永磁同步馬達的發展與應用愈來愈廣泛，然而不應只注重於效能的提升，馬達故障檢測也是一大重要環節。在需長時間穩定運作的應用場合下，如航空、冷凍空調系統等，其馬達的損壞可能導致整個系統設備停擺，故須建立預防性故障檢測系統。本文以馬達數學模型化與磁場導向控制(FOC)之基礎下，分析永磁同步馬達線間短路故障特徵，再將故障程度分級，建立模型知識庫結合支援向量機(Support Vector Machine, SVM)進行分類。本文方法將從驅動器中獲取已具備電壓、電流特徵資訊外，相較於須大量數據為基底之檢測法，更能減少額外電腦設備成本。另一特點為能於初期發現微小故障，並且將故障程度分級，如此一來便能掌握馬達堪用狀況，判別是否需要立即檢修，降低成本損失。本文利用ANSYS Maxwell®軟體之⸢等效電路提取⸥ (ECE)功能，提取設計後之永磁同步馬達故障有限元素模型，並匯入硬體在線迴路(Hardware in the loop)取得健康與線間短路故障真實數據，建立訓練學習模型，進行未標籤馬達之健康狀況檢測。

This thesis applies machine learning to develop a detection system for inter-turn short-circuit (ITSC) fault for permanent magnet synchronous motor (PMSM). Under the circumstances that demand long-term and consistent operation such as aviation, air conditioning system, etc., motor failure may result in malfunction of whole systems. In such cases, it is necessary to build up a fault detection system. Based on the construction of ITSC faults mathematical model, this thesis analyzes the fault characteristics with which the training model can be built and the support vector machine (SVM) is employed to classify the faults. In this method, the fault features of motor controlling signals can be obtained directly from the driver, and also the cost of computer equipment can be reduced in comparison with those data-driven detection, which requires a large amount of data. Moreover, the minor faults can be detected at early stage and be classified to the faults levels so that the use condition of the motor can be monitored and the motor will be identified whether it is usable or not. This thesis employs the equivalent circuit extraction (ECE) of ANSYS Maxwell® to extract the models in different fault levels of finite element analysis and imports them into the hardware in the loop (HIL) to get the real data. Finally, the results of classification are verified according to the accuracy testing of unlabeled motors.

[1] R. Radenbaugh (2004). "Refrigeration for superconductors," In Proceedings of the IEEE, vol. 92, no. 10, pp. 1719-1734.
[2] 范家瑞,陳浩瑋,黃振瑋,王建昌 (2017)。高速高功率永磁馬達驅動與節能關鍵技術開發和應用(第四期)，臺灣能源期刊。
[3] P. O'Donnell (1985). "Report of Large Motor Reliability Survey of Industrial and Commercial Installations Part I," IEEE Transactions on Industry Applications, vol. 21, no. 4, pp.5-7.
[4] S.Karmakar, S.Chattopadhyay, M.Mitra, S.Sengupta (2016).《Induction motor fault diagnosis: Approach through Current Signature Analysis》, Springer Singapore.
[5] M. Eftekhari, M. Moallem, S. Sadri, M. F. Hsieh (2014). "Online Detection of Induction Motor’s Stator Winding Short-Circuit Faults," IEEE Systems Journal, vol. 8, no. 4, pp.566-570.
[6] B. Vaseghi, B. N. Mobarakeh, N. Takorabet, F. M. Tabar (2007). "Modeling of Non-Salient PM Synchronous Machines under Stator Winding Inter-turn Fault Condition: Dynamic Model - FEM Model," IEEE Vehicle Power and Propulsion Conference (VPPC), pp. 635-640.
[7] C. Lai, A. Balamurali, V. Bousaba, K. L. V. Iyer, N. Kar (2014). "Analysis of Stator Winding Inter-Turn Short Circuit Fault in Interior and Surface Mounted Permanent Magnet Traction Machines," Proc. IEEE Transportation Electrification Conference (ITEC), pp. 1-5.
[8] G. E. Gouda, N. S. Jyothi (2017). "Analysis and Co-Simulation of BLDC Motor Drive with Fault Detection by FEA Method," IJSRD - International Journal for Scientific Research & Development, vol. 5, no. 6, pp.57-66.
[9] S. M. A. Cruz, A. J. M. Cardoso (2001). "Stator winding fault diagnosis in three-phase synchronous and asynchronous motors by the extended Park's vector approach," IEEE Transactions on Industry Applications, vol. 37, no. 5, pp. 1227-1233.
