地下配電系統電力電纜所造成的事故中，基於人為疏失造成電纜接頭絕緣劣化之比例為最高，如能應用局部放電信號之檢測以達到預防性的故障診斷，則能減少事故發生，提高供電可靠度。故此，本文旨在應用音射法於電纜接頭瑕疵型態之局部放電辨識研究。首先，參考經常處理地下電纜接續的施工人員之經驗與相關文獻，製作一條良品及三條人工瑕疵的電纜接頭試驗樣品，以音射法於高壓室內完成其局部放電之檢測。其次，應用希爾伯特-黃變換之經驗模態分解，降低背景雜訊對電纜接頭試驗樣品的辨識影響。接著，於時間、頻率與振幅分佈的希爾伯特-黃圖譜萃取分形維數及間隙度二個特徵，以減少類神經網路輸入層之神經元，並縮短其訓練學習之時間。最後，以類神經網路、山峰聚類法及減法聚類法分別進行試驗樣品之辨識，在背景雜訊為0%及5%時的辨識率均能達到100%，甚至背景雜訊達到15%時，辨識率均還有70%以上之辨識效果。另外，本文首次應用聚類法於電力設備絕緣瑕疵型態之辨識，在不同的背景雜訊下與類神經網路之辨識效果各有所長，未來期望研究成果能提供現場量測研究人員參考之用。

For the modern distribution system, most of the accidents for underground power cable were resulted from the failure of cable joint due to the artificial mistake of field workers. If the partial discharge signals from the cable joints could be detected and used for insulation discrimination, then the possible accidents could be previously prevented and also upgrade the reliability of electricity power distribution. Therefore, in this dissertation, it was intentionally adopted acoustic emission method in defection recognition of partial discharge of power cable joint. First of all, according to the experience of engineers for related work of underground power cable placements and related reference literature, one good sample and three artificial defections of cable joints were made and proceed to the detection of their partial discharge. Then, the Empirical Mode Decomposition (EMD) of Hilbert-Huang Transform (HHT) was applied and tried to decrease the background noises which may affect the accuracy of recognition for the cable joints samples. As a result two features which were fractal dimension and lacunarity were extracted through the spectrum of HHT so as to decrease input neuron of neural network and shorten the learning time. Finally, the neural network, mountain clustering and subtractive clustering were all implemented to proceed to the recognition of cable joints samples and the recognition rate could get to 100% through 0% and 5% background noise. Furthermore, the recognition rate could still get to 70% while the noise was 15%. In this dissertation, the clustering approach was first implemented in defect recognition of power insulation facilities, and comparing with traditional neural network method under different noise level with promising results especially in lower noise environment. Therefore, the encouraging results from this research could be important references for both of the field engineers and researchers in the future.

[1] 張憲章，「台電技術報告-輸電線路電纜工程」，2002年。
[2] 張瑞村，「數位局部放電量測應用於高壓電纜終端接頭絕緣狀態之評估」，碩士論文，國立台灣科技大學，2005年。
[3] “High-Voltage Test Techniques-Partial Discharge Measurements,” IEC 60270, 2001.
[4] 賴佳良，「模鑄式比流器之局部放電音射信號辨識」，碩士論文，國立台灣科技大學，2007年。
[5] K. Uchida, S. Kobayashi, T. Kawashima, H. Tanaka, S. Sakuma, K. Hirotsu, and H. Inoue, “Study on Detection for The Defects of XLPE Cable Lines,” IEEE Transactions on Power Delivery, Vol. 11, No. 2, pp. 663-668, Apr. 1996.
[6] F. H. Kreuge, “Partial Discharge Detection in High Voltage Equipment,” Butterworths, 1989.
[7] D. Kind, “High-voltage Experimental Technique,” Vieweg, 1985.
[8] E. Gulski, “Digital Analysis of Partial Discharges,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 2, No. 5, pp. 822-837, 1995.
[9] 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.
