臺灣博碩士論文加值系統

　　反覆學習控制系統的學習增益與誤差的收斂性能有非常密切的關係，本論文針對此一問題，研究離散型反覆學習控制系統的學習增益設計方法，提出改良學習增益的設計架構，以增進學習系統的學習收斂速度。本論文的第一個重點是引用模糊邏輯系統來設計學習增益，根據學習誤差的大小與變化，適應性地調整學習增益，並提出速度型與位置型的兩種適應模糊學習增益的設計概念。由於模糊邏輯系統的後件部通常用經驗法則來選擇，不易達成最佳的設計，因此本論文的第二個重點是引用基因演算法，希望藉著基因演算法的尋優功能來搜尋模糊學習增益的後件部的最佳參數。另外，本論文並針對基因演算法提出改良的策略，進一步提高基因演算最佳參數的搜尋速度。
最後，本論文利用一個數值範例，透過電腦模擬驗證所提出的基因演算適應模糊反覆學習控制器之性能。模擬結果顯示，不論速度型或位置型的模糊學習增益，改良型基因演算法則均可以有效地決定模糊學習增益的後件部規則參數。而基於改良型基因演算法所設計的適應模糊反覆學習控制器，的確能有效改進反覆學習的收斂速度，提高反覆學習控制的學習性能。

The learning gain of iterative learning control system has a close relationship to the convergence of learning error. In this thesis, we study the learning gain design approach for discrete iterative learning controller and propose a design structure to improve the learning convergent speed. The first part of this thesis is to apply the fuzzy logic system for the design of learning gain. The learning gain can be adaptively tuned according to the magnitude and the change of learning error. Speed-type and position-type approaches are presented for the implementation of adaptive fuzzy learning gain. However, the optimal design of the fuzzy logic system is hard to achieve because the consequent part is in general chosen by trial and error. Hence, in the second part of this thesis, a genetic algorithm is then introduced to search for the optimal parameters of the adaptive fuzzy learning gain. Furthermore, a modified version of genetic algorithm is also presented in order to improve the search speed of the optimal parameters.
Finally, a numerical example is used for computer simulation to demonstrate the learning performance for the genetic algorithms based adaptive fuzzy iterative learning controller. Simulation results show that the consequent parameters can be determined no matter the speed-type or position-type fuzzy learning gain is used. Based on the optimal parameters given by the proposed genetic algorithm, the convergent speed and learning performance can be effectively improved.

誌謝
中文摘要
ABSTRACT
目錄
圖錄
表錄
第一章、緒論
1-1 研究動機
1-2 反覆學習控制
1-3 模糊控制
1-3-1 模糊控制理論簡介
1-3-2 模糊控制系統架構
1-4 基因演算法
1-4-1 基因演算法的沿革
1-4-2 編碼(Encoding)與解碼(Decoding)
1-4-3 隨機(Random)產生初始族群(Initial population)
1-4-4 計算適應性函數(Fitness Function)
1-4-5 基因演算法的演算過程
第二章：適應模糊反覆學習控制之設計
2-1 無初始誤差的情況
2-2 適應模糊學習增益的設計
2-3模擬範例
第三章：改良型基因演算法
3-1 動機
3-2 分裂演進
3-3 智慧型交配
3-4 染色體重組
3-5 強制演進
3-6 改良型基因演算法之驗証
3-6-1應用於模糊控制倒車入庫
3-6-2 實驗結果
第四章：改良型基因演算法應用於適應模糊反覆學習控制器之設計與實驗結果
4-1 改良型基因演算法於適應模糊反覆學習控制器之設計
4-2 模糊範例
4-2-1 系統架構
4-2-2 改良型基因演算法於模糊學習增益之設計
4-2-3速度型適應模糊學習控制系統之實驗結果
4-2-4 位置型適應模糊學習控制系統之實驗結果
第五章：結論與建議

