本文將電力品質事故暫態信號經小波轉換進行分析，並透過巴賽瓦定理針對各階小波係數計算其頻譜能量，以保留原始信號特徵。應用可拓理論與可拓類神經網路於電力品質事故辨識系統，可拓理論能依據特徵資料建立電力品質事故辨識的物元模型，藉由可拓關聯函數計算辨識資料和事故種類之關聯度，電力品質事故便可經由關聯度直接辨識出來。可拓類神經網路是結合可拓理論和類神經網路所形成之新型類神經網路，藉由創新的可拓距離函數取代歐幾里德距離，計算辨識資料和事故種類之關聯度，能實行監督式學習和獲得更短學習時間，並且網路架構較傳統類神經網路簡單。
為了證實本文提出辨識系統之實用性，使用Matlab模擬電力系統不同型態之電力品質事故信號，並收集實際現場量測波形資料作為測試波形，經測試結果顯示，本文所建構之辨識系統具有不錯的辨識效果。最後，利用LabVIEW圖形監控軟體開發電力品質事故辨識介面，以方便相關人員進行電力品質事故辨識使用。

In the present study, the wavelet transform method is used to analyze the transient signals in the power quality events. Then, the Parseval’s theorem is applied to measure the spectrum energy of different scales of Wavelet transform coefficients. With the application of the above-proposed approaches, the characteristics of the original power signals can be reserved. The extension theory and extension neural network (ENN) are applied in the recognition system of the power quality events. Based on the extension theory, the matter-element models are built according to the collected characteristic data. The extended correlation function is applied to calculate the relation degree between the power quality events and the recognized characteristics. With this proposed method, the power quality events can be directly identified by the calculated relation degrees. Extension neural network is a new topology of neural networks that combines extension theory with neural networks. It uses extension distance instead of Euclidean Distance (ED) to measure the relation degree between recognized data and event cluster types; it can facilitate supervised learning, shorter learning duration and simpler structures than traditional neural networks did.
To demonstrate the effectiveness of the proposed recognition systems, both the simulated patterns, which are generated via the Matlab software tools, and the field patterns of power quality events are collected as testing data. The test results show that the recognition systems proposed in this present study has provided promising performance in recognizing the power quality events. Finally, the researcher uses the LabVIEW software to design an interface for recognizing power quality events, providing more user-friendly event-recognizing tools for related members in this field.

中文摘要 i
英文摘要 ii
謝誌 iv
目錄 v
圖目錄 viii
表目錄 xi

第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 文獻探討 4
1.4 研究方法 7
1.5 論文架構 9

第二章 電力品質問題與監測 11
2.1 簡介 11
2.2 電力暫態現象與種類 13
2.3 電力暫態監測與解決方法 21
2.4 小結 23

第三章 利用小波轉換方法分析電力暫態信號 24
3.1 簡介 24
3.2 傳統訊號分析方法 25
3.3 小波轉換 28
3.4 小波轉換多重解析格式 33
3.5 濾波器頻寬與離散小波轉換之間的關係 39
3.6 巴賽瓦定理 43
3.7 小結 44

第四章 可拓理論與類神經網路 45
4.1 簡介 45
4.2 可拓理論 46
4.3 物元的概念 49
4.3.1 物元的可拓性 50
4.3.2 物元的變換 54
4.4 可拓集合理論 56
4.4.1 可拓集合的概念 56
4.4.2 關聯函數 58
4.5 類神經網路 60
4.6 雙層類神經網路(無隱藏層感知機) 64
4.7 小結 75

第五章 電力品質事故辨識方法與數值驗證結果 76
5.1 簡介 76
5.2 電力品質事故波形信號模擬電路 77
5.3 小波轉換特徵值之擷取 85
5.4 可拓理論辨識系統 91
5.5 可拓類神經網路辨識系統 98
5.6 實際量測數值 111
5.7 電力品質事故辨識系統圖控介面 113
5.8 小結 117

