適應性模糊類神經控制系統設計

Design of Adaptive Fuzzy-Neural Control System

許駿飛(Chun-Fei Hsu)

指導教授 ： 林志民

元智大學/工程學院/電機工程學系/博士(2002年)

摘要

本論文主要針對模糊邏輯控制器與類神經網路控制器進行設計，並將適應性調整與滑動模式的設計技巧結合應用在控制系統參數學習能力上。在模糊邏輯控制器設計方面，提出單調整模糊滑動模式控制與全調整模糊滑動模式控制方法。在提出的單調整控制器只調整模糊規則庫，然而全調整控制器則可同時調整模糊規則庫與歸屬函數。在類神經網路控制器設計方面，則提出類神經網路適應性控制、回饋型類神經網路適應性控制與監督式回饋型模糊類神經網路控制系統，其中類神經網路之參數調整利用最陡坡降法調整法則與李亞普諾夫穩定理論以增加網路收斂速度與系統之穩定性。另外提出一混合式模糊滑動模式控制器用來解決高階耦合系統。最後，將所開發之控制法則應用於飛彈導引、感應伺服馬達、防鎖煞車、機翼震盪與氣彈力等系統以驗證這些方法之可行性。

關鍵字

模糊控制 ； 類神經網路

並列摘要

This dissertation focuses on the design of the fuzzy logic controllers and neural network controllers based on the sliding-mode control and adaptive control technologies. For the fuzzy logic controller designs, a single-tuned fuzzy sliding-mode control and a full-tuned fuzzy sliding-mode control systems are developed. The single-tuned control system can tune the rule sets of fuzzy rules; and the full-tuned control system can tune not only the rule sets but also membership functions of the fuzzy rules. For the neural network controller designs, a neural-network-based adaptive control, a recurrent-neural-network- based adaptive control and a supervisory recurrent-fuzzy-neural-network control design methods are proposed. In these control system designs, an on-line parameter tuning methodology, using the gradient descent method or the Lyapunov stability theorem, is developed to increase the learning capability and to guarantee the systems’ stability. Moreover, a hybird fuzzy sliding-mode control design method is developed to resolve a high-order coupled system. Finally, the developed control system design methods are applied to some control system applications, such as missile guidance system, induction servomotor system, antilock braking system, wing rock system, and aeroelastic system, to demonstrate the effectiveness of the proposed design methods.

並列關鍵字

fuzzy logic control ； neural network

參考文獻

[3] C. C. Lee, “Fuzzy logic in control systems: fuzzy logic controller-part I/II,” IEEE Trans. Systems, Man, and Cybernetics, vol. 20, no. 2, pp. 404-435, 1990.

[4] H. O. Wang, K. Tanaka, and M. F. Griffin, “An approach to fuzzy control of nonlinear systems: stability and design issues,” IEEE Trans. Fuzzy Systems, vol. 4, no. 1, pp. 14-23, 1996.

[5] R. Palm, “Robust control by fuzzy sliding mode,” Automatica, vol. 30, no. 9, pp. 1429-1437, 1994.

[6] S. W. Kim and J. J. Lee, “Design of a fuzzy controller with fuzzy sliding surface,” Fuzzy Sets and Systems, vol. 71, no. 3, pp.359-369, 1995.

[7] X. Yu, Z. Man, and B. Wu, “Design of fuzzy sliding-mode control systems,” Fuzzy Sets and Systems, vol. 95, no. 3, pp. 295-306, 1998.