電力設備因長期運轉及環境變化等因素下，將導致絕緣劣化的發生，進而引起不必要的停電事故，甚至造成經濟上的損失。因此如何達到預防性的故障診斷，為電力相關研究之重要課題之一。本文利用音射檢測技術針對五種不同瑕疵類型之模鑄式比流器，實際加壓量測其局部放電之音射信號，將所量測到的試驗數據，利用統計學眾數之原理，擷取出局部放電音射信號之特徵值，作為類神經網路之輸入數據，並進行故障類型之辨識。由於現場加壓檢測時，試驗過程中所量測之信號，有時會受到雜訊的干擾，而影響辨識系統之正確性，於是在本文中以人工方式，加入不同大小之隨機雜訊，並探討對於辨識系統之影響。最後，提出以小波轉換方式將信號裡的雜訊濾除，並經由實驗數據發現，小波轉換確實可有效降低雜訊對信號的影響，進而提高系統之辨識率。

Owing to the long-term operation and environmental change, the electrical equipment generally faces the deterioration problem of insulation material. Thus, the unnecessary power outages will happen resulting in tremendous losses based on economic concern. Hence, to prevent this damage in advance becomes an important issue of the power system. In this thesis, the high voltage test procedure provided by standard has been applied on defected cast-resin current transformer to get the acoustic emission signal raised by partial discharge phenomena. There are 5 experiment models of cast-resin current transformers with pre-manufactured insulation defects. To increase the recognition rate, the salient features of the acoustic emission obtained from partial discharge measurement are extracted by a statistics theory. These features are subsequently used as the input data for a back-propagation neural network. Because the measured acoustic signals might be disturbed by noise that always affect the results of recognition system in the field. Therefore, some random noises with different magnitude were added to the acoustic signal to explore the recognition rate of the proposed neural network systems. The wavelet transforms are also used as the tool of noise filtering and the simulation results shows that the wavelet transform can effectively reduce the noise and improve the recognition rate.

[1]成永紅，電力設備絕緣檢測與診斷，中國電力出版社，2001年。
[2]V. K. Agarwal, H. M. Banford, B. S. Bernstein, E. L. Brancato, R. A. Fouracre, G. C. Montanari, J. L. Parpal, D. M. Ryder and J. Tanaka, “The Mysteries of Multifactor Ageing,” IEEE Electrical Insulation Magazine, Vol. 11, No. 3, pp. 37-43, 1995.
[3]“High-Voltage Test Techniques-Partial Discharge Measurements,” IEC 60270, 2001.
[4]李建明，高壓電氣設備試驗方法，中國電力出版社，2001年。
[5]D. Kind, “High-voltage Experimental Technique,” Vieweg, 1985.
[6]F. H. Kreuge, “Partial Discharge Detection in High Voltage Equipment,” Butterworths, 1989.
[7]E. Gulski, “Digital Analysis of Partial Discharges,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 2, No. 5, pp. 822-837, 1995.
[8]F. H. Kreuger, E. Gulski, and A. Krivda, “Classification of Partial Discharge,” IEEE Transactions on Electrical Insulation, Vol. 28, No. 6, pp. 917-931, 1993.
[9]許晉維，「應用類神經網路於比流器局部放電圖譜之辨識」，碩士論文，國立台灣科技大學，2002年。
[10]“AE Testing Fundamentals Equipment Applications,” Handbook, 2002.
[11]“Standard Definitions of Terms Relating to Acoustic Emission,” American Society for Testing and Materials (ASTM E610-82), 1999.
[12]J. C. Spanner, A. Brown and A. Pollock, “Fundamentals of Acoustic Emission Testing,” Nondestructive Testing Handbook, Vol. 5, pp. 11-44, 1987.
[13]D. E. Bray and D. McBride, “Nondestructive Testing Techniques,” John Wiley & Sons, pp. 345-377, 1992.
[14]P. P. Nelson and D. S. Glaster, “AE and Discrete Fracture Propagation in Rock,” Acoustic Emission/Microseismic Activity in Geological Structures and Materials, Proceedings of the 4th Conference, pp. 117-130, 1989.
[15]吳瑞南、林育勳，「局部放電電氣信號量測技術介紹」，量測資訊，第85期，2002年。
[16]宋執誠，高電壓技術，中國電力出版社，1995年。
[17]Y. Tian, P. L. Lewin, A. E. Davies and Z. Richardson, “Acoustic Emission Detection of Partial Discharges in Polymeric Insulation,” High Voltage Engineering Symposium, pp. 22-27, 1999.
[18]顏能通，「應用類神經網路於模鑄型變壓器部份放電音頻信號之辨識」，碩士論文，國立成功大學，2005年。
[19]M. C. Hu and I. S. Tsai, “The inspection of fabric defects by using wavelet transform,” Journal of the Textile Institute, Vol. 91, No. 3, pp. 420-433, 1999.
[20]葉怡成，應用類神經網路，儒林圖書，2002年。
[21]周鵬程，類神經網路入門，全華科技圖書，2006年。
[22]M. T. Hagan, H. B. Demuth and M. Beale, “Neural Network Design,” PWS Publishing Company, 1996.
[23]J. M. Zurada, “Introduction to Artificial Neural Systems,” West Publishing Company, 1992.
[24]羅華強，類神經網路-Matlab的應用，高立圖書，2005年。
[25]M. Riedmiller and H. Braun, “A Direct Adaptive Method for Faster Backpropagation Learning: The RPROP Algorithm,” IEEE Conference on Electrical Insulation, Vol. 1, pp. 586-591, 1993.
[26]A. Grossman and J. Morlet, “Decomposition of Hardy Functions into Square Integrable Wavelets of Constant Shape,” SIAM Journal on Mathematical Analysis, 1984.
[27]廖紹綱，數位影像處理活動Matlab，全華科技圖書，1999年。
[28]R. M. Rao and A. S. Bopardikar, “Wavelet Transforms: Introduction to Theory and Applications,” Addison Wesley, First Printing, 1998.
[29]S. Mallat, “A Theory for Multiresolution Signal Decomposition: The Wavelet Representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, No. 7, pp. 674-693, 1989.
[30]S. Mallat, “Multiresolution Channel Decomposition of Images and Wavelet Models,” IEEE Transactions on Acoustics, Speech, Signal Processing, Vol. 37, No. 7, pp. 2091-2110, 1989.
[31]M. Vetterli and J. Kovacevic, “Wavelets and Subband Coding,” Prentice Hall, New Jersey, 1995.
[32]D. L. Donoho, “De-noising by Soft-Thresholding,” IEEE Transactions on Information Theory, Vol. 41, No. 3, pp. 613-627, 1995.
[33]D. L. Donoho and I. M. Johnstone, “Adapting to Unknown Smoothness via Wavelet Shrinkage,” Journal of the American Statistical Association, Vol. 90, pp. 1200-1224, 1995.
[34]C. S. Burrus, R. A. Gopinath and H. Guo, “Introduction to Wavelets and Wavelet Transforms,” Prentice-Hall, 1989.
[35]D. F. Guo, W. H. Zhu, Z. M. Gao and J. Q. Zhang, “A Study of Wavelet Thresholding Denoising,” 5th International Conference on Signal Processing Proceedings, Vol. 1, pp. 329-332, 2000.
[36]“Instrument Transformers Part1: Current Transformers,” IEC60044-1, pp. 29-31, 1996.
[37]「變比器」，CNS11437，C4435，2001年。
[38]陳美源，統計學，三民圖書，2002年。
[39]吳權威、呂琳琳，Excel 2003函數與統計應用實務，網弈科技圖書，2004年。