永磁同步馬達因具備良好的暫態響應、高效率與高功率密度的特性，在自動化設備的場域有相當大的優勢。然而，當馬達的設計不良、操作者使用不當或處在高溫高電流環境，會使馬達發生故障。為了可即時監測永磁同步馬達之故障，本研究提出基於驅動器資訊的智能監測方法，利用磁場導向控制之物理量資訊與負載之資訊，監測馬達是否故障。本研究針對永磁同步馬達最具代表性的故障；永久磁鐵的退磁，進行模型的驗證。對於8 % 輕微退磁的馬達在變轉速、變扭矩的情況下仍具有0.97接受者操作特徵曲線下面積之監督正確性，驗證本研究提出之方法可以有效應用於永磁同步馬達的即時故障監測。

Permanent magnet synchronous motors have considerable advantages in the field of automation equipment due to their good transient response, high efficiency, and high-power density. However, when the motor is poorly designed, improperly used by the operator, or in a high temperature and high current environment, the motor can fail. In order to monitor the faults of permanent magnet synchronous motors in real time, this study proposes an intelligent monitoring method based on driver information, which uses the physical quantity information of magnetic field-oriented control and the information of the load to monitor whether the motor is faulty or not. In this study, the model is verified for the most reoccurring fault of the permanent magnet synchronous motor, which is the demagnetization of permanent magnet. For a motor with a slight demagnetization of 8 %, the supervisory accuracy of the area under the receiver operating characteristic curve is 0.97 under the condition of variable speed and variable torque. It is verified that the method proposed in this study can be effectively applied to the real-time fault monitoring of permanent magnet synchronous motors.

[1] Chen Y, Liang S, Li W, Liang H, Wang C. "Faults and Diagnosis Methods of Permanent Magnet Synchronous Motors: A Review," Applied Sciences. 2019.
[2] F. Caccavale and I. D. Walker, "Observer-based fault detection for robot manipulators," Proceedings of International Conference on Robotics and Automation, pp. 2881-2887 vol.4, 1997.
[3] B. Freyermuth, "An approach to model based fault diagnosis of industrial robots," Proceedings. 1991 IEEE International Conference on Robotics and Automation, pp. 1350-1356 vol.2, 1991.
[4] J. Rosero, J. Cusido, A. G. Espinosa, J. A. Ortega and L. Romeral, "Broken Bearings Fault Detection for a Permanent Magnet Synchronous Motor under non-constant working conditions by means of a Joint Time Frequency Analysis," 2007 IEEE International Symposium on Industrial Electronics, pp. 3415-3419, 2007.
[5] Z. A. Ping, Y. Juan and W. Ling, "Fault Detection of Stator Winding Interturn Short Circuit in PMSM Based on Wavelet Packet Analysis," 2013 Fifth International Conference on Measuring Technology and Mechatronics Automation, pp. 566-569, 2013.
[6] M. Zhu, W. Hu and N. C. Kar, "Acoustic Noise-Based Uniform Permanent-Magnet Demagnetization Detection in SPMSM for High-Performance PMSM Drive," IEEE Transactions on Transportation Electrification, vol. 4, no. 1, pp. 303-313, 2018.
[7] I. -H. Kao, W. -J. Wang, Y. -H. Lai and J. -W. Perng, "Analysis of Permanent Magnet Synchronous Motor Fault Diagnosis Based on Learning," in IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 2, pp. 310-324, Feb. 2019.
[8] 王舜弘,蔡明祺教授, "Unsupervised Demagnetization Fault Diagnosis in Permanent Magnet Synchronous Motors," 國立成功大學機械工程學系碩士論文, 2020.
[9] E. Principi, D. Rossetti, S. Squartini and F. Piazza, "Unsupervised electric motor fault detection by using deep autoencoders," in IEEE/CAA Journal of Automatica Sinica, vol. 6, no. 2, pp. 441-451, 2019.
[10] Z. Wang, J. Yang, H. Ye and W. Zhou, "A review of Permanent Magnet Synchronous Motor fault diagnosis," 2014 IEEE Conference and Expo Transportation Electrification Asia-Pacific (ITEC Asia-Pacific), 2014.
[11] Hao Tang, Rongxiang Zhao, Shengqing Tang and Zheng Zeng, "Control of three-phase PWM boost rectifiers in stationary frame using proportional-resonant controller," 2012 IEEE International Symposium on Industrial Electronics, pp. 270-274, 2012.
[12] Tzu-Yu Liu, C. -H. Chen, Wen-Chun Chi and M. -Y. Cheng, "Study on the current control loop of PMSM based on sinusoidal commutation," 2011 IEEE Ninth International Conference on Power Electronics and Drive Systems, pp. 670-675, 2011.
[13] 陳俊霖,謝易儒, "淺談交流馬達d-q 軸轉換," 國立成功大學馬達科技研究中心電子報750期, 2017.
[14] 江翊華,“以空拍機馬達為例探討反電動勢分析與量測,” 國立成功大學馬達科技研究中心電子報第783期, 2020.
[15] T. Jayalakshmi and A. Santhakumaran, "Statistical normalization and back propagation for classification, International Journal of Computer Theory and Engineering, vol.3, No.1, 2011.
[16] H. Li, J. Li, X. Guan, B. Liang, Y. Lai and X. Luo, "Research on Overfitting of Deep Learning," 2019 15th International Conference on Computational Intelligence and Security (CIS), pp. 78-81, 2019.
[17] N. Chowdhury and M. A. kashem, "A comparative analysis of Feed-forward neural network & Recurrent Neural network to detect intrusion," 2008 International Conference on Electrical and Computer Engineering, pp. 488-492, 2008.
[18] L. Mauch and B. Yang, "A new approach for supervised power disaggregation by using a deep recurrent LSTM network," 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 63-67, 2015.
[19] G. E. Hinton and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks, " Science, vol.313, no.5786, pp.504-507, 2006.
[20] O. I. Provotar, Y. M. Linder and M. M. Veres, "Unsupervised Anomaly Detection in Time Series Using LSTM-Based Autoencoders," 2019 IEEE International Conference on Advanced Trends in Information Theory (ATIT), pp. 513-517, 2019.
[21] P. Bholowalia and A.Kumar, "EBK-means: A clustering technique based on elbow and k-means in WSN," International Journal of Computer Applications, vol.105, no.9, pp.17-24, 2014.