本論文主旨在於能利用一套診斷系統來辨識出三相感應電機轉子斷條故障。在此提出的方法首先利用音射感測器取得音射訊號，再透過小波轉換將信號分解成數個頻段的時域訊號，將這些時域訊號之特徵取出，利用主成份分析法將多種特徵作適當的維度選擇，最後基於K-鄰近演算法進行分析分類。本實驗擷取四種不同轉子斷條狀態下的音射訊號，所有資料將被分成兩組用來訓練及測試K-鄰近演算法機制，四種轉子斷條包含無缺陷及三種故障狀態；此分類器被用來辨識出無缺陷與三種故障型態，實驗及方法被用於一15瓩三相感應馬達上，實驗結果證明其辨識率可達80%，在轉子斷條故障診斷是可行的。

In this thesis, a fault diagnosis system is proposed to perform rotor bar fault detection in three-phase induction motor. Acoustic emission signals acquired from acoustic emission sensors are analyzed by the proposed method. These signals are decomposed into severel time domain data with different frequency bandwidths, features of the data are extracted, reduced to lower dimension by using principal component analysis (PCA) and classified by K-nearest neighbors algorithm.
A series of field test are performed in four rotor bar fault conditions, and all data are provided to train and then test classifiers. This K-nearest neighbors based classifier is then applied to distinguish healthy rotor bar from different fault conditions. The method is applied to a 15 kW three phase induction motor using different rotor bars with four conditions. Experimental results show the good agreement that 80% recognition rate is achieved and prove the feasibility to diagnosis rotor bars faults.

[1] M. Sahraoui, A. J. Marques Cardoso, and A. Ghoggal, “The Use of a Modified Prony Method to Track the Broken Rotor Bar Characteristic Frequencies and Amplitudes in Three-Phase Induction Motors,” IEEE Trans. on Industrial Applications, Vol. 51, No. 3, pp. 2136-2147, Feb. 2014.
[2] K. S. Gaeid, H. W. Ping, M. Khalid, and A. L. Salih, “Fault Diagnosis of Induction Motor Using MCSA and FFT,” IEEE International Conf. Industrial Engineering and Engineering Management, Singapore, Dec. 6-9, 2015, pp. 85-92.
[3] M. Nemec, K. Drobniˇc, D. Nedeljkovi´c, R. Fišer, and V. Ambrožiˇc, “Detection of Broken Bars in Induction Motor Through the Analysis of Supply Voltage Modulation,” IEEE Trans. on Industrial Applications, Vol. 57, No. 8, pp.2879-2888, Aug. 2010
[4] A. Singh, B. Grant, R. DeFour, C. Sharma, and S. Bahadoorsingh, “A Review of Induction Motor Fault Modeling,” IEEE Electric Power Systems Research, Vol. 133, Apr. 2016, pp. 191-197
[5] I. Kathir, S. Balakrishnan, and R. J. Bevila, “Fault Analysis of Induction Motor,” International Conf. Emerging Trends in Electrical and Computer Technology, Tamil Nadu, India, Mar. 23-24, 2011, pp. 476-479.
[6] I. Kathira, S. Balakrishnanb, and G. Sakthivelc, “Detection of Rotor Fault in an Induction Motor Under Standstill Condition-A Power Quality Perspective,” International Conf. on Advances in Engineering Science and Management, Nagapattinam, Tamil Nadu, Mar. 30-31, 2012, pp. 547-552.
[7] A. Ceban, R. Pusca, and R. Romary, “Study of Rotor Faults in Induction Motors Using External Magnetic Field Analysis” IEEE Trans. on Industrial Electronics, vol. 59, No.5, pp. 2082-2093, Jul. 2011.
[8] H. Jivajee and I. Culbert, “Detecting Broken Rotor Bars Prevents Catastrophic Damage,” [Online], Maintenance Technology, 2004, [cited May 18, 2016], available from the World Wide Web: < http://www.maintenancetechnology.com/2004/11/detecting-broken-rotor-bars-prevents-catastrophic-damage/ >.
