在本文中，我們提出結合H∞補償器和遞迴式類神經網路補償器（Recurrent Neural Network, RNN）之綜合控制系統，並對系統的參考輸入作追蹤控制。首先引用Hwang【3】和Doyle【6】所提出的時域解法求得H∞ 補償器，再與一使用倒傳遞演算法的遞迴式類神經網路補償器【5】作結合。
　　通常為了要確保系統的強健性，H∞補償器會出現過份保守的設計，及較長的測試時間，而且當外擾的大小超過了限制範圍時，系統的強健性會被影響。因此在所設計的綜合控制系統中，使用了具有自動學習，及自動診斷功能的RNN補償器。RNN補償器由量測誤差瞬間的斜率，預測出過大的超越量後，做出適度的矯正工作，以彌補H∞補償器不足之處。不過，由於RNN補償器的計算量較一般的類神經控制器大，所以本文使用了倒傳遞演算法來做RNN補償器的學習規則，以增加運算上的速度。
　　最後，本文對一已知狀態空間方程式之飛機的數學模型做電腦模擬。由模擬結果顯示出，所設計出的控制系統，與單只有H∞控制器比較起來，在追蹤性能的收斂速度方面上，沒有太大的差距，但在最大超越量上有改善，顯示出所加入的遞迴式類神經網路補償器有確實發揮出功能。

　In this study, a composite design of Recurrent Neural Network (RNN) H∞-Compensator is proposed for tracking the desired input. The composite control system is composed of an H∞ compensator, which is proposed by Hwang 【3】 and Doyle 【6】, and a back-propagation RNN compensator.
　In order to make the controlled system robust, the H∞ control law is relatively conservative in the solution process. To speed up the convergence of tracking errors and match the prescribed performance, the recurrent neural network with self-learning algorithm is used to improve the performance of the H∞-compensator. The back-propagation algorithm in the proposed RNN-H∞ compensator is applied to minimize the calculating time of the predicting parameters.
　Computer simulation results show that the desired performance can easily be achieved by using the proposed RNN-H∞ compensator under the presence of disturbances.

【1】 C. Attaianese, A. Perfetto, and G. Tomasso, “Robust Position Control of DC Drives by Means of H∞ Controllers, “Proc. IEE-Elect. Power Applicat. , vol. 146, no. 4, pp. 391-396, 1999.

【2】 C. C. Ku and K. Y. Lee, “Diagonal Recurrent Neural Networks for Dynamic Systems Control, “IEEE Trans. Neural Networks, vol. 6, pp. 144-156, Jan. 1995.

【3】 C.N. Hwang, “Formulation Of H2 and H∞ Optimal Control Problems- A Variational Approach, “Journal Of The Chinese Institute Of Engineers, vol. 16, no. 6, pp. 853-866, 1993.

【4】 D. R. Hush and B. G. Home, “Progress in supervised neural networks, “IEEE Signal Processing Magazine, Vol. 10 Issue: 1, pp. 8-39 Jan. 1993.

【5】 Faa-Jeng Lin, Senior Member, IEEE, Tzann-Shin Lee, and Chih-Hong Lin, “Robust H∞ Controller Design with Recurrent Neural Network for Linear Synchronous Motor Drive, “IEEE Transations on Industrial Electronics, Vol. 50, No. 3, June 2003.

【6】 John C. Doyle, Keith Glover, Pramod P. Khargonekar, Bruce A. Francis, “State-Space Solutions to Standard H2 and H∞ Control Problems, “IEEE Transactions on Automatic Control, vol. 34, no. 8, pp. 831-847, August 1989.

【7】 P. S. Sastry, G. Santharam and K. P. Unnikrishnan, “Memory neuron networks for identification and control of dynamical systems, “Neural Network IEEE Trans., Vol. 5, No. 2, pp. 306-319, 1994.

【8】 R. Naim, G. Weiss, and S. Ben-Yaakov, “H∞ Control Applied to Boost Power Converters, “IEEE Trans. Power Electron, vol. 12, pp. 677-683, July 1997.

【9】 S. C. Sivakumar, W. Robertson, and W. J. Phillips, “On-line Stabilization of Block-Diagonal Recurrent Neural Networks, “IEEE Transactions on Neural Networks, vol. 10, pp. 167-175, Mars. 1999.

【10】 Simon Haykin, “Neural networks-A Comprehensive Foundation, “McMaster University, Hamilton, Ontario, Canada, pp. 8-22, 1994.

【11】 S. Kumpati and K. S. Narendra, “Neural networks for control: theory and practice, “Proceedings of the IEEE, Vol. 84, No. 10, Oct. 1996.

【12】 T. W. S. Chow and Y. Fang, “A Recurrent Neural-Network-Based Real-Time learning Control Strategy Applying to Nonlinear Systems with Unknown Dynamics, “IEEE Trans. Ind. Electron., vol. 45, pp. 151-161, Feb. 1998.

【13】 黃正能，詹國琴，“非線性系統之H∞控制器設計及迴路整型，“國立成功大學造船及船舶機械工程研究所碩士論文，1999。

【14】 楊憲東，“H∞ 控制理論與應用，“成功大學航空太空研究所，92年。

【15】 蘇木春與張孝德，“機械學習類神經網路、模糊系統以及基因演算法則(二版)，“全華科技圖書股份有限公司，臺北市， 03月89年。