 2004.

[23]Xinghuo Yu, Kaynak, O. “ Sliding-Mode Control With Soft Computing: A Survey”, IEEE Transactions on Industrial Electronics, vol.56, pp. 3275 - 3285, 2009.

[24]Y. Yildiz, A. Sabanovic, K.Abidi. “Sliding mode neuro controller for uncertain systems ” , IEEE Tans on industry and electronics, vol.54, pp. 1676-1684, 2007.

[25]Yeong-Chan Chang, “Neural network-based H∞ tracking control for robotic systems”. IEEE Proc-Control Theory Appl. , vol.147, no.3, pp. 303-311, May 2000.

[26]李祖聖，“高等模糊控制講義”， 國立成功大學電機系。

[27]蘇義閎、黃正能“H∞模糊滑動複合控制設計與其在水下載具上之應用”, 國立成功大學造船及船舶機械工程研究所碩士論文, 2010。

[28]郭鴻霖、黃正能“類神經網路應用於H∞控制系統之研究”, 國立成功大學造船及船舶機械工程研究所碩士論文, 2000。

[29]楊憲東、葉芳柏，“線性與非線性H∞控制理論”，全華科技圖書股份公司，1997。

[30]楊憲東，“非線性控制講義”，國立成功大學航太系，2009。

[31]楊憲東，“H∞控制理論及應用講義”，國立成功大學航太系，1999。