臺灣博碩士論文加值系統

本論文提出小波轉換結合類神經網路分類器，針對感應電動機故障，進行訊號分析，並以k最近鄰分類法進行感應電動機故障辨識。首先，本研究提出小波轉換結合k最近鄰法分類器，此模型乃是藉由小波轉換多重解析度分析法及k最近鄰分類法構成，本研究提出之小波轉換結合類神經網路分類器，相較於小波轉換結合倒傳遞類神經網路分類器，具有較佳辨識率。另外，對於量測訊號雜訊干擾問題，本研究透過加入雜訊使分析訊號之SNR降低為25dB、20dB、15dB及10dB，並進行故障分類，以驗證本模型之強健性。

This thesis proposed a classifier combine a wavelet transform with neural network. The classifier perform a signal analysis for the stator current of the induction motor and identify faults in induction motors by the k-nearest neighbor (k-NN) algorithm. Firstly,this study proposed a classifier which combine the wavelet transform with the k-nearest neighbor algorithm. This classifier model was composed of multiple resolution analysis (MRA) of wavelet transform and k-nearest neighbor algorithm. The classifier purposed in this study has a better recognition rate than the classifier combines the wavelet transform with back propagation neural network (BPNN). In addition,the study reduced the SNR of the input signal for testing the reliability of the model.

中文摘要 I
Abstract II
目錄 III
圖目錄 VI
表目錄 VIII
第一章 緒論 1
1.1 研究動機及背景 1
1.2 文獻回顧 2
1.3 本論文貢獻 3
1.4 章節概要 3
第二章 訊號分析理論簡介 4
2.1 前言 4
2.2 傅立葉概論 4
2.2.1 快速傅立葉轉換簡介 5
2.2.2 短時傅立葉葉轉換 7
2.3 小波轉換簡介 8
2.3.1 連續小波轉換 8
2.3.2 離散小波轉換 9
2.3.3 多重解析度分析 10
2.4 本章結論 13
第三章 類神經網路簡介 14
3.1 前言 14
3.2 神經元模型 15
3.3 倒傳遞神經網路 19
3.4 k最近鄰分類法 23
3.5 本章結論 23
第四章 馬達訊號量測與分析結果 24
4.1 前言 24
4.2 馬達故障樣本介紹 25
4.2.1 軸承破壞故障樣本加工 25
4.2.2 定子層間短路故障樣本加工 27
4.2.3 轉子斷條故障樣本加工 28
4.3 馬達電流訊號量測 29
4.3.1 實驗設備 29
4.3.2 電流訊號量測流程 30
4.4 訊號量測與分析結果 31
4.5 本章結論 36
第五章 特徵擷取與類神經網路辨識結果 37
5.1 前言 37
5.2 小波轉換分析結果特徵擷取 37
5.2.1 特徵擷取結果 39
5.3 實驗數據與使用分類器 42
5.4 辨識結果討論 43
5.4.1 倒傳遞類神經網路辨識結果 43
5.4.2 k最近鄰法辨識結果 43
5.5 本章結論 44
第六章 結論與未來展望 45
6.1 結論 45
6.2 未來發展方向 45
參考文獻 47
 
圖目錄
圖 2.1 多重解析空間 12
圖 2.2 多重解析分解架構示意圖 12
圖 3.1生物神經細胞示意圖 15
圖 3.2單一神經元模型 16
圖 3.3 活化函數 18
圖 3.4 倒傳遞神經網路基本結構圖 19
圖 3.5 倒傳遞神經網路訓練流程圖 22
圖 3.6 k-NN示意圖 23
圖 4.1 感應馬達外觀 25
圖 4.2 三相感應馬達軸承 26
圖 4.3 軸承內環滾道缺損加工說明 26
圖 4.4 三相感應馬達定子（紅色指標處） 27
圖 4.5 三相感應馬達轉子與軸承 28
圖 4.6 實驗設備架構 29
圖 4.7 三相鼠籠式感應馬達運作示意圖 30
圖 4.8 訊號分析與量測流程圖 30
圖 4.9 健康樣本小波轉換結果 32
圖 4.10 軸承內環缺損樣本小波轉換結果 33
圖 4.11 定子層間短路樣本小波轉換結果 34
圖 4.12 轉子斷條樣本小波轉換結果 35
圖 5.1 小波轉換多重解析分析之特徵擷取流程 38
圖 5.2 電流訊號小波多重解析度分析 特徵能量圖(SNR=∞) 40
圖 5.3 電流訊號小波多重解析度分析 特徵能量圖(SNR=25dB) 40
圖 5.4 電流訊號小波多重解析度分析 特徵能量圖(SNR=20dB) 41
圖 5.5 電流訊號小波多重解析度分析 特徵能量圖(SNR=15dB) 41
圖 5.6 電流訊號小波多重解析度分析 特徵能量圖(SNR=10dB) 42
 
