感應馬達之系統參數會隨操作環境的不同而產生參數漂移的現象。 在無速度感測器
控制的相關研究中, 轉子電阻漂移多為溫度的改變、 低轉速的控制, 亦或是加入負載的
情況尤為嚴重, 也因此參數的估測尤其受到重視。 主要原因在於轉子電阻的變化, 對於
轉速及磁通估測值會造成很大的誤差, 進而使閉迴路控制性能降低。 因此在無感測器控
制架構下, 控制系統對於估測器的仰賴程度相當高。
以類神經網路 (Artifical Neural Network, ANN) 為基礎所發展之估測器因具有
模擬人類大腦學習能力可做離線和線上即時估測參數, 且相較於一般估測器不需依賴模
型參數來控制, 因此在無感測器控制議題上廣泛的被採用。 然而先前的文獻中, 以類神
經網路為基礎之估測器多以離線的方式調整估測器, 而線上的估測器在低轉且加上負載
的情況效果又不佳。 針對此問題, 本論文以類神經網路之小腦模型控制器 (Cerebellar
Model Adaptive Controller, CMAC) 和適應線性元件 (Adaptive Linear Element,
ADALINE) 為基礎, 發展出可以同時估測轉速和轉子電阻的複合型類神經網路 (Hy-
brid Artifical Neural Network, HANN)。 此估測器藉由線上估測轉子電阻, 將參數
回授到磁通估測器, 藉此改善在低轉和負載下磁通估測的誤差, 進而改善速度估測之效
果。 本論文也以模糊控制器 (Fuzzy Controller) 和速度-積分控制器 (Proportional -
Integral Controller, PI) 為基礎, 發展出一混和型模糊-速度積分控制器 (Fuzzy - PI
controller) 來做為感應馬達的速度控制器, 結合模糊控制器和速度積分控制器的優點,
來得到與傳統控制器相較下更為精準且靈活的控制器。

The performance of sensorless control of induction motors (IMs) is dramat-
ically affected by the variation of parameters such as rotor resistance especially
at low speeds and heavy loads. A novel hybrid artificial neural network (HANN),
including a cerebellar model adaptive controller (CMAC) and an adaptive linear
element (ADALINE), is developed in this thesis to estimate the rotor resistance
and the motor speed simultaneously. On the other hand, a self-tuning PI-type
fuzzy logic controller (FLC) is used to achieve motor speed control based on the
speed estimate. Experimental results show that the proposed sensorless speed con-
trol strategy achieves accurate speed control even at low speed and under loaded
conditions.

[1] 李育和, 「具速度估測及短路防止時間補償之數位變頻器」, 國立中山大學電機工程學系, 碩士論文
(2002).
[2] 李義政, 「基於 Windows CE.NET 環境之感應馬達速度控制系統之研製」, 國立臺灣科技大學電機
工程學系, 碩士論文 (2005).
[3] 林志宇, 「以 FPGA 實現永磁同步馬達速度控制器設計與製作」, 國立台灣科技大學電機工程學系,
碩士論文 (2015).
[4] 林奉機, 「基於類神經網路之永磁同步馬達滑動模式無感測控制」, 南臺科技大學電機工程學系, 碩士
論文 (2014).
[5] 張維然, 「向量控制感應馬達的模糊控制器之研究」, 中正理工學院電子工程學系, 碩士論文 (1999).
[6] 陳伯峰, 「改良型磁通估測器應用於無轉速感測器的感應馬達純量控制系統之研製」, 崑山科技大學
電機工程學系, 碩士論文 (2006).
[7] 黃仲欽, 「電機機械理論」, 課程講義,2010.
[8] 黃欽彥, 「直接轉矩控制系統之模糊小腦模型定子電阻估測器設計」, 國立台北科技大學電機工程學
系, 碩士論文 (2010).
[9] 劉昌煥 主編, 「電機機械」, 東華書局,2002.
[10] 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,2008.
[11] 謝文政, 「切換式磁阻馬達智慧型驅動系統之研製」, 國立台北科技大學電機工程學系, 碩士論文
(2005).
[12] 藍健倫, 「以單一霍爾感測器實現永慈同步馬達向量控制」, 國立台灣科技大學電機工程學系, 碩士論
文 (2011).
[13] T. Instruments, Digital Motor Control.
Texas Instruments, 2013.
[14] K. S. Tze-Fun Chan, Applied Intelligent Control of Induction Motor Drives.
Wiley-IEEE
Press, 2011.
[15] A. A. E.-S. Mostafa I. Marei, Mostafa F. Shaaban, “A speed estimation unit for induction
motors based on adaptive linear combiner,” Energy Conversion and Management, vol. 50,
pp. 1664 – 1670, July 2009.
[16] E. A. R.-A. Jose M. Gutierrez-Villalobos, Juvenal Rodriguez-Resendiz and M. A. Martinez-
Hernandez, “Sensorless foc performance improved with on-line speed and rotor resistance
estimator based on an artificial neural network for an induction motor drive,” Sensors 2015,
vol. 15, pp. 15311–15325, June 2015.
[17] S. Williamson and R. C. Healey, “Space vector representation of advanced motor models
for vector controlled induction motors,” IEE Proc. Electr. Power Appl., vol. 143, pp. 69–77,
January 1996.
