近年來，永磁同步馬達因具備高效率及高功率密度的優勢，已逐漸成為民生用品以及工業設備中不可或缺的動力源。然而，當馬達的設計不當，造成磁通路徑不順；又抑或是操作者的不當使用，將馬達操作於過負載、高溫以及高電流的環境，造成馬達內的永久磁鐵產生不可逆的退磁現象，導致產線無預警的停擺，情況嚴重時，甚至會發生產線上的意外以致於造成工安上的疑慮。針對上述的問題，已有許多學者提出不同的解決方法。很多文獻需要額外裝設感測器並輔以監督式學習的方法來建立診斷系統，本論文提出一套不需額外裝設感測器之非監督式學習馬達退磁診斷方法，優勢在於僅需馬達驅動器資訊即可進行馬達退磁診斷，可有效縮減診斷系統之建置成本。本研究是經由三種不同退磁狀態的永磁同步馬達，分別為正常、輕度以及嚴重退磁故障的馬達來進行實驗，於涵蓋三種不同狀態的600筆測試資料裡，診斷系統的準確度高達96%，驗證本研究提出之方法可有效應用於永磁同步馬達的退磁故障診斷。

Permanent magnet synchronous motors are among the most important components of both consumer products and industrial equipment. Hence, fault diagnosis is a necessary task for PMSMs. In recent years, several approaches have been proposed for diagnosing demagnetization fault in PMSMs. However, those approaches usually need additional sensors and a supervised learning algorithm was often used to build the fault diagnostic model. In this study, an unsupervised PMSM demagnetization fault diagnosis method is proposed. Five different physics signals from the motor drive are used to train a model by the autoencoder and K-means clustering. In this research, the fault diagnosis of an PMSM is performed in three states, normal, mild demagnetization fault, and severe demagnetization fault. The experimental results indicate that the proposed method is feasible for diagnosing demagnetization fault in PMSMs. The proposed method has 96% accuracy to recognize the demagnetization situation of motors.

[1] A. G. Espinosa, J. A. Rosero, J. Cusido, L. Romeral, and J. A. Ortega, "Fault detection by means of Hilbert–Huang transform of the stator current in a PMSM with demagnetization," IEEE Transactions on Energy Conversion, vol. 25, no. 2, pp. 312-318, 2010.
[2] J. R. R. Ruiz, J. A. Rosero, A. G. Espinosa, and L. Romeral, "Detection of demagnetization faults in permanent-magnet synchronous motors under nonstationary conditions," IEEE Transactions on Magnetics, vol. 45, no. 7, pp. 2961-2969, 2009.
[3] D. Torregrossa, A. Khoobroo, and B. Fahimi, "Prediction of acoustic noise and torque pulsation in PM synchronous machines with static eccentricity and partial demagnetization using field reconstruction method," IEEE Transactions on Industrial Electronics, vol. 59, no. 2, pp. 934-944, 2011.
[4] 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, 2017.
[5] I. H. Kao, W. J. Wang, Y. H. Lai, and J. W. Perng, "Analysis of permanent magnet synchronous motor fault diagnosis based on learning," IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 2, pp. 310-324, 2019.
[6] L. Maraaba, Z. Al-Hamouz, and M. Abido, "An efficient stator inter-turn fault diagnosis tool for induction motors," Energies, vol. 11, no. 3, pp. 653, 2018.
[7] H. Liang, Y. Chen, S. Liang, and C. Wang, "Fault detection of stator inter-turn short-circuit in PMSM on stator current and vibration signal," Applied Sciences, vol. 8, no. 9, pp. 1677, 2018.
[8] S. Liang, Y. Chen, H. Liang, and X. Li, "Sparse Representation and SVM Diagnosis Method for Inter-Turn Short-Circuit Fault in PMSM," Applied Sciences, vol. 9, no. 2, pp. 224, 2019
[9] D. Zhen, Z. Wang, H. Li, H. Zhang, J. Yang, and F. Gu, "An Improved Cyclic Modulation Spectral Analysis Based on the CWT and Its Application on Broken Rotor Bar Fault Diagnosis for Induction Motors," Applied Sciences, vol. 9, no. 18, pp. 3902, 2019.