第六章 結論與展望 118
6.1 結論 118
6.2 展望 120
參考文獻 121

圖目錄
圖2.1 電力中斷信號波形圖 15
圖2.2 電壓驟降信號波形圖 17
圖2.3 電壓驟昇信號波形圖 18
圖2.4 電壓閃爍信號波形圖 19
圖2.5 電力諧波信號波形圖 21
圖3.1 電力暫態信號辨識方式架構圖 25
圖3.2 訊號經過傅利葉轉換於頻域上 25
圖3.3 訊號經過短時傅利葉轉換於時域與頻域上 26
圖3.4 訊號經過小波轉換於尺度域與時間域上 28
圖3.5 函數Ψa,b(t)在固定參數b時的時域-頻域平面解析圖 33
圖3.6 多重解析一階層信號分解架構圖 41
圖3.7 多重解析兩階層信號分解架構圖 41
圖3.8 多重解析三階層信號分解架構圖 42
圖3.9 多重解析三階層信號分解之頻率響應分佈 42
圖4.1 可拓理論架構圖 47
圖4.2 矛盾問題的示意圖 48
圖4.3 不同方向所呈現矛盾問題的示意圖 49
圖4.4 點x與兩區間的位值 59
圖4.5 可拓關聯函數 60
圖4.6 生物神經細胞模型 61
圖4.7 雙層類神經網路(無隱藏層感知機) 64
圖4.8 類神經網路的運算流程圖 67
圖4.9 二維分類問題的示意圖 70
圖4.10 學習率的選擇(過大) 72
圖4.11 學習率的選擇(過小) 72
圖5.1 特徵值擷取方式流程圖 77
圖5.2 電力中斷模擬電路圖 78
圖5.3 電力中斷模擬波形 78
圖5.4 電壓驟昇模擬電路圖 79
圖5.5 電壓驟昇模擬波形 80
圖5.6 電壓驟降模擬電路圖 81
圖5.7 電壓驟降模擬波形 81
圖5.8 電壓閃爍模擬電路圖 82
圖5.9 電壓閃爍模擬波形 83
圖5.10 電力諧波模擬電路圖 84
圖5.11 電力諧波模擬波形 84
圖5.12 正常波形、電壓驟降、電壓驟昇之各階小波能量 89
圖5.13 去除基頻能量之各階小波能量分佈圖 90
圖5.14 本文所提之可拓關聯函數 92
圖5.15 可拓類神經網路的架構 99
圖5.16 可拓距離曲線圖 101
圖5.17 調整權重結果 103
圖5.18 可拓類神經網路訓練疊代曲線(全部事故樣本) 106
圖5.19 可拓類神經網路訓練疊代曲線(二分之一事故樣本) 107
圖5.20 可拓類神經網路訓練疊代曲線(三分之一事故樣本) 108
圖5.21 可拓類神經網路訓練疊代曲線(三分之二事故樣本) 109
圖5.22 可拓類神經網路訓練疊代曲線(四分之一事故樣本) 110
圖5.23 電力品質事故實測波形信號 112
圖5.24 可拓理論辨識系統圖控介面 115
圖5.25 可拓類神經網路辨識系統圖控介面 116

表目錄
表2.1 電力系統電磁現象種類與特性 14
表2.2 電力品質之污染源、影響對象與改善對策分類 22
表4.1 三種不同類型的數學集合 47
表4.2 常用轉換函數 69
表5.1 可拓理論辨識系統之分類和辨識結果(全部事故樣本) 95
表5.2 可拓理論辨識系統之分類和辨識結果(二分之ㄧ事故樣本) 96
表5.3 可拓理論辨識系統之分類和辨識結果(三分之ㄧ事故樣本) 96
表5.4 可拓理論辨識系統之分類和辨識結果(三分之二事故樣本) 97
表5.5 可拓理論辨識系統之分類和辨識結果(四分之ㄧ事故樣本) 97
表5.6 可拓類神經網路辨識系統之分類和辨識結果(全部事故樣本) 106
表5.7 可拓類神經網路辨識系統之分類和辨識結果(二分之一事故樣本) 107
表5.8 可拓類神經網路辨識系統之分類和辨識結果(三分之一事故樣本) 108
表5.9 可拓類神經網路辨識系統之分類和辨識結果(三分之二事故樣本) 109
表5.10 可拓類神經網路辨識系統之分類和辨識結果(四分之一事故樣本) 110
表5.11 辨識系統於實測電壓信號資料之辨識結果 112