[10] 楊正光、林育勳，「局部放電技術應用於電力設備之預防診斷」，電機月刊，第134期，第200-206頁，2002年。
[11] 陳昭榮、邱乾政、葉崇源、林育勳，「部份放電法應用於電力設備絕緣檢測」，中華民國第二十二屆電力工程研討會，高雄，第811-815頁，2002年。
[12] 潘彥竹，「局部放電量測系統之研製」，碩士論文，國立台灣科技大學，2004年。
[13] 李建明、朱康，「高壓電氣設備試驗方法」，中國電力出版社，第二版，第298-322頁，2000年。
[14] 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，第35-38頁，2002年。
[15] R. E. James and B. T. Phung, “Development of Computer-Based Measurements and Their Application to PD Pattern Analysis,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 2, No. 5, pp. 838-856, October 1995.
[16] 邱昌容、王乃慶，「電工設備局部放電及其量測技術」，機械工業出版社，第一版，1994年。
[17] AE Testing Fundamentals Equipment Applications, Handbook, 2002.
[18] “Standard Definitions of Terms Relating to Acoustic Emission,” American Society for Testing and Materials (ASTM E610-82), 1999.
[19] J. C. Spanner, A. Brown, and A. Pollock, Fundamentals of Acoustic Emission Testing, Nondestructive Testing Handbook, Vol. 5, pp. 11-44, 1987.
[20] D. E. Bray and D. McBride, Nondestructive Testing Techniques, John Wiley & Sons, pp. 345-377, 1992.
[21] 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.
[22] 張植，「長壽電纜性能綜合報導」，電機月刊，第七卷第十二期，第128-147頁，1997年。
[23] Jarot Setyawan, “Investigation of Partial Discharge Occurrence and Detectability in High Voltage Power Cable Accessories,” M.S. thesis, Delft University of Technology, Delft, Netherlands, 2009.
[24] 鄭富雄，「25kV高壓電纜接頭之施工與事故分析及防範對策」，碩士論文，中原大學，2003年。
[25] 吳文良，「國內交連PE電力電纜的發展」，產業調查與技術季刊，第120期，第58-69頁，2007年。
[26] 李仁智，「有限元素法應用於電力電纜電磁效應分析」，碩士論文，吳鳳技術學院，2006年。
[27] 台灣電力公司業務處，「地下配電線路設計，配電技術手冊(四)」，1996年。
[28] 台灣電力公司業務處，「架空配電線路器材」，1996年。
[29] “XLPE Cable Systems Users Guide,” ABB.
[30] 聯友機電公司，http://www.ueitw.com.tw/termination.html。
[31] 張建國，「地下電纜接頭局部放電線上監控系統之研製」，碩士論文，國立台灣科技大學，2006年。
[32] 台灣翔登公司，「預鑄型屋外電纜直線接頭-施工說明書」。
[33] 台灣電力公司，「高壓電力電纜接頭處理施工範例，技術手冊(七)」。
[34] 台灣電力公司，「既設地下電路改接工程之竣工耐壓試驗方式研究-期末報告」，2010年。
[35] 許朝翔，「應用局部放電技術於交鏈聚乙烯電力電纜接續匣之瑕疵辨識」，碩士論文，國立台灣科技大學，2011年。
[36] N. E. Huang, Z. Shen, and S. R. Long, “A New Review of Nonlinear Water Waves: The Hilbert Spectrum,” Annu. Rev. Fluid Mech, Vol. 31, pp. 417-457, Jan. 1999.
[37] B. X. Du, G. Wei, Y. Wu, and M. Ouyang, “Wavelet-Based and Fractal Theory on Partial Discharge Classification,” IEEE International Conference on Electrical Insulating Materials, pp. 463-466, Jun. 2005.
[38] Q. Zhang, Y. Lu, and X. Zhang, “PD Pattern Classification for DC System Based on Fractal Dimensions Combined with Statistical Features,” IEEE International Conference on Properties and Applications of Dielectric Materials, pp. 427-430, Jun. 2006.
[39] 于德介、楊宇，「機械故障診斷的Hilbert-Huang變換方法」，北京，科學出版社，2006年。
[40] X. Wang, B. Li, Z. Liu, H. T. Roman, O. L. Russo, K. K. Chin, and K. R. Farmer, “Analysis of Partial Discharge Signal Using The Hilbert–Huang Transform,” IEEE Transactions on Power Delivery, Vol. 21, No. 3, pp. 1063-1067, Jul. 2006.