[1]M. Uchiyama, “Formation of high-speed motion pattern of a mechanical arm by trial”, Trans. SICE (Society for Implementation and Control Engineers(in Japanese), vol. 14, pp. 706-712, 1978.
[2]S. Arimoto, S. Kawamura, and F. Miyazaki, “Bettering operation of robots
by learning”, J. of Robotic Systems, vol. 1, pp.123-104, 1984.
[3]G. Casalino, and G. Bartolini, “A learning procedure for the control of movements of robotic manipulators”, IASTED Symp. on Robotics and Automation, pp. 108-111, 1984.
[4]J. J. Craig, “Adaptive control of manipulators through repeated trials”, Proceedings of American Control Conference, San Diego, CA, June, 1984.
[5]J. E. Hauser, “Learning control for a class of nonlinear systems”, Proceedings of the IEEE 26th Conference on Decision and Control, Los Angeles, California, U.S.A., pp. 859-860, 1987.
[6]T. Sugie and T. Ono, “An iterative learning control law for dynamicsystems”, Automatica, 27, pp. 729-732, 1991.
[7]G. Heinzinger, D. Fenwick, B. Paden, and F. Miyazaki, “Stability of learning control with disturbances and uncertain initial conditions”, IEEE Trans. on Automatic Control, vol. 37(1), pp. 110-114, 1992.
[8]S. Kawamura, F. Miyazaki, and S. Arimoto, “Realization of robot motion based on learning method”, IEEE Trans. on System, Man, and Cybernetics, vol. 18, pp. 126-134, 1988.
[9]S. Arimoto, “Robustness of learning control for robot manipulators”, Proceedings of the IEEE International Conference on Robotics and Automation, Cincinnati, Ohio, U.S.A., pp. 1528-1533, 1990.
[10]S. Arimoto, “Learning control theory for robotic motion”, Int. J. of Adaptive Control and Signal Processing, vol. 4, pp. 543-564, 1990.
[11]S. Arimoto, T. Naniwa, and H. Suzuki, “Robustness of P-type learning control with a forgetting factor for robotic motions”, Proceedings of the IEEE 29th Conference on Decision and Control, Honolulu, Hawaii, U.S.A., pp. 2640-2645, 1990.
[12]T. Y. Kuc, J. S. Lee, and K. Nam, “An iterative learning control theory for a class of nonlinear dynamic systems”, Automatica, vol. 28, pp. 1215-1221, 1992.
[13]Z. Geng, R. L. Carroll, and J. Xie, “Two-dimensional model algorithm analysis for a class of iterative learning control systems”, International Journal of Control, vol. 52, pp. 833-862, 1990.
[14]J. E. Kurek, and M. B. Zaremba, “Iterative learning control systhesis based on 2-D system theory”, IEEE Trans. on Automatic Control, vol. 38, pp. 121-125, 1993.
[15]S. S. Saab, “A discrete-time learning control algorithm for a class of linear time-invariant systems”, IEEE Trans. on Automatic Control, vol. 40, pp. 1138-1141, 1995.
[16]C.-J. Chien, “A discrete iterative learning control for a class of nonlinear time-varying systems” IEEE Transactions on Automatic Control, vol. 43, pp. 748-752, 1998.
[17]L. A. Zadeh, “Fuzzy Set”, Information and Control, vol. 8, pp. 338-353, 1965.
[18]L. X. Wang, Adaptive Fuzzy Systems and Control, Englewood Cliffs, NJ : Prentice Hall, 1994.
[19]J. Holland, “Adaptation in Natural and Artificial Systems”, Ann Arbor, MI: University of Michigan Press, 1975.
[20]E. Sanchez, T. Shibata, and L. A. Zadeh, Genetic Algorithms and Fuzzy Logic Systems Soft Computing Perspectives, World Scientific, 1997.
[21]李承錕，「適應模糊反覆學習控制器的設計與FPGA晶片實作」，華梵大學電子工程學系碩士學位論文，PP. 11-15，民國九十七年九月。
[22]Shinn-Ying Ho, Li-Sun Shu, and Jian-Hung Chen, ”Intelligent evolutionary algorithms for large parameter optimization problems”, IEEE Transactions on Evolutionary Computation, Vol. 8, No. 6, pp. 522-541 2004.
[23]江衍科，「改良型基因演算模糊控制器之設計與運用」，華梵大學機電工程學系碩士學位論文，pp. 35-43，民國九十三年七月。