根據國外研究指出，低壓交流線路中，電弧事故所引起的火災為電氣火災主要的原因之一。若能及時檢測出電弧故障，中斷故障區域，可以大幅減少電氣火災的發生。本論文藉由電弧故障檢測平台，針對線路中供應不同特性的家電負載進行電弧故障的實驗，利用快速傅立葉轉換分析電弧發生時在線路電流之時域與頻域的特性。本文再透過小波轉換及計算電流失真功率作為判斷是否發生串聯電弧故障之特徵向量。最後本文使用Keras與Matlab兩種程式庫，分別使用五層隱藏層與三層隱藏層類神經網路，將特徵向量分別於兩種類神經檢測法進行檢測後比較。研究結果顯示，Keras程式庫之五層隱藏層類神經模型判斷電弧故障較為準確，且此程式碼使用開放式程式庫，對於日後軟硬體開發時，更方便使用。

According to foreign investigations, arc faults are one of the main causes of electrical fires. If arc faults can be detected in time, the occurrence of electrical fires can be greatly reduced. In this thesis, the arc faults detection platform is used to conduct experiments on low voltage AC circuits with household appliances of different characteristics. The fast Fourier transform (FFT) is used to analyze the time domain and frequency domain characteristic of the line current when arc occurs. In this thesis, the discrete wavelet transform (DWT) and current distortion power are used as the eigenvectors for detecting whether a series arc faults occurs. Two neural network algorithms, Keras and Matlab, are be compared in detection. Research results show that the Keras library is more accurate, and it’s codes are open access. It is more convenient to use it to develop software and hardware in the future.

[1] 內政部消防署，「106-109年全國火災次數起火原因及火災損失統計表」，https://www.nfa.gov.tw/cht/index.php
[2] National Fire Protection Association (NFPA),“Home Electrical Fires,’’ https://www.nfpa.org/-/media/Files/News-and-Research/Fire-statistics-and-reports/US-Fire-Problem/Fire-causes/osHomeElectricalFires.pdf
[3] Arc-Fault Circuit Interrupters, UL Standard 1699-2008, 2008.

[4] K. Zeng, L. Xing, Y. Zhang, and L. Wang, “Characteristics analysis of AC arc fault in time and frequency domain,”2017 Prognostics and System Health Management Conference (PHM-Harbin),Harbin,China,pp.1-5, July, 2017.

[5] P. Muller, S. Tenbohlen, R. Maier, and M. Anheuser, “Characteristics of series and parallel low current arc faults in the time and frequency domain,”2010 Proceedings of the 56th IEEE Holm Conference on Electrical Contacts,SC,USA, pp. 1-7, October, 2010.

[6] C. Hong, C. Xiaojuan, X. Wei, and W. Cong,“Short-time fourier transform based analysis to characterization of series arc fault,”2009 2nd International Conference on Power Electronics and Intelligent Transportation System (PEITS), Shenzhen, China, pp. 185-188, December, 2009.