[18] T. I. Europe, Sensorless Control with Kalman Filter on TMS320 Fixed-Point DSP, 1997.
[19] Z. J. Deng Xin, L. Hui, and W. Qingyi, “Design of mras-based observer in speed sen-
sorless induction motor drive,” IEEE Conference on Industrial Electronics and Applica-
tions,ICIEA, pp. 3585 – 3590, May 2009.
[20] M. Dybkowski and T. Orlowska-Kowalska, “Application of the stator current-based mras
speed estimator in the sensorless induction motor drive,” Power Electronics and Motion
Control Conference,EPE-PEMC, pp. 2306 – 2311, September 2008.
[21] H. M. Kojabadi, L. Chang, and R. Doraiswami, “A mras-based adaptive pseudoreduced-
order flux observer for sensorless induction motor drives,” IEEE Transactions on Power
Electronics, vol. 20, pp. 930–938, July 2005.
[22] K. Ohyama, G. Asher, and M. Sumner, “Low speed and regenerating operation of sensorless
vector control system of induction motor using observer gain tuning and high frequency
injection technique,” 13th European Conference on Power Electronics and Applications, 2
EPE ’09., pp. 1 – 8, September 2009.
[23] H. Zatocil, “Sensorless control of ac machines using high-frequency excitation,” 13th Inter-
national Power Electronics and Motion Control Conference,EPE-PEMC 2008., pp. 1024 –
1032, September 2008.
[24] H. Kiyotake, K. Shinohara, K. Yamamoto, and D. Katoh, “Speed sensorless vector control
of induction motors utilizing slot harmonics caused by variation of inductance,” 4th IET
Conference on Power Electronics, Machines and Drives,PEMD 2008., pp. 722 – 726, July
2008.
[25] R. Raute, C. Caruana, C. S. Staines, J. Cilia, M. Sumner, and G. Asher, “Sensorless control
of induction machines by using pwm harmonics for rotor bar slotting detection,” Industry
Applications Society Annual Meeting,IAS’08. IEEE, pp. 1 – 8, October 2008.
[26] M. Barut, O. Bogosyan, and M. Gokasan, “Experimental evaluation of braided ekf for
sensorless control of induction motors,” IEEE Trans. On Industrial Electronics, vol. 55,
February 2008.
[27] Y. Zhang, Z. Zhao, T. Lu, and L. Yuan, “A comparative study of luenberger observer,
sliding mode observer and extended kalman filter for sensorless vector control of induction
motor drives,” Energy Conversion Congress and Exposition,2009, pp. 2466 – 2473, 2009.
[28] T. Orlowska-Kowalska, M. Dybkowski, and K. Szabat, “Adaptive neuro-fuzzy control of the
sensorless induction motor drive system,” 12th International Power Electronics and Motion
Control Conference,EPE-PEMC 2006., pp. 1836 – 1841, September 2006.
[29] M. Zerikat, S. Chekroun, and A. Mechernene, “Fuzzy-neural networks controller-based ada-
patation mechanism for mras sensorless induction motor drives,” 8th International Sym-
posium on Advanced Electromechanical Motion Systems and Electric Drives Joint Sympo-
sium,ELECTROMOTION 2009., pp. 1–7, July 2009.
[30] C. M. Lin and C. F. Hsu, “Recurrent-neural-network-based adaptive-backstepping con-
trol for induction servomotors,” TRANSACTIONS ON INDUSTRIAL ELECTRONICS,
vol. 52, pp. 1677–1684, DECEMBER 2005.
[31] M. Wlas, Z. Krzeminski, J. Guzinski, A. R. Haithem, and H. A. Toliyat, “Artificial-neural-
network-based sensorless nonlinear control of induction motors,” Transactions on Energy
Conversion, vol. 20, pp. 520–528, SEPTEMBER 2005.
[32] C. H. Tsai and H. C. Lu, “Observer-based speed estimation method for sensorless vector
control using aritficial neural network,” Electric Machines and Power systems, vol. 28, pp.
861–873, SEPTEMBER 2000.
[33] J. R. Heredia, F. P. Hidalgo, and J. L. D. Paz, “Sensorless control of induction motors by
artificial neural networks,” Transactions on Industrial Electronics, vol. 48, pp. 1038–1040,
OCTOBER 2001.
[34] B. Karanayil, M. F. Rahman, and C. Grantham, “Stator and rotor resistance observers
for induction motor drive using fuzzy logic and artificial neural networks,” Transactions on
Energy Conversion, vol. 20, pp. 771–780, DECEMBER 2005.
[35] J. O. Pinto, B. K. Bose, and L. E. B. da Silva, “A stator-flux-oriented vector-controlled
induction motor drive with space-vector pwm and flux-vector synthesis by neural networks,”
Transactions on Industry Applications, vol. 37, pp. 1308–1318, SEPTEMBER 2001.
[36] A. Ba-Razzouk, G. O. A. Cheriti, and P. Sicard, “Field-oriented control of induction motors
using neural-network decouplers,” Transactions on Power Electronics, vol. 12, pp. 752–763,
JULY 1997.
[37] H.-K. Liu, C.-H. Tsai, G. Olivier, and H.-C. Lu, “Cmac neural network application for
induction motor drives,” Systems, Man, and Cybernetics, vol. 10, pp. 2279 – 2284, OCTO-
BER 2011.