模糊理論自提出迄今已數十年，也普遍應用於各種控制系統上，雖然由模糊理論所發展出之模糊控制器，跳脫了傳統控制需知道受控體系統之數學模型，對於未知之系統有強大包容性。但因為模糊知識庫及歸屬函數之建立不易，所以對於轉移函數未知，及參數時時變動之控制系統，仍不易設計一傳統模糊控制器，使控制系統產生良好之響應。

　　針對這些缺點，本文提出了模糊類神經網路控制器，將模糊理論與類神經網路結合在一起，因類神經網路具有自我學習、彈性容錯等功能，所以利用類神經網路演算法來修正控制器和識別器內部參數，使控制器及識別器能自行調整歸屬函數，達到智慧型控制之目的，藉以彌補模糊理論之不足，使轉移函數不精確及參數時時變動之控制系統能產生良好之響應，將此控制器應用於感應電動機速度控制上，以期能得到良好之速度響應。

　　本文以DSP TMS320C32具浮點運算功能之32位元數位訊號處理器作為感應電動機轉速控制器中心，並配合本實驗室自行設計之AD/DA介面卡與驅動電路，以實現本文所提之控制理論於感應電動機上。由模擬及實驗結果得知，本文所提之控制方法，不僅暫態響應快，無穩態誤差，且對於參數變動及負載變動有良好之強健性，驗証了本文所提之控制方法之可行性。

　　Fuzzy theorems have been proposed for several decades and used in various control systems. Fuzzy controllers avoid certain control system models and have strong tolerance for uncertain systems. However, the fuzzy rule base and membership functions are not easy to establish. It is difficult to design a traditional fuzzy controller for a system with uncertainty and parameter variations that can produce excellent response.

　　This thesis proposes a fuzzy neural network controller that combines the fuzzy theorem and neural network. Because the neural network has the ability to be trained, we used a neural network algorithm to amend the parameters in the fuzzy controller and identifier. The fuzzy neural network controller can then make up for the disadvantages in the fuzzy theorem by modifying the membership functions in the controller and identifier. The proposed fuzzy neural network controller is applied to an induction motor speed controller to achieve excellent speed response.

　　The proposed control scheme was implemented using a 32-bit TMS320C32 digital signal processor, AD/DA interface and drive circuit. Simulations and experimental results demonstrated that the proposed control scheme has a quick speed response and no steady state error. This method is robust in parameter variations and load torque disturbance.

[1]L. A. Zadeh, “Fuzzy Set”, Information and Control, Vol. 8, pp. 338-358, 1965.

[2]A. K. Adnanes, “Torque Analysis of Permanent Magnet Synchronous Motors”, IEEE 22nd Power Electronics Specialists Conference, pp. 695-701, 1991.

[3]M. J. Thomas, “Motion Control with Permanent Magnet AC Machines”, Proceedings of the IEEE, Vol. 82, No. 8, pp. 1241-1252, August 1994.

[4]F. J. Lin and C. M. Liaw, “Control of Indirect Field-Oriented Induction Motor Drives Considering the Effects of Dead-Time and Parameter Variations”, IEEE Trans. on Industrial Electronics, Vol. 40, No. 5, pp. 486-495, October 1993.

[5]Q. P. Ha, M. Negnevitsky and F. Palis, “Cascade PI-Controllers with Fuzzy Tuning”, IEEE International Conference on Fuzzy Systems, Vol. 1, pp. 361-366, 1997.

[6]L. A. Zadeh, “Outline of a New Approach to the Analysis of Complex Systems and Decision Processes”, IEEE Trans. on Systems, Man, and Cybernetics, Vol. SMC-3, pp. 28-44, 1973.

[7]L. A. Zadeh, “Fuzzy Logic = Computing with Words”, IEEE Trans. on Fuzzy Systems, Vol. 4, No. 4, pp. 103-111, May 1996.

[8]S. Haykin, Neural Network A Comprehensive Foundation, N.J.: Prentice Hall, 1999.

[9]C. Y. Huang, C. T. Chen and C. L. Huang, “Robust Control of Induction Motor with A Neural-Network Load Torque Estimator and A Neural-Network Identification”, IEEE Trans. on Industrial Electronics, Vol. 46, No. 5, pp. 990-997, October 1999.

[10]T. T. Sheu, C. T. Chen and C. L. Huang, “Self-tuning Control of Induction Motor Drive Using Neural Network Identifier”, IEEE Trans. on Energy Conversion, Vol. 14, No. 4, pp. 881-886, December 1999.

[11]X. Cui and K. G. Shin, “Direct Control and Coordination Using Neural Network”, IEEE Trans. on Systems, Man, and Cybernetics, Vol. 23, No. 3, pp. 686-697, May/June 1993.