[41] A. Daviu, R. Guasp, P. Sanchez, and Perez, “A Critical Comparison Between DWT and Hilbert–Huang-Based Methods for The Diagnosis of Rotor Bar Failures in Induction Machines,” IEEE Transactions on Industy Applications, Vol. 45, No. 5, pp. 1794-1803, Sep. 2009.
[42] Huang N. E., Shen Z., Long S. R., Wu M. C., Shih H. H., Zheng Q., Yen N. C., Tung C. C., and Liu H. H., “The Empirical Mode Decomposition and Hilbert Spectrum for Nonlinear and Non-stationary Time Series Analysis,” Proceedings of the Royal Society London A, Vol.454, pp.903-995, 1998.
[43] R. Yan, “Hilbert–Huang Transform-Based Vibration Signal Analysis for Machine Health Monitoring,” IEEE Transactions on Instrumentation and Measurement, Vol. 55, No. 6, pp. 2320-2329, Dec. 2006.
[44] B. B. Mandelbrot, “The Fractal Geometry of Nature,” W.H. Freeman and Company, 1982.
[45] 張濟忠，「分形」，北京，清華大學出版社，1995年。
[46] B. B. Mandelbrot, ”How Long Is The Coast of Britain? Statistical Selfsimilarity and Fractional Dimension,” Science, Vol. 156, No. 3775, pp. 636-638, May 1967.
[47] 張志三，「漫談碎形」，台北，牛頓出版，1996年。
[48] K. J. Falconer, “Fractal Geometry: Mathematical Foundations and Applications,” Wiley, 1990.
[49] H. Peitgen and H. Jurgens, “Chaos and Fractals New Frontier of Science,” 2004.
[50] 林琦焜，「從Cantor集到碎形」，數學傳播，第25卷，第1期，第3-14頁，2001年。
[51] N. Sarkar and B. B. Chaudhuri, “An Efficient Differential Box-Counting Approach to Compute Fractal Dimension of Image,” IEEE Transactions on Systems, Man and Cybernetics, Vol. 24, No. 1, pp. 115-120, Jan. 1994.
[52] 古峰昌，「XLPE電力電纜局部放電量測與瑕疵模式辨識」，碩士論文，國立勤益科技大學，2009年。
[53] Feng-Chang Gu, Hong-Chan Chang, Fu-Hsien Chen, and Cheng-Chien Kuo, ”Partial Discharge Pattern Recognition of Power Cable Joints Using Extension Method with Fractal Feature Enhancement,” Expert Systems with Applications, 39, pp. 2804–2812, 2012.
[54] 張裴章、張麗秋，「類神經網路」，東華出版社，2006年。
[55] 許晉維，「應用類神經網路於比流器局部放電圖譜之辨識」，國立台灣科技大學電機工程研究所，碩士論文，2003年。
[56] M. Hoof, B. Freisleben, and R. Patsc, “PD Source Identification with Novel Discharge Parameters Using Counter Propagation Neural Networks,” IEEE Transactions on Dielectrics and Electrical Insulation, Vol. 4, No. 1, pp. 17-32, Feb. 1997.
[57] P. R. Krishnaiah and L. N. Kanal, ”Classification, Pattern Recognition, and Reduction of Dimensionality,” Vo1. 2 of Handbook of Statistics, Amsterdam, North-Holland, 1982.
[58] J. C. Bezdek, “Pattern Recognition with Fuzzy Objective Function Algorithms,” New York：Plenum Press,1981.
[59] Yager R. R. and Filev D. P., “Generation of fuzzy Rules by Mountain Clustering,” Journal of Intelligent and Fuzzy Systems, PP. 209-219, Feb. 1994.
[60] Yager R. R. and Filev D. P., “Approximate Clustering Via The Mountain Method,” IEEE Transactions on Systems, pp. 209-219, Feb. 1994.
[61] Chiu S. L., “Fuzzy Model Identification Based on Cluster Estimation,” Journal of Intelligent and Fuzzy Systems, pp. 267-278, Feb. 1994.
[62] Pereira C. and Dourado A., “Application of a Neuro-fuzzy Network with Support Vector Learning to A Solar Power Plant,” 2nd IHP Workshop, Espanha, Almeria, 2002.