[10] S. Bouslimani, S. Drid, L. Chrifi-Alaoui, P. Bussy, M. Hamzaoui (2016). "Inter-turn faults detection using Park vector strategy," In Proceedings of the 2016 17th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA), pp. 244-248.
[11] B. M. Ebrahimi, J. Faiz, M. J. Roshtkhari (2009). "Static- dynamic- and mixed-eccentricity fault diagnoses in permanent-magnet synchronous motors," IEEE Transactions on Industry Electron, vol. 56, no. 11, pp. 4727-4739.
[12] B. M. Ebrahimi, J. Faiz, B. N. Araabi (2010). "Pattern identification for eccentricity fault diagnosis in permanent magnet synchronous motors using stator current monitoring," IET Electric Power Applications, vol. 4, no. 6, pp. 418-430.
[13] H. Cherif, A. Menacer, B. Bessam, R. Kechida (2015). "Stator inter turns fault detection using discrete wavelet transform," 2015 IEEE 10th International Symposium on Diagnostics for Electrical Machines Power Electronics and Drives (SDEMPED), vol. 55, no. 2, pp. 138-142.
[14] O. A. Mohammed, N. Y. Abed, S. Ganu (2006). "Modeling and characterization of induction motor internal faults using finite-element and discrete wavelet transforms," IEEE Transactions on Magnetics, vol. 42, no. 10, pp. 3434-3436.
[15] R. Kechida, A. Menacer, H. Talhaoui (2015). "Discrete wavelet transform for stator fault detection in induction motors," 2015 IEEE 10th International Symposium on Diagnostics for Electrical Machines Power Electronics and Drives (SDEMPED), pp. 104-109.
[16] J. A. Rosero, L. Romeral, J. A. Ortega, and E. Rosero (2009). "Short-Circuit Detection by Means of Empirical Mode Decomposition and Wigner–Ville Distribution for PMSM Running Under Dynamic Condition, " IEEE Transactions on Industry Electron, vol. 56, no. 11, pp. 4534-4547.
[17] C. Wang, X. Liu, and Z. Chen (2014). "Incipient Stator Insulation Fault Detection of Permanent Magnet Synchronous Wind Generators Based on Hilbert Huang Transformation," IEEE Transactions on Magnetics, vol. 50, no. 11, pp. 1-4.
[18] H. Nejjari, M. E. H. Benbouzid (2000). "Monitoring and Diagnosis of Induction Motors Electrical Faults Using a Current Park’s Vector Pattern Learning Approach," IEEE Transactions on Industry Applications, vol. 36, no. 3, pp. 275-277.
[19] V. P. Mini, S. Sivakottiah, S. Ushakumari (2010). "Fault Detection and Diagnosis an Induction Motor using Fuzzy Logic," Proceedings of the IEEE Region 8 International Conference on Computational Technologies in Elect and Electronics Engineering (SIBIRCON), pp. 459-464.
[20] K. Yu, F. Yang, H. Guo, J. Xu (2010). "Fault diagnosis and location of brushless DC motor system based on wavelet transform and artificial neural network," International Conference on Electrical Machines and Systems (ICEMS), pp. 1048-1052.
[21] J. Yang, M. Dou, Z. Dai, D. Zhao, and Z. Zhang (2016). "Modeling and fault diagnosis of inter-turn short circuit for five-phase PMSM based on Particle Swarm Optimization," IEEE Applied Power Electronics Conference and Exposition (APEC), pp. 3134-3139.
[22] T. H. Nguyen (2016). "Design of 10kW Interior Permanent Magnet Motor for EV Traction," National Cheng Kung University Master Thesis.
[23] M. Zafarani, E. Bostanci, T. Goktas, B. Akin (2018). "Inter-turn Short Circuit Faults in Permanent Magnet Synchronous Machines: An Extended Review and Comprehensive Analysis," IEEE Journal of Emerging and Selected Topics in Power Electronics, vol. 6, no. 4, pp. 1-1.
[24] C. Cortes, V. Vapnik (1995). "Support-Vector Networks," Machine Learning, vol. 20, no. 3, pp. 273-297.
[25] 黃瑞堯 (2010)。以核支持向量機為架構的影像分析應用，國立成功大學碩士論文。
[26] D. P. Bertsekas (1982).《Constrained Optimization and Lagrange Multiplier Methods》, Academic Press.
[27] K. Muller, S. Mika, G. Riitsch, K. Tsuda and B. Scholkopf (2001). "An introduction to kernel-based learning algorithms," IEEE Transactions on Neural Networks, vol. 12, no. 2, pp. 181-201.