[9] S. D. Ochoa and M. Pacas, “Detection of Rotor Asymmetries in Induction Motors at Standstill,” IEEE International Symposium on Industrial Electronics, Taipei, Taiwan, May 28-31, 2013, pp. 1-6
[10] Azima DLI, “Rotor Bar Monitoring via Motor Current Analysis,” [Online], Woburn, MA.: AZIMA|DLI, Inc., 2009, [cited May 15, 2016], available from the World Wide Web: < http://azimadli.com/vibman/rotorbarmonitoringviamotorcurrentanalysis.htm >.
[11] J. Atanasi, C. Jordi, E. A. García, O. J. Antonio, and R. Luis, “Double Frequency Test for Detecting Faults in Induction Machines” IEEE Conf. Industrial Electronics Society, North Carolina, USA, Nov. 6-10, 2005, pp. 1516-1521.
[12] David Cournapeau, “Decomposing Signals in Components (matrix factorization problems),” [Online], Scikit learn Machine Learning in python, 2009, [cited May 15, 2016], available from the World Wide Web: < http://scikit-learn.org/stable/modules/ decomposition.html >.
[13] W. Hereman, Wavelets: Theory and Applications An Introduction, 1nd ed., Gabor T. Herman, 2007.
[14] E. C. C. Lau and H. W. Ngan, “Detection of Motor Bearing Outer Raceway Defect by Wavelet Packet Transformed Motor Current Signature Analysis,” IEEE Trans. on Instumentation and Measurement, vol. 59, No. 10, pp.2683-2690. Oct. 2010
[15] V. L. Pham, and K. P. Wong, “Wavelet-transform-based algorithm for harmonic analysis of power system waveforms,” IEEE Proceedings Generation Trans. and Distribution, vol. 146, No. 3, pp. 249-254, May 1999.
[16] C. Valens, “A Really Friendly Guide to Wavelets,” 1999
[17] P. Klapetek and I. Daubechies, Ten Lectures on Wavelets: Society for Industrial and Applied Mathematics, 1nd ed., I. Daubechies, 2002.
[18] T. Berger, J. O. Strömberg, and T. Eltoft, “Adaptive Regularized Constrained Least Squares Image Restoration,” IEEE Trans. on Image Processing, vol. 8, No. 9, pp. 1191-1203 , Sep. 1999.
[19] X. Zhu, C. Zhou, and I. J. Kemp, “An Improved Methodology for Application of Wavelet Transform to Partial Discharge Measurement Denoising,” IEEE Trans. on Dielectrics and Electrical Insulation, Vol.12, No.3, pp.586-594, Jun. 2005.
[20] I. Shim, J. J. Soraghan, and W. H. Siew, “A Noise Reduction Technique for on-Line Detection and Location of Partial Discharges in High Voltage Cable Networks,” Measurement Science and Technology, Vol. 11, No.12, pp.1708-1713, Nov. 2000.
[21] D. L. Donoho, “Denoising by Soft Thresholding,” IEEE Trans. Information Theory, Vol. 41, pp.961-627, May 1994.
[22] The Mathworks, Inc., “Wavelets From Conjugate Mirrors Filters,” Critically Sampled Wavelet Reconstruction.
[23] National Instruments Corporation, “WA Denoise VI,” [Online], Austin, State of Texas, USA, National Instruments Corporation, 2010, [cited May 15, 2016], available from the World Wide Web: < http://zone.ni.com/reference/en-XX/help/371419D-01/lvwavelettk/wa_de_noise/ >.
[24] L. Pastia, B. Walczaka, D.L. Massarta, and P. Reschiglianb, “Optimization of Signal Denoising in Discrete Wavelet Transform,” Chemometrics and Intelligent Laboratory Systems, Vol 48, pp. 21-34, Jun. 14, 1999.
[25] M. A. Farahani, M. T. V. Wylie, E. C. Guerra, and B. G. Colpitts, “Reduction in the Number of Averages Required in BOTDA Sensors Using Wavelet Denoising Techniques,” Journal of Lightwave Technology, vol. 30, No. 8, pp. 1134-1142, Apr. 2012
[26] B. S. Krongold, A. M. Sayeed, M. A. Moehring, J. A. Ritcey, M. P. Spencer, and D. L. Jones, “Time-Scale Detection of Microemboli in Flowing Blood with Doppler Ultrasound,” IEEE Trans. on Biomedical Engineering, vol. 46, No. 9, pp. 1801-1809, Sep. 1999
[27] D. L. Lin, The Study of Partial Discharge Detection in GIS Based on Wavelet Theory, M. thesis, Dept. of Electrical and Engineering , National Chung Kung University, Tainan, Taiwan, Jun. 2006.