[1]W. E. Kazibwe, R. J. Ringlee, G. W. Woodzell, and H. M. Sendaula, “Power Quality: A Review,” IEEE Computer Applications in Power, Vol. 3, No. 1, pp. 39-42, Jan. 1990.
[2]J. W. Gray and F. J. Haydock, “Industrial Power Quality Considerations When Installing Adjustable Speed Drive Systems,” IEEE Trans. on Industry Applications, Vol. 32, No. 3, pp. 646-652, May-June. 1996.
[3]R. C. Lentz, F. J. Mercede, and J. N. Mercede, “A Student Design Project to Improve Power Quality for a Commercial Facility,” IEEE Trans. on Power Systems, Vol. 10, No. 1, pp. 3-10, Feb. 1995.
[4]E. F. Fuchs, D. J. Roesler, and F. Alashhab, “Sensitivity of Home Appliances to Harmonics and Fractional Harmonics of the Power System’s Voltage. Part I: Transformers and Induction Machines,” IEEE Trans. on Power Delivery, Vol. 2, No. 2, pp. 437-444, 1987.
[5]E. F. Fuchs, D. J. Roesler, and K. P. Kovacs, “Aging of Home Appliances Due to Harmonics of the Power System’s Voltage,” IEEE Trans. on Power Delivery, Vol. 1, No. 3, pp. 301-307, 1984.
[6]O. Poisson, P. Rioual, and M. Meunier, “New Signal Processing Tools Applied to Power Quality Analysis,” IEEE Trans. on Power Delivery, Vol. 14, No. 2, pp. 561-566, April 1999.
[7]M. McGranaghan, “Power Quality Standards,” Electrical Contractor Magazine, Power Quality for the Electrical Contractor Course, Electrotek Concepts, Inc., http://www.electrotek.com/.
[8]G. T. Heydt, P. S. Fjeld, C. C. Liu, D. Pierce, L. Tu, and G. Hensley, “Applications of the Windowed FFT to Electric Power Quality Assessment,” IEEE Trans. on Power Delivery, Vol. 14, No. 4, pp. 1411-1416, Oct. 1999.
[9]G. T. Heydt, “A New Method for the Calculation of Subtransmission and Distribution System Transients Based on the FFT,” IEEE Trans. on Power Delivery, Vol. 4, No. 3, pp. 1869-1875, July 1989.
[10]S. Santoso, W. M. Grady, E. J. Powers, J. Lamoree, and B. C. Bhatt, “Characterization of Distribution Power Quality Events with Fourier and Wavelet Transforms,” IEEE Trans. on Power Delivery, Vol. 15, No. 1, pp. 247-254, Jan. 2000.
[11]P. S. Wright, “Short-Time Fourier Transforms and Wigner-Ville Distributions Applied to the Calibration of Power Frequency Harmonic Analyzers,” IEEE Trans. on Instrumentation and Measurement, Vol. 48, No. 2, pp. 475-478, April 1999.
[12]A. M. Gaouda, M. A. Salama, M. R. Sultan, and A. Y. Chikhani, “Power Quality Detection and Classification Using Wavelet- Multiresolution Signal Decomposition,” IEEE Trans. on Power Delivery, Vol. 14, No. 4, pp. 1469-1476, Oct. 1999.
[13]G. T. Heydt and A. W. Galli, “Transient Power Quality Problems Analyzed Using Wavelets,” IEEE Trans. on Power Delivery, Vol. 12, No. 2, pp. 908-915, April 1997.
[14]P. Pillay and A. Bhattachariee, “Application of Wavelets to Model Short-Term Power System Disturbances,” IEEE Trans. on Power System, Vol. 11, No. 4, pp. 2031-2037, November 1996.
