現今馬達廣泛應用於不同類型之工業領域，是不可缺少的設備之一。但馬達發生故障時，會導致巨大的財物損失。本論文主要透過不同特徵及分類器來探討三相感應馬達軸承故障診斷系統辨識率。實驗以一個15瓩三相感應馬達作為實驗對象，設計五種不同軸承狀態，包含健康及四種故障類別。利用主成分分析法及獨立成分分析法特徵選取，並且使用支持向量機及類神經網路來辨識不同的故障。透過不同特徵與分類器間交叉比對並找出辨識率最高的方法，實驗結果顯示透過主成分分析法與類神經網路的方式可使系統擁有最佳辨識率，其三軸辨識率最高可達97.33%。

Nowadays, induction motors have been used to different types of industry applications in factory. And motors are indispensable equipment in our life. When motors are out of work, it will bring us huge financial lost. This thesis mainly explores the recognition rate of three-phase induction motor bearing fault diagnosis system through different features and classifiers. A 15kW three-phase induction motor is used as the experimental object. And, five different bearing states are designed, including health and four fault conditions. Features are selected through principal component analysis and independent component analysis. Support vector machines and neural networks are used to identify different faults. The highest recognition rat can be founded out through the cross comparison of different features and classifiers. The experimental results show that the system have the best recognition rate through the principal component analysis method and the neural network, and the maximum recognition rate of the three axes can reach 97.33%.

[1] M. E. H. Benbouzid, "A review of induction motors signature analysis as a medium for faults detection," IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society, Aachen, Germany, pp. 1950-1955, 1998.
[2] A. Garcia-Perez, R. d. J. Romero-Troncoso, E. Cabal-Yepez, and R. A. Osornio-Rios, "The application of high-resolution spectral analysis for identifying multiple combined faults in induction motors," IEEE Transactions on Industrial Electronics, vol. 58, no. 5, pp. 2002-2010, 2011.
[3] Y. Li and H. Yu, "Three-phase induction motor operation trend prediction using support vector regression for condition-based maintenance," 2006 6th World Congress on Intelligent Control and Automation, Dalian, pp. 7878-7881, 2006.
[4] M. K. Rad, M. Torabizadeh, and A. Noshadi, "Artificial neural network-based fault diagnostics of an electric motor using vibration monitoring," Proceedings 2011 International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE), Changchun, pp. 1512-1516, 2011.
[5] S. Ignat, E. Stancel, and I. Stoian, "Support for condition based maintenance Operating equipment performances monitoring, " Proceedings of 2012 IEEE International Conference on Automation, Quality and Testing, Robotics, Cluj-Napoca, pp. 234-239, 2012.
[6] A. Rastegari and M. Bengtsson, "Implementation of condition based maintenance in manufacturing industry - a pilot case study," 2014 International Conference on Prognostics and Health Management, pp. 1-8, 2014.
[7] K. S. Gaeid , H. W. Ping , M. Khalid , and A. L. Salih , "Fault diagnosis of induction motor using MCSA and FFT," Electrical and Electronic Engineering, Vol. 1 No. 2, pp. 85-92, 2011.
[8] J. Sripriya and E. S. Samundeeswari, "Comparison of neural networks and support vector machines using PCA and ICA for feature reduction," Int. J. Comput , pp. 31-36, 2012.
[9] S. Zhang, S. Zhang, B. Wang, and T. G. Habetler, "Machine learning and deep learning algorithms for bearing fault diagnostics-a comprehensive review," arXiv preprint arXiv:1901.08247, 2019.
[10] K. K. Vasan and B. Surendiran, "Dimensionality reduction using principal component analysis for network intrusion detection, " Perspectives in Science , pp. 510-512, 2016.
[11] L. J. Cao, K. S. Chua, W. K. Chong, H. P. Lee, and Q. M. Gu, "A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine," Neurocomputing, pp. 321-336, 2003.
[12] A. Bouzalmat, J. Kharroubi, and A. Zarghili, "Comparative study of PCA, ICA, LDA using SVM classifier," Journal of Emerging Technologies in Web Intelligence, pp. 64-68, 2014.
[13] M. S. Reza and J. Ma, "ICA and PCA integrated feature extraction for classification," 2016 IEEE 13th International Conference on Signal Processing (ICSP), pp. 1083-1088, 2016.
[14] C. M. Chao, Y. W. Yu, B. W. Cheng, and Y. L. Kuo, "Construction the model on the breast cancer survival analysis use support vector machine, logistic regression and decision tree," Journal of medical systems, 2014.
[15] Z. Wang, "Fast algorithms for the discrete W transform and for the discrete Fourier transform," IEEE Transactions on Acoustics, Speech, and Signal Processing, pp. 803-816, 1984.
[16] D. Kolba and T. Parks, "A prime factor FFT algorithm using high-speed convolution," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 25, no. 4, pp. 281-294, 1977.
[17] R. Preuss, "Very fast computation of the radix-2 discrete Fourier transform," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 30, no. 4, pp. 595-607, 1982.
[18] J. W. Cooley and J. W. Tukey, "An algorithm for the machine calculation of complex Fourier series," Mathematics of computation, pp. 297-301, 1965.
[19] J. M. Cimbala, "Fourier transforms, DFTs, and FFTs," Fourier Transforms, pp.1, 2010
[20] K. J. Xu, "Signal analysis and process," Tsinghua University, Taiwan, 2006.
[21] B. A. Olshausen, " Aliasing, " PSC 129: Sensory Processes, 2000.
[22] Y. C. Du, W. C. Hu, and L. Y. Shyu, "The effect of data reduction by independent component analysis and principal component analysis in hand motion identification," The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 84-86, 2004.