[7] 趙尚程、張認成、杜建華、楊凱、潘冷，「採用小波變換的光伏串聯電弧故障檢測」，華僑大學學報，第38卷，第1期，第7-12頁，2017。
[8] 劉曉明、趙洋、曹雲東、侯春光、王麗君，「基於小波變換的交流系統串聯電弧故障診斷」，電工技術學報，第29卷，第1期，第10-17頁，2014。
[9] C.H. Kim, H. Kim, Y.H. Ko, S.H. Byun, R. Aggarwal, and A.T. Johns,“A novel fault-detection technique of high-impedance arcing faults in transmission lines using the wavelet transform,”IEEE Transactions on Power Delivery ,vol. 17, no. 4, pp. 921-929, October, 2002.
[10] R. Zhang and Z. Song,“Arc fault detection method based on signal energy distribution in frequency band,”2012 Asia-Pacific Power and Energy Engineering Conference, Shanghai, China ,pp. 1-4, March 2012.
[11] C. E. Restrepo,“Arc fault detection and discrimination methods,” Electrical Contacts-2007 Proceedings of the 53rd IEEE Holm Conference on Electrical Contacts, PA, USA, pp. 115-122, September ,2007.
[12] C. Xiaochen, W. Li, S. Qiangang, and M. Zhen,“AC arc fault detection based on Mahalanobis Distance,”2012 15th International Power Electronics and Motion Control Conference (EPE/PEMC), Novi Sad, Serbia ,pp. DS3b. 13-1-DS3b. 13-6, September, 2012.
[13] Y. Zhao, X. Zhang, Y. Dong, and W. Li,“Characteristics analysis and detection of AC arc fault in SSPC based on wavelet transform,”2016 IEEE International Conference on Aircraft Utility Systems (AUS), Beijing, China,pp. 476-481, October ,2016.
[14] M.A.Abdulrachman, E.Prasetyono, D.O.Anggriawan, and A.Tjahjono,“Smart detection of AC series arc fault on home voltage line based on fast fourier transform and artificial neural network,”2019 International Electronics Symposium (IES), Surabaya, Indonesia , pp. 439-445, September, 2019.
[15] 王奕捷，「低壓線路串聯電弧故障時域及頻域分析與檢測」，碩士學位論文，國立臺灣科技大學，臺北，2012。
[16] 洪晨軒，「低壓屋內配線串聯電弧故障檢測與辨識」，碩士學位論文，國立臺灣科技大學，臺北，2013。
[17] 史明哲，「應用模糊理論與類神經網路於低壓線路電弧故障檢測」，碩士學位論文，國立臺灣科技大學，臺北，2015。
[18] 鄭惠翔，「低壓電弧故障斷路器用訊號檢測」，碩士學位論文，國立臺灣科技大學，臺北，2010。
[19] 林以樵，「應用決策樹於交流電路串聯電弧故障檢測與FPGA晶片設計」，碩士學位論文，國立臺灣科技大學，臺北，2019。
[20]鄭家誠，「應用電流失真功率於電路串聯電弧故障檢測
PGA晶片設計」，碩士學位論文，國立臺灣科技大學，臺北，2020。
[21] IEEE Standard Definitions for the Measurement of Electric Power Quantities Under Sinusoidal, Nonsinusoidal, Balanced, or Unbalanced Conditions, IEEE Standard 1459-2010, March ,2010.
[22] TensorFlow，TensorFlow Core，https://www.tensorflow.org/tutorials
[23] NFPA 921 Guide for Fire and Explosion Investigations, National Fire Protection Association, 2011.
[24] 曾元超，「防範住家電器火災的新技術」，台電月刊，第549期，第26-31頁，2008。
[25] G. D. Gregory and G. W. Scott,“The arc-fault circuit interrupter, an emerging product,”1998 IEEE Industrial and Commercial Power Systems Technical Conference. Conference Record. Papers Presented at the 1998 Annual Meeting (Cat. No. 98CH36202), Edmonton,Canada, pp. 48-55, October ,1998.
[26] G. D. Gregory, K. Wong, and R. F. Dvorak,“More about arc-fault circuit interrupters,”IEEE Transactions on Industry Applications, vol. 40, no. 4, pp. 1006-1011, October, 2003.
[27] K. J. Lippert and T. A.Domitrovich“AFCIs—From a standards perspective,”IEEE Transactions on Industry Applications ,vol. 50, no. 2, pp. 1478-1482, March ,2013.
[28] 劉鈺韋，「運用小波轉換與類神經網路檢測屋內低壓線路串聯電弧故障」，博士學位論文，國立臺灣科技大學，臺北，2015。
[29] 董長虹、高志、於嘯海，「小波分析工具箱原理與應用」，國防工業出版社，2004。
[30] W. G. Morsi and M. E. El-Hawary, “Reformulating Three-Phase Power Components Definitions Contained in the IEEE Standard 1459–2000 Using Discrete Wavelet Transform,” IEEE Transactions on Power Delivery, vol. 22, no. 3, pp. 1917-1925, June ,2007.
[31] S. Mallat, A Wavelet Tour of Signal Processing, Academic Press, San Diego, third edition, 2009.
[32] W. G. Morsi and M. E. El-Hawary, “Reformulation power components definitions contained in the ieee standard 1459-2000 using discrete wavelet transform,” IEEE Transaction on Power Delivery, vol. 22, no. 3, July ,2007.
[33] B. Lubanovic，精通Python 運用簡單的套件進行現代運算 第二版(賴屹民譯)，碁峰資訊股份有限公司，2020。
[34] 葉怡成，「類神經網路應用與實作」，儒林圖書公司，2009。