[15]W. A. Wilkinson and M. D. Cox, “Discrete Wavelet Analysis of Power System Transients,” IEEE Trans. on Power System, Vol. 11, No. 4, pp. 2038-2044, November 1996.
[16]D. C. Robertson, O. I. Camps, J. S. Mayer, and W. B. Gish, “Wavelets and Electromagnetic Power System Transients,” IEEE Trans. on Power Delivery, Vol. 11, No. 2, pp. 1050-1057, April 1996.
[17]L. Angrisani, P. Daponte, D. Apuzzo, and A. Testa, “A Measurement Method Based on the Wavelet Transform for Power Quality Analysis,” IEEE Trans. on Power Delivery, Vol. 13, No. 4, pp. 990-998, October 1998.
[18]Elmitwally, A. Farghal, S. Kandil, M. Abdelkader, and S. Elkateb, M. “Proposed Wavelet-Neurofuzzy Combined System for Power Quality Violations Detection and Diagnosis,” IEE Proc.-Gener. Transmission and Distribution, Vol. 148, No. 1, pp.15-20, January 2001.
[19]F. Mo and W. Kinsner, “Wavelet Modelling of Transient in Power Systems,” 1997 Conference on Communications, Power and Computing Proceedings; Winnipeg, MB; pp.132-137, May 22-23, 1997.
[20]S. Sannoto, E, J Powers, W. M Grady, and P. Hofmann, “Power Quality Assessment via Wavelet Transform Analysis,” IEEE Trans. on Power Delivery, Vol. 11, No. 2, pp. 924-930, April 1996.
[21]B. Perunicic, M. Mallini, Z.Wang, and T. Liu, “Power Quality Disturbance Detection and Classification Using Wavelets and Artifical Neural Networks,” Harmonics And Quality of Power, 1998. Proceedings. 8th International Conference on, Vol. 1, pp.77-82, 14-16 Oct. 1998.
[22]J. S. Huang, M. Negnevitsky, and T. Nguyen, “A Neural-Fuzzy Classifier for Recognition of Power Quality Disturbances,” IEEE transactions on Power Delivery, Vol. 17, No. 2, pp.609-616, April 2002.
[23]D. Borras, M. Castilla, N. Moreno, and J. C. Montano, “Wavelet and Neural Structure: A New Tool for Diagnostic of Power System Disturbances,” IEEE Transactions on Industry Applications, Vol. 37, No. 1, pp.184-190, Jan./Feb. 2001.
[24]H. W. Dommel, Electromagnetic Transients Program, Reference Manual (EMTP Theory Book), Bonneville Power Administration, Portland, 1986.
[25]J. Arrillaga, B. C. Smith, N. R. Waston, and A. R. Wood, Power System Harmonic Analysis, John Wiley & Sons Ltd., West Sussex, 1995.
[26]IEEE Recommended Practices and Requirements for Harmonic Control in Electrical Power Systems, IEEE Standard 519-1992, IEEE, New York, 1993.
[27]D. E. Newland, “An Introduction to Random Vibrations, Spectral and Wavelet Analysis Longman Scientific & Technical,” England, 1993.
[28]A. Grossman and J. Morlet, “Decompositions of Hardy Functions into Square Integrable Wavelets of Constant Shape,” SIAM Journal of Mathematical Analysis, Vol. 15, No. 4, pp. 723-736, July 1984.