[10] J. Burriel-Valencia, R. Puche-Panadero, J. Martinez-Roman, A. Sapena-Bano, M. Pineda-Sanchez, J. Perez-Cruz, and M. Riera-Guasp, "Automatic fault diagnostic system for induction motors under transient regime optimized with expert systems," Electronics, vol. 8, no. 1, pp. 6, 2019.
[11] Y.-M. Hsueh, V. R. Ittangihal, W.-B. Wu, H.-C. Chang, and C.-C. Kuo, "Fault Diagnosis System for Induction Motors by CNN Using Empirical Wavelet Transform," Symmetry, vol. 11, no. 10, pp. 1212, 2019.
[12] Y.-M. Hsueh, V. R. Ittangihala, W.-B. Wu, H.-C. Chang, and C.-C. Kuo, "Condition Monitor System for Rotation Machine by CNN with Recurrence Plot," Energies, vol. 12, no. 17, pp. 3221, 2019.
[13] J.-H. Lee, J.-H. Pack, and I.-S. Lee, "Fault Diagnosis of Induction Motor Using Convolutional Neural Network," Applied Sciences, vol. 9, no. 15, pp. 2950, 2019.
[14] M. E. Iglesias-Martínez, J. A. Antonino-Daviu, P. Fernández de Córdoba, and J. A. Conejero, "Rotor Fault Detection in Induction Motors Based on Time-Frequency Analysis Using the Bispectrum and the Autocovariance of Stray Flux Signals," Energies, vol. 12, no. 4, pp. 597, 2019.
[15] A. Mejia-Barron, J. J. de Santiago-Perez, D. Granados-Lieberman, J. P. Amezquita-Sanchez, and M. Valtierra-Rodriguez, "Shannon Entropy Index and a Fuzzy Logic System for the Assessment of Stator Winding Short-Circuit Faults in Induction Motors," Electronics, vol. 8, no. 1, pp. 90, 2019
[16] J. Burriel-Valencia, R. Puche-Panadero, J. Martinez-Roman, A. Sapena-Bano, and M. Pineda-Sanchez, "Fault Diagnosis of Induction Machines in a Transient Regime Using Current Sensors with an Optimized Slepian Window," Sensors, vol. 18, no. 1, pp. 146, 2018.
[17] I.-H. Kao, W.-J. Wang, Y.-H. Lai, and J.-W. Perng, "Analysis of permanent magnet synchronous motor fault diagnosis based on learning," IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 2, pp. 310-324, 2018.
[18] M. Skowron, M. Wolkiewicz, T. Orlowska-Kowalska, and C. T. Kowalski, "Effectiveness of Selected Neural Network Structures Based on Axial Flux Analysis in Stator and Rotor Winding Incipient Fault Detection of Inverter-fed Induction Motors," Energies, vol. 12, no. 12, pp. 2392, 2019.
[19] M. Dybkowski and K. Klimkowski, "Artificial Neural Network Application for Current Sensors Fault Detection in the Vector Controlled Induction Motor Drive," Sensors, vol. 19, no. 3, pp. 571, 2019.
[20] S. Zolfaghari, S. B. M. Noor, M. Rezazadeh Mehrjou, M. H. Marhaban, and N. Mariun, "Broken rotor bar fault detection and classification using wavelet packet signature analysis based on fourier transform and multi-layer perceptron neural network," Applied Sciences, vol. 8, no. 1, pp. 25, 2018.
[21] T. Jayalakshmi and A. Santhakumaran, "Statistical normalization and back propagation for classification," International Journal of Computer Theory and Engineering, vol. 3, no. 1, pp. 1793-8201, 2011.
[22] G. E. Hinton and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, vol. 313, no. 5786, pp. 504-507, 2006.
[23] L. I. Nwankwo, "A least squares plane surface polynomial fit of two dimensional potential field geophysical data using matlab," Nigerian Journal of Pure and Applied Sciences, vol. 21, pp. 2006-2013, 2006.
[24] A. K. Jain, M. N. Murty, and P. J. Flynn, "Data clustering: a review," ACM Computing Surveys, vol. 31, no. 3, pp. 264-323, 1999.
[25] S. Chattopadhyay, M. Mitra, and S. Sengupta, Electric Power Quality, Springer, 2011, pp. 89-96.
[26] P. Bholowalia and A. Kumar, "EBK-means: A clustering technique based on elbow method and k-means in WSN," International Journal of Computer Applications, vol. 105, no. 9, pp.17-24, 2014.