現今的工廠與居家之低壓配電線路中都裝設過電流及過載保護裝置，有些特定支路還必須安裝漏電斷路器，來確保用電安全。然而，根據國外調查指出，有些住宅火災發生原因，懷疑是因為電弧故障所引起。電弧故障斷路器(Arc-Fault Circuit Interrupter-AFCI)是一種偵測線路中電弧故障發生的保護裝置，它透過對電弧特性判別來偵測串聯及並聯電弧，在電弧的熱能引起火災前盡早切離電源。本研究針對幾種不同特性的負載，進行串聯電弧故障檢測，經由電弧故障檢測平台蒐集串聯電弧實驗數據，將實驗數據與相關文獻進行電弧的時頻特性比對及驗證，作為電弧故障檢測法的依據。本研究採用兩種策略，分別是頻域特性綜合分析法與小波高頻能量累積法進行訊號處理，並將結果擷取特徵，結合倒傳遞類神經類網路辨識電弧故障。最後，將電弧故障辨識結果與商用AFCI的動作結果進行比較。而研究結果顯示，兩種辨識系統與商用AFCI相比，的確能判斷出發生串聯電弧故障，且誤動作的機率不高。本論文找出的檢測方法未來如能開發使用，應可在電弧的熱能引起火災前儘早切離電源，降低火災的發生率。

For the safe use of electric power, it is important to detect the occurring of line faults on the low voltage power circuits and switch off the power source before the occurring of fires by using protection devices, such as magnetic circuit breakers and leakage current detectors. However, many oversea examples reveal the facts that a number of home fires are caused by electric arc faults. The arc-fault circuit interrupter (AFCI) is a device which can detect the occurring of electric arc faults on the low voltage circuits, and then it can switch off the power source before the occurring of fire. In this study, it is to investigate series arc fault detection of circuits feeding several characteristics of the load. The test data are collected through the arc fault testing platform. The series arc fault will be verified by evaluating the time-frequency characteristics of experimental data and compared with relative literature. This study proposes two strategies for the signal processing of experimental data, and then building the extracted features based on the results. These extracted features are applied to artificial neural network (ANN) for recognition of arc fault. Finally, the experimental data with series arc faults are used to test the detecting methods and compare with the commercial devices. As the results of recognition, the purposed recognition systems can effectively detect the occurring of series arc faults, and the probability of malfunction is low.

[1]內政部消防署，http://www.nfa.gov.tw/main/index.aspx。
[2]曾元超，「防範住家電氣火災的新技術」，台電月刊，549期，頁26-31，SEP. 2008。
[3]USFA (USA). Electrical Fire Safety: A Factsheet on Home Electrical Fire Prevention. United States Fire Administration; 2008. http://www.usfa.dhs.gov/citizens/all_citizens/home_fire_prev/electrical.shtm.
[4]Thomas Neesen,“Residential wiring and electrical safety in Europe”, ICF congress Prague, Austria, 2004.
[5]J.M. Martel, M. Anheuser, and F. Berger, “A study of arcing fault in the low-voltage electrical installation,” Proceeding of the 56th IEEE Holm Conference on Electrical Contacts (HOLM), Charleston, South- Carolina, USA, pp. 1-11, 2010.
[6]D. Gregory and W. Scott, “The Arc-Fault Circuit Interrupter: An Emerging Product,” IEEE Transactions on Industry Applications, vol. 34, pp. 928-933, September/October 1998.
[7]E. Restrepo, “Arc Fault Detection and Discrimination Methods,” Proceedings of the 53th IEEE Holm Conference on Digital Object Identifier: Electrical Contacts (HOLM), pp. 115-122, 2007.
[8]D. Li, “A Method for Residential Series Arc Fault Detection and Identification,” Proceedings of the 55th IEEE Holm Conference on Digital Object Identifier: Electrical Contacts, pp. 4013–4016, 2009.
[9]H. Cheng, X. Chen, F. Liu, and C. Wang, “Series Arc Fault Detection and Implementation Based on The Short-time Fourier Transform,” Proceeding of the Asia-Pacific Digital Object Identifier: Power and Energy Engineering Conference (APPEEC), pp. 1-4, 2010.
[10]P. Muller, S.Tenbohlen, R. Maier, and M. Anheuser, “Artificial Low Current Arc Fault for Pattern Recognition in Low Voltage Switchgear,” Proceedings of the 55th IEEE Holm Conference on Digital Object Identifier: Electrical Contacts, pp. 15-21, 2009.
[11]P. Muller, S. Tenbohlen, and M. Anheuser, “Artificial Low Current of Series and Parallel Low Current Arc Faults in the Time and Frequency Domain, ” Proceedings of the 56th IEEE Holm Conference on Digital Object Identifier: Electrical Contacts (HOLM), pp. 1-7, 2010.
[12]Z. Ruixiang and S. Zhengxiang, “Arc Fault Detection Method Based on Signal Energy Distribution in Frequency Band,” Proceedings of the Asia-Pacific Conference on Power and Energy Engineering, Shanghai, China, pp. 1-4, March, 2012.
[13]X. Liu, C. Hou, X. Leng, and Z. Lai, “Arc fault diagnosis and analysis based on wavelet neural network,” Proceedings of 2011 1st International Conference on Electric Power Equipment - Switching Technolog, Xi’an, China, pp. 187-190, October, 2011.
[14]S. Ma and L. Guan, “Arc-Fault Recognition Based on BP Neural Network,” Proceedings of 2011 Third International Conference on Measuring Technology and Mechatronics Automation, Shanghai, China, pp. 584-586, January, 2011.
[15]R. Michael, S. Patrick, and T Etienne, “Method to Design Arc Fault Detection Algorithm Using FPGA,” Proceedings of the 57th IEEE Holm Conference on Digital Object Identifier: Electrical Contacts (HOLM), pp. 1-5, 2011.
[16]鄭惠翔，「低壓電弧故障斷路器用訊號檢測」，碩士論文，國立台灣科技大學碩士論文，民國99年。
[17]簡佑倫，「低壓線路串聯電弧故障檢測」，碩士論文，國立台灣科技大學碩士論文，民國100年。
[18]王奕捷，「低壓線路串聯電弧故障時域及頻域分析與檢測」，碩士論文，國立台灣科技大學碩士論文，民國101年。
[19]D. Gregory, K. Wong, and F. Dvorak, “More About Arc-Fault Circuit Interrupters,” IEEE Transactions on Industry Applications, vol. 40, pp. 1006-1011, July/August 2004.
[20]Arc-Fault Circuit Interrupter, UL Standard 1699-2008, Illinois, U.S.A, 2008.
[21]傅祖勳，「電力品質資料分析與壓縮」，博士論文，國立台灣科技大學博士論文，民國91年。
[22]高志、余嘯海著，MATLAB小波分析工具箱處理與應用，國防工業出版社 民國93年。
[23]Daubechies, I., Ten Lectures on Wavelet, SIAM, CBMS series (1922).
[24]L. J. Hadjileontiadis, D. A. Patakas, N. J. Margaris, and S. M. Panas, “Separation of crackles and squawks from vesicular sounds using a wavelet-based filtering technique,” COMPEL, vol. 17, pp. 649–657, 1998.
[25]張德丰，「詳解MATLAB數字信號處理」，電子工業出版社，民國99年。
[26]張斐章、張麗秋和黃浩倫，「類神經活用理論與實務」，東華書局，民國93年。
[27]周鵬程，「類神經活用Matlab」，全華圖書股份有限公司，民國95年。
[28]王進德，「類神經網路與模糊控制理論入門與應用」，全華圖書股份有限公司，民國100年。