摘 要
本文為提出一可自調適之比例積分控制器，在轉子磁場導向向量控制架構下設計感應電動機轉速控制器。利用類神經網路進行識別受控體參數與估測負載轉矩，其識別方法採用遞迴最小平方演算法使識別出系統參數，最後將所識別出的的參數經極點安置法求出所需要的控制器參數，使控制器參數趨於最佳化。

在模擬方面採用MATLAB/SIMULINK軟體配合馬達模組，架構感應馬達向量控制與設計類神經網路比例積分控制器，硬體實現方面採用馬達控制驅動介面卡，經控制策略產生出脈波寬度調變訊號，將訊號送給後級放大器以調變出所需的電源給感應馬達，最後將模擬結果及實驗結果與傳統控制器做比較，以驗證其自調適控制器具有良好的響應與網路學習能力。

關鍵字：類神經網路、遞迴最小平方，自調適

Abstract
The purpose of this thesis is to design and investigate the application of the self-tuning PI controller under indirect rotor-flux-oriented induction motor driver. In this paper, the controller use neural network concepts to provide speed control of induction motor that is robust to both the dynamic changes in plant parameters and the introduction of load disturbances. This neural netwrok is two layer and uesd RLS(Recurisive Least-Squares) Algorithm to minimize the difference between the motor’s actural response and that predicted by the neural estimator, and use pole placement method to determination the controller parameter.
In the experimental setup, the control program is developed on the PC-Based motor controller development system, program coded in the MATLAB/SIMULINK are used for simulation and verification. The simulation and experimental results demonstrate that the neural network control attains good performances and have learning ability.

Keyword：Neural Network、Recurisive Least-Squares、Self-tuning

參考文獻
[1]F. Blaschke, “The principle of field-orientation as applied to the new Transvektor closed-loop control system for rotating-field machines,” Siemens Review 34, pp. 217-220, 1972.
[2]B. C. Kuo, Digital Control Systems. Philadelphia, PA: Saunders, 1992.
[3]何裕山，“比例積分微分控制器之原理與應用”，量測資訊，第41期，pp.76-85，1955。
[4]沈金鐘，“PID控制器理論、調整與實現”，滄海書局，民國九十年三月。
[5]熊京民、鍾博欽、張啟鴻，“以最陡坡降法做PID控制器的微調”，2003中華民國自動控制研討會，pp. 1955-1606，2003。
[6]劉昌煥，“交流電機控制：向量控制與直接轉矩控制原理”，東華書局，民國九十二年五月二版。
[7]蘇木春、張孝德，“機器學習：類神經網路、模糊系統以及基因演算法則”，全華科技圖書，民國八十八年。
[8]T. T. Sheu and T. C. Chen, “Self-tuning Control of Induction Motor Drive Using Neural Netwrok Identifier,” IEEE Trans. on Energy Conversion, vol. 14, no. 4, pp. 881-886, Dec., 1999.
[9]C. Y. Huang, T. C. 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 Electron., vol. 46, no. 5, pp. 990-998, Oct., 1999.
[10]T. C. Chen and T. T. Sheu, “Model Reference Robust Speed Control for Induction-Motor Drive with Time Delay Based on Neural Network,” IEEE Trans. on Systems, Man, and Cybernetics, vol. 31, no. 6, pp. 746-753, Nov., 2001.
[11]T. C. Chen and T. T. Sheu, “Model Reference Neural Network Controller for Induction Motor Speed Control,” IEEE Trans. on Energy Conversion, vol. 17, no. 2, pp. 157-163, June., 2002.
[12]Edwin K. P. Chong and Stanislaw H. Zak, An Introduction To Optimization. NY:Wiley-Interscience, 2001.
[13]蔡庚佑，“感應電動機速度控制器之設計與分析”碩士論文，國立台灣科技大學電機工程研究所，民國九十一年六月。
[14]王偉修、劉昌煥，“PC-Based馬達控制器即時發展系統”，微鋒自動科技發行，民國八十七年十二月。
[15]G. V. Puskorius and L. A. Feldkamp, “Neurocontrol of Nonlinear Dynamical Systems with Kalman Filter Trained Recurrent Networks,” IEEE Trans. on Neural Networks, vol. 5, no. 2, pp. 279-297, Mar., 1994.
[16]A. F. Stronach, P. Vas and P. Lees, “The application of self-tuning digital controllers in variable-speed drives,” Fifth Internation Conference. on Power Electronics and Variable-Speed Drives, pp.119-124, Oct., 1994.
[17]J. K. Ji and S. K. Sul, “DSP-based self-tuning IP speed controller with load torque compensation for rolling mill dc drive,” IEEE Trans. on Industrial Electron, vol. 42, no. 4, pp. 382-386, Aug., 1995.
[18]H. D. Patino, and D Liu, “Neural Network-Based Model Reference Adaptive Control System,” IEEE Trans. on Systems, Man, and Cybernetics-Part B, vol. 30,no. 1, pp. 198-204, Feb., 2000.
[19]K. S. Narendra and K. Parthasarathy, “Identification and Control of Dynamical Systems Using Neural Networks,” IEEE Trans on Neural Networks, vol. 1, no. 1, pp. 321-326, Mar., 2000.
[20]S. H. Kim, T. S. Park, J. Y. Yoo and G. T. Prak, “Speed-Sensorless Vector Control of an Induction Motor Using Nerual Netwrok Speed Estimation.” IEEE Trans. on Industrial Electronics, vol. 48, no. 3, pp. 609-614, June., 2001.
[21]W. S. Oh, B. K. Bose, K. M. Cho and H. J. Kim, “Self tuning neural network controller for induction motor drives,” IEEE 2002 28th Annual Conference. on Industrial Electronics Society, vol. 1, pp.152-156, Nov., 2002。
[22]G. C. Goodwin and K. S. Sin, Adaptive Filtering Prediction and Control. Englewood Cliffs, NJ: Prentice-Hall, 1984.
[23]K. J. Astrom and T. Hagglund, Automatic Tuning of PID Controllers, Instrument Society of America, 1988.
[24]陳世章，“以FPGA為基礎之感應馬達向量控制晶片研製”，碩士論文，國立臺灣科技大學電機工程研究所，民國九十二年六月。
[25]陳何各，“感應電動機之自調整模糊控制晶片設計”，碩士論文，國立臺灣科技大學電機工程研究所，民國九十二年六月。
[26]張智星，“MATLAB程式設計與應用”，清蔚科技發行，民國八十九年二月。