[29]S. Mallat, “A Theory for Multiresolution Signal Decomposition: The Wavelet Representation,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 11, No. 7, pp. 674-693, July 1989.
[30]S. Mallat, “Multifrequency Channel Decomposition of Images and Wavelet Models,” IEEE Trans. Acoust., Speech, Signal Processing, Vol. 37, No. 7, pp. 2091-2110, Dec. 1989.
[31]S. Mallat, “Multiresolution Approximation and Wavelet,” Trans. Am. Mach. Intel., Vol. 135, No. 7, pp. 69-88, 1989.
[32]I. Daubechies, “Orthonormal Bases of Compactly Supported Wavelet,” Communications in Pure Applied Math, Vol. 41, No. 7, pp. 909-996, 1988.
[33]S. Mallat, Multiresolution Representation and Wavelets, Ph.D. Dissertation, University of Philadelphia, Philadelphia, 1988.
[34]M. Kezunovic and L. Yuan, “A Novel Method for Equipment Sensitivity Study during Power Quality Event,” Power Engineering Society Winter Meeting, 2000. IEEE, Vol. 2, pp. 993-998, January 2000.
[35]W. Cai, “The Extension Set and Incompatibility Problem,” J. of Scientific Exploration, Vol. 1, pp.81-93, 1983.
[36]楊春燕、張擁軍、蔡文，“可拓集合及其應用研究”，Mathematic in Practice and Theory, Vol. 32, No. 2, PP. 301-308, March, 2002.
[37]Y. P. Huang and H. J. Chen, “The Extension-Based Fuzzy Modeling Method and Its Applications,” in Proc. IEEE Canadian Conf. on Electrical and Computer Engineering, Edmonton, Alberta, Canada, pp. 977-982, 1999.
[38]M. H. Wang and H. C. Chen, “Application of Extension Theory to the Fault Diagnosis of Power Transformers,” Proceeding of the 22nd Symposium on Electrical Power Engineering, pp.797-800, 2001.
[39]A. Keyhani and S. M. Miri, “Observers for Tracking of Synchronous Machine Parameters and Detection of Incipient Faults,” IEEE Transactions on Energy Conversion, Vol. 1, pp.121-126, 1995.
[40]蔡文、楊春燕、林傳初原著，黃有評、邱紹維、游力川編譯，“可拓工程方法”，全華科技圖書有限公司，2001年。
[41]葉怡成 編著，“類神經網路模式應用與實作”，儒林圖書有限公司，2000年。
[42]Constantin Von and Altrock, “Fuzzy Logic & Neuro Fuzzy Applications Explained,” pp. 57-72, June, 1998.
[43]林昇甫、洪成安 編著，“神經網路入門與圖樣辨識”，全華科技圖書有限公司，2002年。
[44]陳家湧，「類神經網路應用於設備故障診斷之研究」，國立彰化師範大學電機工程學系碩士論文，2006年。
[45]Martin T. Hagan, Howard B. Demuth, and Mark H. Beale, “Neural Network Design,” Theory and Examples, pp. 14-16, 1995.
[46]粘遙輝，「類神經網路於電力品質干擾波形之辨識」，淡江大學電機工程學系(控制系統組)碩士論文，2002年。
[47]林穎駿，「應用小波轉換與類神經網路於電力品質事故之監測與辨識」，中原大學電機工程學系碩士論文，2003年。
[48]A. M. Gaouda, E. F. El-Saadany, M. M. A. Salama, V. K. Sood, and A. Y. Chikihani, “Monitoring HVDC Systems Using Wavelet Multi-Resolution Analysis,” IEEE Transactions on Power System, Vol. 16, pp.662-670, No. 4, November 2001.
[49]M. H. Wang and C. P. Hung, “Extension Neural Network and Its Applications”, Neural Network, Vol. 16, pp.779-784, 2003.
[50]M. H. Wang, “Partial Discharge Pattern Recognition of Current Transformers Using an ENN”, IEEE Transactions on Power Delivery, Vol. 20, No.3, pp.1984-1990, July 2005.