[12]C. C. Ku and K. Y. Lee, “Diagonal Recurrent Neural Networks for Dynamic System Control”, IEEE Trans. on Neural Networks, Vol. 6, No. 1, pp. 144-156, January 1995.

[13]X. Liang, “Comments On “Diagonal Recurrent Neural Networks for Dynamic System Control”—Reproof of Theorems 2 and 4”, IEEE Trans. on Neural Networks, Vol. 8, No. 3, pp. 811-812, May 1997.

[14]G. A. Rovithakis and M. A. Christodoulou, “Adaptive Control of Unknown Plants Using Dynamical Neural Networks”, IEEE Trans. on Systems, Man, and Cybernetics, Vol. 24, No. 3, pp. 400-412, March 1994.

[15]J. Nie and D. A. Linkens, “Learning Control Using Fuzzified Self-Organizing Radial Basis Function Network”, IEEE Trans. on Fuzzy Systems, Vol. 1, No. 4, pp. 280-287, November 1993.

[16]Y. Y. Chen, K. Z. Lin and S. T. Hsu, “A Self-Learning Fuzzy Controller”, IEEE International Conference on Fuzzy Systems, pp. 189-196, February 1992.

[17]J. S. R. Jang, “Self-Learning Fuzzy Controllers Based on Temporal Back Propagation”, IEEE Trans. on Neural Networks, Vol. 3, No.5, pp. 714-723, September 1992.

[18]I. Rojas, H. Pomares, J. Ortega and A. Prieto, “Self-Organized Fuzzy System Generation from Training Examples”, IEEE Trans. on Fuzzy Systems, Vol. 8, No. 1, pp. 23-36, February 2000.

[19]S. J. Huang and J. S. Lee, “ A Stable Self-Organizing Fuzzy Controller for Robotic Motion Control”, IEEE Trans. on Industrial Electronics, Vol. 47, No. 2, pp. 421-428, April 2000.

[20]C. T. Lin and C. S. G. Lee, “Neural-Network-Based Fuzzy Logic Control and Decision System”, IEEE Trans. on Computers, Vol. 40, No. 12, pp. 1320-1336, December 1991.

[21]Y. Diao and K. M. Passino, “Neural-Network-Based Fuzzy Logic Control and Decision System”, IEEE Trans. on Control Systems Technology, Vol. 40, No. 12, pp. 494-509, May 2001.

[22]H. X. Li and C. L. P. Chen, “The Equivalence Between Fuzzy Logic Systems and Feedforward Neural Networks”, IEEE Trans. on Neural Networks, Vol. 11, No. 2, pp. 356-365, March 2000.

[23]K. Kiguchi and T. Fukuda, “Intelligent Position/Force Controller for Industrial Robot Manipulators-Application of Fuzzy Neural Networks”, IEEE Trans. on Industrial Electronics, Vol. 44, No. 6, pp. 753-761, December 1997.

[24]F. J. Lin, R. J. Wai and S. L. Wang, “A Fuzzy Neural Network Controller for Parallel-Resonant Ultrasonic Motor Drive”, IEEE Trans. on Industrial Electronics, Vol. 45, No. 6, pp. 928-937, December 1998.

[25]Texas Instrument, TMS320C32 Floating-Point DSP Optimizing C Compiler User’s Guide, Rev. B, February 1995.

[26]Texas Instrument, TMS320C32 Floating-Point DSP Assembly Language Tools User’s Guide, Rev. B, February 1995.

[27]Loughborough Sound Images plc, PC/C32 Dos Software User Guide, Ver. 1.00, July 1995.

[28]Loughborough Sound Images plc, MPC View for PC/C32 User Manual, Ver. 1.01, August 1996.

[29]B. K. Bose, Power Electronics and AC Drives, Prentice-Hall, Englewood Cliffs, New Jersey, 1986.

[30]J. M. Mendel and G. C. Mouzouris, “Designing Fuzzy Logic Systems”, IEEE Trans. on Circuits and Systems-II: Analog and Digital Signal Processing, Vol. 44, No. 11, pp. 885-895, November 1997.

[31]L. X. Wang, A Course In Fuzzy Systems and Control, Prentice-Hall International, Inc., 1997.

[32]N. N. Karnik and J. M. Mendel, “Type-2 Fuzzy Logic Systems”, IEEE Trans. on Fuzzy Systems, Vol. 7, No. 6, pp. 643-658, December 1999.

[33]G. C. Mouzouris and J. M. Mendel, “Nosingleton Fuzzy Logic Systems: Theory and Application”, IEEE Trans. on Fuzzy Systems, Vol. 5, No. 1, pp. 56-71, February 1997.

[34]G. C. Mouzouris and J. M. Mendel, “Dynamic Non-Singleton Fuzzy Logic Systems for Nonlinear Modeling”, IEEE Trans. on Fuzzy Systems. Vol. 5, No. 2, pp. 199-208, May 1997.