[23] S. Hussain, N. Z. Quazilbash, S. Bai, and S. Khoja, "Reduction of variables for predicting breast cancer survivability using principal component analysis," 2015 IEEE 28th International Symposium on Computer-Based Medical Systems, Sao Carlos, pp. 131-134, 2015.
[24] M. Waqar, H. Dawood, P. Guo, M. B. Shahnawaz, and M. A. Ghazanfar, "Prediction of stock market by principal component analysis," 2017 13th International Conference on Computational Intelligence and Security (CIS), Hong Kong, pp. 599-602, 2017.
[25] Y. Zhou, S. Cao, D. Wen, H. Zhang, and L. Zhao, "The study of face recognition based on hybrid principal components analysis and independent component analysis," 2011 International Conference on Electronics, Communications and Control (ICECC), Ningbo, pp. 2964-2966, 2011.
[26] I. T. Jolliffe, "Principal component analysis, " Springer-Verlag New York, Inc., 2ed, 2002.
[27] N. Kwak, C. H. Choi, and J. Y. Choi, "Feature extraction using ICA," International Conference on Artificial Neural Networks, pp. 568-573, 2001.
[28] I. Guney, E. Kilic, O. Ozgonenel, M. Ulutas, and E. Karadeniz, "Fault detection in induction motors with independent component analysis (ICA)," 2009 IEEE Bucharest PowerTech, Bucharest, pp. 1-4, 2009.
[29] J. E. Garcia-Bracamonte, J. M. Ramirez-Cortes, J. de Jesus Rangel-Magdaleno, P. Gomez-Gil, H. Peregrina-Barreto, and V. Alarcon-Aquino, "An approach on MCSA-based fault detection using independent component analysis and neural networks," IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 5, pp. 1353-1361, 2019.
[30] J. E. Garcia-Bracamonte, J. Rangel-Magdaleno, J. M. Ramirez-Cortes, P. Gomez-Gil, and H. Peregrina-Barreto, "Induction motors fault detection using independent component analysis on phase current signals," 2018 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Houston, pp. 1-6, 2018.
[31] Q. Miao, D. Wang, and M. Pecht, "Rolling element bearing fault feature extraction using EMD-based independent component analysis," 2011 IEEE Conference on Prognostics and Health Management, Montreal, pp. 1-6, 2011.
[32] Z. Wang, C. S. Chang, X. German, and W. W. Tan, "Online fault detection of induction motors using independent component analysis and fuzzy neural network," 8th International Conference on Advances in Power System Control, Operation and Management (APSCOM 2009), Hong Kong, China, pp. 1-6, 2009.
[33] C.W. Chang, T.H. Sun, and C.Y. Cheng, " Using data mining methods for constructing the prognosis model of the breast cancer," Indurstrial Engineering and Management Chaoyang University of Technology, 2010.
[34] S. S. Haykin, S. S. Haykin, S. S. Haykin, K. Elektroingenieur, and S. S. Haykin, " Neural networks and learning machines, " Pearson education Upper Saddle River, 2009.
[35] Y. Liu, R. Wang, and Y.-S. Zeng, "An improvement of one-against-one method for multi-class support vector machine, " 2007 International Conference on Machine Learning and Cybernetics, vol. 5, pp. 2915-2920, 2007.
[36] W.-M. Lin, C.-H. Wu, C.-H. Lin, and F.-S. Cheng, "Detection and classification of multiple power-quality disturbances with wavelet multiclass SVM," IEEE transactions on power delivery, vol. 23, no. 4, pp. 2575-2582, 2008.
[37] Lu Shuang and Li Meng, "Bearing fault diagnosis based on PCA and SVM," 2007 International Conference on Mechatronics and Automation, Harbin, pp. 3503-3507, 2007.
[38] L. Meng, W. Miao, and W. Chunguang, "Research on SVM classification performance in rolling bearing diagnosis," 2010 International Conference on Intelligent Computation Technology and Automation, Changsha, pp. 132-135, 2010.
[39] S. Zgarni and A. Braham, "Classification of bearing fault detection using multiclass SVM: a comparative study," 2018 15th International Multi-Conference on Systems, Signals & Devices (SSD), Hammamet, pp. 888-892, 2018.
[40] M. Li and P. Zhao, "The application of wavelet packet and SVM in rolling bearing fault diagnosis," 2008 IEEE International Conference on Mechatronics and Automation, Takamatsu, pp. 505-508, 2008.
[41] B. Li, M. Y. Chow, Y. Tipsuwan, and J. C. Hung, "Neural-network-based motor rolling bearing fault diagnosis," IEEE Transactions on Industrial Electronics, vol. 47, no. 5, pp. 1060-1069, 2000.
[42] M. A. Awadallah and M. M. Morcos, "Application of AI tools in fault diagnosis of electrical machines and drives-an overview," IEEE Transactions on Energy Conversion, vol. 18, no. 2, pp. 245-251, 2003.
[43] Z. Ye, B. Wu, and A. R. Sadeghian, "Induction motor mechanical fault online diagnosis with the application of artificial neural network," APEC 2001. Sixteenth Annual IEEE Applied Power Electronics Conference and Exposition, vol. 2, pp. 1015-1021, 2001.
[44] Wikipedia contributors, " Neuron," Wikipedia, 2019
[45] Wikipedia contributors, "Artificial neural network," Wikipedia, 2019
[46] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," Cognitive modeling, 1988.
[47] J. M. Syu and J. F. Chen, "Diagnosis system of bearing fault for three phase induction motor based on support vector machine," master of science, Department of Electrical Engineering, National Cheng Kung University, 2015.
[48] Y. P. Cheng and J. F. Chen, "Fault diagnosis system for three phase induction motor based on back propagation neural network," master of science, Department of Electrical Engineering, National Cheng Kung University, 2018.