[28] C. H. Lee, Partial Discharge Detection Based on Wavelet Theory for High-voltage Cable on Distribution System, M. thesis, Dept. of Electrical and Engineering, National Chung Kung University, Tainan, Taiwan, Jun. 2009.
[29] R. M. Rao, and A. S. Bopardikar, “Wavelet Transforms: Introduction to Theory and Applications: Addison Wesley Longman,” 1998.
[30] P. M. Bentley and J. T. E. McDonnell, “Wavelet Transforms: an Introduction,” Electronics B Communication Engineering Journal, Vol. 6, pp. 175-186, Aug. 1994.
[31] P. D. Agoris, S. Meijer, E. Gulski, and J. J. Smit, “Threshold Selection for Wavelet Denoising of Partial Discharge Data,” IEEE International Symposium on Electrical Insulation, Indianapolis, State of Indiana, USA ,Sept. 19-22, 2004, pp. 62-65
[32] I. Shim, J. J. Soraghan, and W. H. Siew, “Detection of PD Utilizing Digital Signal Processing Methods. Part 3: Open-Loop Noise Reduction,” IEEE Electrical Insulation Magazine, Vol. 17, No.1, pp 1-8, Jan. 2001.
[33] K. W. Huang, Wavelet Application in Acoustic Analysis for Partial Discharge Detection in Cast-Resin Dry-Type Transformers, M. thesis, Dept. of Electrical and Engineering , National Chung Kung University, Tainan, Taiwan, Jun. 2004.
[34] D. Paul, ”Failure Analysis of Dry-Type Power Transformer,” IEEE Trans. on Industry Applications, Vol. 37, No. 3, pp.689-695, May 2001.
[35] X. Ma, C. Zhou, and I. J. Kemp, “Automated Wavelet Selection and Thresholding for PD Detection,” IEEE Electrical Insulation Magazine, Vol. 18, No. 2, pp. 37-45, Mar. 2002
[36] C. He, J. Xing, J. Li, Q. Yang, and R. Wang, “A New Wavelet Threshold Determination Method Considering Interscale Correlation in Signal Denoising,” Mathematical problems in engineering, Vol. 2015, pp.1-9, Aug. 2014.
[37] A. Maćkiewicz, and W. Ratajczak, “Principal Component Analysis (PCA),” Vol. 19, No.3, pp. 303-342, Mar. 1993.
[38] L. I. Smith, “A tutorial on Principal Components Analysis,” Feb. 2002.
[39] K. Scott, “Using Principal Component Analysis to Remove Correlated Signal from Astronomical Images,” National Radio Astronomy Observatory Data Science Meet-up, Virginia, Charlottesville, 2014, [cited May 15, 2016], available from the World Wide Web:< http://www.slideshare.net/CvilleDataScience/az-tecpcadatasciencemeetupkscot t20140218 >.
[40] Pennsylvania State University, “Applied Multivariate Statistical Analysis : Principal Component Analysis,” Commonwealth of Pennsylvania, USA, The Pennsylvania State Universit, [cited May 15, 2016], available from the World Wide Web: < https://onlinecourses.science.psu.edu >.
[41] N. S. Altman, “An Introduction to Kernel and Nearest-neighbor Nonparametric Regression,” The American Statistician, Vol. 46, No. 3, pp.175-185, Aug. 1992.
[42] A. B. M. S. U. Doulah, S. A. Fattah, W.-P. Zhu, and M. O. Ahmad, “Wavelet Domain Feature Extraction Scheme Based on Dominant Motor Unit Action Potential of EMG Signal for Neuromuscular Disease Classification” IEEE Trans. on Biomedical Circuits and Systems, Vol. 8, No. 2, pp. 155-164, Apr. 2014.
[43] M. P. Lin, A Real-time Fall Detection System using Human Body Contours Information and KNN Classifier, M. thesis, Institute of Multimedia Engineering, National Chiao Tong University.
[44] M. Ejazuddin Syed, Attribute Weighting in K-nearest Neighbor Classification, M.Sc. thesis, Information Sciences Computer Science, University of Tampere School, Suomi, Nov. 2014.