表目錄
表 4.1 感應馬達規格 25
表 4.2 馬達樣本代號 31
表 5.1 小波轉換特徵擷取表 39
表 5.2 類神經網路輸入資料 42
表 5.3 BPNN故障辨識結果 43
表 5.4 k-NN故障辨識結果 44
表 5.5 故障辨識結果統整表 44

[1]X. Huang, T. G. Habetler, R. G. Harley, and E. J. Wiedenbrug, “Using a surge tester to detect rotor eccentricity faults in induction motors,” IEEE Transactions on Industry Applications, vol. 43, pp. 1183-1190, Sep.-Oct. 2007.
[2]M. S. Ballal, Z. J. Khan, H. M. Suryawanshi, and R. L. Sonolikar, “Adaptive neural fuzzy inference system for the detection of inter-turn insulation and bearing wear faults in induction motor,” IEEE Transactions on Industrial Electronics, vol. 54, no. 1, pp. 250-258, Feb. 2007.
[3]Pat O''Donnell, “Report of large motor reliability survey of industrial and commercial installations, part I,” IEEE Transaction on Industry Applications, vol.21, no. 4, pp.865-872, Jul.-Aug. 1985.
[4]Pat O''Donnell, “Report of large lotor reliability survey of industrial and commercial installations, part II,” IEEE Transaction on Industry Applications, vol.21, no. 4, pp.853-864, Jul.-Aug. 1985.
[5]I. M. Culbert and W. Rhodes, “Using current signature analysis technology to reliably detect cage winding defects in squirrel-cage induction motors,” IEEE Transactions on Industry Applications, vol. 43, pp. 422-428, Mar.-Apr. 2007
[6]P. Rajamani, D. Dey, and S. Chakravorti, “Cross-correlation aided wavelet network for classification of dynamic insulation failures in transformer winding during impulse test,” IEEE Transactions on Dielectrics and Electrical Insulation, vol. 18, pp. 521-532, Apr. 2011.
[7]X. H. Huang, T. G. Habetler, and R. G. Harley, “Detection of rotor eccentricity faults in a closed-loop drive-connected induction motor using an artificial neural network,” IEEE Transactions on Power Electronics, vol. 22, pp. 1552-1559, Jul. 2007.
[8]E. C. C. Lau, and H. W. Ngan, “Detection of motor bearing outer raceway defect by wavelet packet transformed motor current signature analysis,” IEEE Transactions on Instrumentation and Measurement, vol. 59, no. 10, pp.2683-2690, Oct. 2010.
[9]W. Zhou, B. Lu, G. Habetler, and R. G. Harley, “Incipient bearing fault detection via motor stator current noise cancellation using wiener filter,” IEEE Transaction on Industry Applications, vol.45, no. 4, pp. 1309-1317, Jul.-Aug. 2009.
[10]J. H. Jung, J. J. Lee, and B. H. Kwon, “Online diagnosis of induction motors using MCSA,” IEEE Transactions on Industrial Electronics, vol. 53, pp. 1842-1852, Dec. 2006.
[11]A. Ferrah, K. J. Bradley, and G. M. Asher, “An FFT-based novel approach to noninvasive speed measurement in induction motor drives,” IEEE Trans. on Instrumentation and Measurement, vol. 41, no. 6, pp. 797–802, Dec. 1992.
[12]C. Kral, T. G. Habetler, R. G. Harley, F. Pirker, G. Pascoli, H. Oberguggenberger, and C. J. M. Fenz, “A comparison of rotor fault detection techniques with respect to the assessment of fault severity,” IEEE Power Electronics and Drives, SDEMPED, Atlanta, GA, USA, 24–26 Aug. 2003, pp. 265–270.
[13]A. Sadeghian, Z. Ye, and B. Wu, “Online detection of broken rotor bars in induction motors by Wavelet Packet Decomposition and Artificial Neural Networks,” IEEE Trans. on Instrumentation and Measurement, vol. 58, no. 7, pp. 2253–2263, Jul. 2009.
[14]M. A. S. K. Khan, T. S. Radwan, and M. Azizur Rahman, “Real-Time Implementation of Wavelet Packet Transform-Based Diagnosis and Protection of Three-Phase Induction Motors,” IEEE Trans. on Energy Conversion, vol. 22, no. 3, pp. 647–655, Sept. 2007.
[15]J. A. Antonino-Daviu, M. Riera-Guasp, J. R. Folch, and M. P. M. Palomares, “Validation of a New Method for the Diagnosis of Rotor Bar Failures via Wavelet Transform in Industrial Induction Machines,” IEEE Trans. on Industry Applications, vol. 42, no. 4, pp. 990–996, Jul./ Aug. 2006.
[16]M. Y. Chow, R. N. Sharpe, and J. C. Hung, “On the application and design of artificial neural networks for motor fault detection—Part 1,” IEEE Transactions on Industrial Electronics, vol. 40, pp. 181-188, 1993.
