一般的控制系統都是非線性的，系統包含有未知的元素諸如未知系統參數或系統內部改變的不確定性，以及外部的干擾，這些因素都很有可能造成控制系統的工作性能下降，甚至造成閉迴路系統不穩定。因此本文提出了一個非線性自適應類神經 H∞-控制器，來針對具有外部干擾及有不確定項的非線性系統去設計。
在本篇論文中使用了收斂速度較快RBF(Radial Basis Function)類神經網路去估測系統中的不確定項。並加入狀態觀測器和H∞-控制器，H∞-控制器用來壓低對外部干擾和神經網絡的逼近誤差的影響。狀態觀測器用於估計無法測量的系統狀態。控制器和參數更新基於Lyapunov的理論可以保證跟蹤誤差會漸近收斂為零。
最後，本文分別以倒單擺系統與機械臂系統兩個例子，執行電腦模擬，模擬結果表明，用尼可士圖或奇異值圖可對自適應類神經H∞-控制器性能作圖形上的分析。此外，在本研究中使用極點設置法來調整控制增益，而不是任意分配，以確保控制器的預設性能。電腦模擬結果證明了控制器的可行性，並實現所需的預設性能。

A general system is usually nonlinear and contains unknown elements, such as the plant parameter variations，the system uncertainties and disturbances. These factors are likely to cause ill-effects on the system performance and result in the instability of the closed-loop system. This research presents a nonlinear adaptive-neural H∞-controller，which is designed to exclude the above uncertainties .
In this thesis，the RBF (Radial Basis Function) neural network is used to estimate the uncertain nonlinear terms of the system in order to speed up the convergence of estimating errors. The H∞-control low in the proposed controller is ultilized to suppress the effect of the external disturbances on the controlled outputs. The Adaptive-neural portion of the composite controller makes the controller more efficient on the estimation of uncertain states or nonlinear uncertain terms. The nonlinear system is then examined by using the Lyapunov stability theorem to ensure the closed-loop stability.
An inverted pendulum and a robot manipulator are respectively used as two examples in computer simulations. The simulation results reveal that the proposed adaptive-neural H∞-controller can track the desired performance graphically by the aid of Nichols Chart or singular value plots. Besides，in this study，the adjustable gains of the proposed controller are assigned by the pole-placement method in stead of arbitrary assignment to make sure the satisfaction of the prespecified performance. The computer simulations also attest the controller feasibility of the proposed controller on achievement of the desired performance.

[1] C.C. Kung, T.H. Chen, L.H. Kung, "Modified Adaptive Fuzzy Sliding Mode Controller for Uncertain Nonlinear Systems", IEICE Trans. Fundamentals, Vol. E88-A, No.5, pp.1328-1334, May 2005.

[2] Chen Mou, Jiang Chang_sheng, Wu Qing_xian. Adaptive -control of a class of uncertain nonlinear systems based on RBF neural networks[J]. Control Theory&Applications, 2003, 20(1): 27-32

[3] C.N. Hwang, "Tracking controllers for robot manipulators", Master Dissertation, Michigan State University, 1986.

[4] F. Kurt and S. Dierk, “An improved stable adaptive fuzzy control method,” IEEE Trans. Fuzzy Syst., vol. 7, pp. 27–40, Feb. 1999

[5] H.F. HO, Y.K. Wong, A.B. Rad, "Adaptive fuzzy sliding mode control with chattering elimination for nonlinear SISO systems", Simulation Modelling Practice and Theory, Vol.17, No.7 , pp.1199-1210, 2009.

[6] HAYAKAWA T., HADDAD W.M., HOVAKIMYAN N.: ‘Neural network adaptive control for a class of nonlinear uncertain dynamical systems with asymptotic stability guarantees’, IEEE Trans. Neural Netw., 2008, 19, (1), pp. 80–89

[7] H Hui., LIU Guo-rong., GUO Peng.: ‘Adaptive Neural Network H∞ tracking control for a class of uncertain nonlinear systems’, 2009 IEEE, 34, (5), pp. 158 - 162

[8] SASTRY S.S., ISIDORI A.: ‘Adaptive control of linearization systems’, IEEE Trans. Autom. Control, 1989, 34, (11),pp. 1123–1131

[9] S.C. Tong, T.Y. Chai, Fuzzy adaptive control for a class of nonlinear systems, Fuzzy Sets and Systems 101 (1999) 31–39.

[10] S. N. Huang, K.K. Tan and T. H. Lee. “Nonlinear adaptive control of
Interconnected systems using neural networks,” IEEE Trans. Neural Networks, vol. 17, no. 1, Jan. 2006, pp.243-246.

[11] S.Huang, K.K. Tan and T.H. Lee, “Decentralized control design for largescale systems with strong interconnections using neural networks,” IEEE Trans. Automa. Contr., vol. 48, no. 5, May, 2003, pp. 805-810.

[12] Tang Jiantao, Tong Shaocheng. Adaptive -control of nonlinear
systems based on neural networks[J]. Control and Decision, 1999,
14(4): 297-302.

[13] Y. G. Leu, T. T. Lee, and W. Y. Wang, “On-line tuning of fuzzy-neural network for adaptive control of nonlinear dynamiceal systems,” IEEE Trans. Syst., Man, Cybern. B, vol. 27, pp. 1034–1043, Dec. 1997

[14] Y C Chang, B S Chen. A nonlinear adaptive -tracking control design in robotic systems via neural networks[J]. IEEE Transactions on Automatic Control, 1997, 5(1): 13-29.

[15] YANG Y.S., WANG X.F.: ‘Adaptive - tracking control for a class of uncertain nonlinear systems using radial-basisfunction neural networks’, Neurocomputing, 2007, 70,pp. 932–941

[16] 王振興，"類神經網路講義"，國立成功大學電機系，2011。

[17] 黃正能，"非線性系統分析講義"，國立成功大學系統系，2011。

[18] 楊憲東，" 控制理論及應用講義"，國立成功大學航太系，2010。

[19] 韓曾晉，“適應控制系統”，科技圖書股份有限公司，2002。

[20] 林濬毓，“ 適應性模糊複合控制器設計與應用”， 國立成功大學系統系，2011。

[21] 曾仲熙，“控制器設計與模擬範例二版”，東華書局，2010。

[22] 謝秉澂，“非線性多變數適應-H∞控制器之設計”， 國立成功大學系統系，2005。

[23] 黃翰生，“機械臂之H∞-類神經滑動綜合控制器設計”， 國立成功大學系統系，2011。