[45] J. Tian, C. Morillo, M. H. Azarian, and M. Pecht, “Motor Bearing Fault Detection Using Spectral Kurtosis-Based Feature Extraction Coupled With K-Nearest Neighbor Distance Analysis”, IEEE Trans. on Industrial Electronics, vol. 63, No. 3, pp. 1793-1803, Mar. 2016.
[46] M. E. Syed, Attribute Weighting in K-nearest Neighbor Classification, M.Sc. thesis Supervisors, Information Sciences Computer Science, University of Tampere School, Kati Iltanen, Martti Juhola, Nov. 2014.
[47] G. Songy, J. Rochas, L. E. Beze, F. Huet, and F. Magoul`esy, ”K Nearest Neighbour Joins for Big Data on MapReduce: a Theoretical and Experimental Analysis,” IEEE Trans. on Knowledge and Data Engineering, vol. PP, pp. 1-18, May 2016.
[48] B. M. Ebrahimi, and J. Faiz, ”Diagnosis and Performance Analysis of Three Phase Permanent Magnet Synchronous Motors with Static, Dynamic and Mixed Eccentricity,” IET Electric Power Applications, Vol. 4, pp. 53-66, Apr. 2009
[49] I. Colak, M. Yesilbudak, S. Sagiroglu, and H. T. Kahraman, ”An Intelligent Approach for Speed Stability Analysis of a Travelling Wave Ultrasonic Motor based on Genetic k-NN Algorithm,” IEEE 5th International Conf. on Application of Information and Communication Technologies, Baku, Azərbaycan Respublikası, Oct. 12-14, 2011, pp. 1-5.
[50] O. Sutton, “Introduction to k Nearest Neighbor Classification and Condensed Nearest Neighbor Data Reduction,” Feb. 2012
[51] E. Mirkes, “KNN and Potential Energy (Applet),” [Online], Britain, University of Leicester, 2011, [cited May 02, 2016], available from the World Wide Web: < http://www.math.le.ac.uk/people/ag153/homepage/KNN/KNN3.html >.
[52] L. Kozma, “k Nearest Neighbours Algorithm,” [Online], Suomi, Helsinki University of Technology, 2008, [cited May 15, 2016], available from the World Wide Web: < http://www.lkozma.net/knn2.pdf >.
[53] S. R. Bhide, Fundamentals of Power System Protection, 1nd ed., 2010.
[54] CAPGO Acoustic Emissions, ‘Advantages of acoustic emissions monitoring,’
[55] Vallen-Systeme GmbH, “AE Testing Fundamentals Equipment Applications,” [Online], Munich, Germany, Vallen-Systeme GmbH, 2002, [cited May 02, 2016], available from the World Wide Web: <http://www.ndt.net/article/v07n09/05/05.htm >.
[56] J. C. Spanner, A. Brown and A. Pollock, Fundamentals of Acoustic Emission Testing, 2nd ed, Nondestructive Testing Handbook, 1987.
[57] IEEE Std C57.127-2000, Guide for the Detection of Acoustic Emissions from Partial Discharges in Oil-Immersed Power Transformers.
[58] "AE Sources". ndt-ed.org. Retrieved 2014-12-13.
[59] G. Shen, Z. Wu, J. Zhang, Advances in Acoustic Emission Technology, 1nd ed, New York, Springer-Verlag, 2013.
[60] F. Wasilewski, “Wavelet Daubechies 7 (db7),” [Online], Filip Wasilewski, 2008, [cited Apr. 02, 2016], available from the World Wide Web: < http://wavelets.pybytes.com /wavelet/db7/ >.
[61] Oracle Co., “Data Mining Concept：9 Feature Selection and Extraction,” [Online], LRACLE, 2008, [cited Apr. 02, 2016], available from the World Wide Web: < https://docs.oracle.com/cd/B28359_01/datamine.111/b28129/feature_extr.htm >.
[62] O. Söder, “KNN classifiers 1.1.1. Feature weighting,” [Online], 2008, [cited May 15, 2016], available from the World Wide Web: < http://www.fon.hum.uva.nl/praat/manual /kNN_classifiers_1_1_1__Feature_weighting.html >