[17]洪惟曉、陳培文、張郁斌、揚名全 譯，「訊號與系統-第二版」，全華圖書股份有限公司，2007。
[18]J. W. Cooley and J. W. Tukey, “An algorithm for the machine calculation of complex Fourier series,” Math. Comput., vol. 19, pp. 297–301, April 1965.
[19]A. Ferrah, K. J. Bradley, and G. M. Asher, “An FFT-based novel approach to noninvasive speed measurement in induction motor drives,” IEEE Trans. on Instrumentation and Measurement, vol. 41, no. 6, pp. 797–802, Dec. 1992.
[20]A. Grossman, and J. Morlet, “Decompositions of hardy functions into square integrable wavelet of constant shape,” Society for Industrial and Applied Mathematics Journal of Mathematical Analysis, vol. 15, no. 4, pp. 723–736, Jul. 1984.
[21]V. L. Pham, and K. P. Wong, “Wavelet-transform-based algorithm for harmonic analysis of power system waveforms,” IEEE Generation, Transmission and Distribution, vol. 146, no. 3, pp. 249–254, May. 1999.
[22]K. L. Butler, and S. S. Dey, “Using discrete wavelet transforms to characterize equipment failures for maintaining distribution systems reliability,” in Proc. 4th Int. Conf. Power Syst. Oper. Planning, Accra, Ghana, pp. 104–110, Aug. 2000.
[23]B. Ayhan, M –Y. Chow, and M. H. Song, “Multiple Discriminant Analysis and Neural-Network-Based Monolith and Partition Fault-Detection Schemes for Broken Rotor Bar in Induction Motors,” IEEE Trans. on Industrial Electronics, vol. 53, no. 4, pp. 1298–1308, Aug. 2006.
[24]S. Mishra, C. N. Bhende, and B. K. Panigrahi, “Detection and Classification of Power Quality Disturbances Using S-Transform and Probabilistic Neural Network,” IEEE Trans. on Power Delivery, vol. 23, no. 1, pp. 280–287, Jan. 2008.
[25]V. N. Ghate and S. V. Dudul, “Cascade Neural-Network-Based Fault Classifier for Three-Phase Induction Motor,” IEEE Trans. on Industrial Electronics, vol. 58, no. 5, pp. 1555–1563, May 2011.
[26]S. Tamura and M. Tateishi, “Capabilities of a Four-Layered Feedforward Neural Network: Four Layers Versus Three,” IEEE Trans. on Neural Networks, vol. 8, no. 2, pp. 251–255, Mar. 1997.
[27]G. B. Huang, L. Chen, and C. K. Siew, “Universal Approximation Using Incremental Constructive Feedforward Networks With Random Hidden Nodes,” IEEE Trans. on Neural Networks, vol. 17, no. 4, pp. 879–892, Jul. 2006.
[28]G. Cybenlo, “Neural networks in computational science and engineering,” IEEE Computational Science & Engineering, vol. 3, no. 1, pp. 36-42, 1996.
[29]顧力栩，沈晉慧 譯，「人工智慧：智慧型系統導論」，台灣培生教育出版股份有限公司，2007。[30]汪惠健，「類神經網路設計」，新加坡商湯姆生亞洲私人有限公司，民國94年。
[30]顧力栩，沈晉慧 譯，「人工智慧：智慧型系統導論」，台灣培生教育出版股份有限公司，2007。
[31]D. F. Specht, “Probabilistic neural networks for classification, mapping, or associative memory,” in Proceedings of the IEEE International Conference on Neural Networks, vol. 1, San Diego, CA, July 1988, pp. 525-532.
[32]E. Fix and J. L. Hodges, “Discriminatory analysis, Nonparametric Discrimination, Consistency Properties,” US Air Force School of Aviation Medicine, TX, Technical Report Number 4, Project 21-49-004 , Randolph Field, pp. 261-279, 1951.
[33]E.Parzen, “On the estimation of a probability density function and mode,” Annals of Mathematical Statistics, vol. 33, pp. 1065-1076, 1962.
[34]D.C. Plaut, S. J. Nowlan, and G. E. Hinton, “Experiments on learing by back propagation,” Technical Report CMU-CS-86-126, 1986.
[35]D. E. Rumblhart, G. E. Hinton, and R. J. Willia, “Learning representations by back-propagation errors,” Nature, vol. 323, pp. 533–536, 1986.
[36]C. Charalambous, “Conjugate gradient algorithm for efficient training of artificial neural networks,” IEEE Proceedings G, vol. 139, No.3, pp. 301-310, Jun. 1992.
[37]E. Kreyszig, Advanced Engineering Mathematics, 8nd ed. New York: John Wiley& Sons, Inc., 1999.
[38]W. A. Chavalitwongse, Y. J. Fan, and R. C. Sachdeo, “On the time series k-nearest neighbor classification of abnormal brain activity,” IEEE Transactions on System, Man and Cybernetics Part A: System and Humans, vol. 37, no. 6, pp. 1005-1016, Nov. 2007.