簡易檢索 / 詳目顯示

研究生: 蔡承諾
Cheng-no Tsai
論文名稱: 應用貝氏分類器與訊號處理技術於串聯電弧故障檢測
Application of Bayesian Classifier and Signal Processing Technology to Detection of Series Arc Fault
指導教授: 吳啟瑞
Chi-Jui Wu
口試委員: 吳啟瑞
Chi-Jui Wu
李尚懿
San-Yi Lee
郭明哲
Ming-Tse Kuo
關錦龍
Jin-Lung Guan
學位類別: 碩士
Master
系所名稱: 電資學院 - 電機工程系
Department of Electrical Engineering
論文出版年: 2023
畢業學年度: 111
語文別: 中文
論文頁數: 176
中文關鍵詞: 串聯電弧電弧檢測小波轉換傅立葉轉換帶通濾波器貝氏分類器機率類神經
外文關鍵詞: Series Arc, Arc Detection, Wavelet Transform, Fourier Transform, Bandpass Filter, Bayesian classifier, Probabilistic Neural Network
相關次數: 點閱:239下載:4
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 依據國外調查指出,當低壓線路發生電弧故障時,若未及時將故障清除,則電弧產生的高溫與火花可能會對電器設備造成損害,甚至燃起周遭的易燃物,導致發生火災。因此電弧故障為家庭電氣火災事件之主要原因之一,需慎重看待。本論文建立低壓交流串聯電弧與直流串聯電弧實驗平台,針對線路中供應不同特性的家電負載進行串聯電弧故障實驗。首先使用小波轉換、快速傅立葉轉換與帶通濾波器訊號處理技術,先取得線路電流特徵向量。再使用Python軟體撰寫貝氏分類器與機率類神經(probabilistic neural network,PNN)兩種檢測法作為串聯電弧故障檢測,並與商用電弧斷路器(arc fault circuit interrupter,AFCI)與商用電弧故障偵測器(arc fault detector,AFD)進行比較。由測試結果顯示,當線路在正常運轉與發生串聯電弧故障時,在線路供應於某些負載且發生串聯電弧故障時,貝氏分類器有出現誤判的情形,但其仍為廣泛使用的分類器之一,訓練速度快,達到省時且精準的檢測結果。


    According to foreign research, when an arc fault occurs on low voltage circuit and is not cleared immediately, the high temperature and sparks generated by the arc may cause damage to electrical equipment and even ignite flammable materials around it, leading to a fire. Therefore, arc faults are one of the main reasons for household electrical fires and should be prevented. This thesis establishes an experimental platform for AC and DC series arc and conducts arc fault experiments on household electrical loads with different characteristics supplied on low voltage circuit. First, signal processing techniques such as wavelet transform, fast fourier transform, and band pass filters are used to obtain the eigenvector of the circuit current. Then, the Bayesian classifier and the probabilistic neural network (PNN) are two detection methods written in Python software, compared with commercial arc-fault circuit interrupter (AFCI) and arc-fault detector (AFD). The test results show when the circuit operating normally or occuring series arc faults on certain loads are supplied, the Bayesian classifier may be misjudgments, but it is one of the widely used classifiers with fast training speed and accurate detection results, achieving time-saving and precise detection.

    摘要 Abstract 誌謝 目錄 圖目錄 表目錄 第一章 緒論 1.1 研究背景與動機 1.2 文獻探討 1.3 研究內容 1.4 章節敘述 第二章 串聯電弧故障特性與實驗設備 2.1 前言 2.2 電弧故障類型與特性 2.2.1 電弧 2.2.2 電弧故障種類 2.2.3 交流電力系統電弧故障 2.2.4 交流串聯電弧故障之時頻特性 2.2.5 直流電力系統電弧故障 2.2.6 直流串聯電弧故障之時頻特性 2.2.7 交流串聯電弧與直流串聯電弧之比較 2.3 交流電弧與直流電弧之相關標準 2.3.1 UL1699與NEC210.12 2.3.2 NEC690.11與用戶用電設備裝置規則 2.3.3 UL1699B 2.4 商用電弧故障保護裝置 2.4.1 商用交流電弧故障保護裝置 2.4.2 商用直流電弧故障保護裝置 2.5 電弧故障實驗設備與實驗方法 2.5.1 實驗設備 2.5.2 交流串聯電弧故障實驗方法 2.5.3 直流串聯電弧故障實驗方法 2.6 小結 第三章 串聯電弧故障電流波形訊號處理 3.1 前言 3.2 線路電流訊號取樣設定 3.3 傅立葉轉換 3.3.1 離散傅立葉轉換 3.3.2 快速傅立葉轉換 3.3.3 串聯電弧故障線路電流之快速傅立葉分析 3.4 小波轉換 3.4.1 離散小波轉換 3.4.2 小波多層解析 3.4.3 串聯電弧故障線路電流之小波多層分析 3.5 帶通濾波器 3.5.1 原理 3.5.2 串聯電弧故障線路電流之橢圓帶通濾波器分析 3.6 高頻能量累積值 3.7 小結 第四章 貝氏分類器與機率類神經檢測法 4.1 前言 4.2 貝氏分類器 4.2.1 貝氏定理 4.2.2 分類原理與訓練流程 4.2.3 貝氏分類器判斷流程 4.3 機率類神經網路檢測法 4.3.1 機率類神經網路訓練流程 4.3.2 機率類神經網路訓練模組參數 4.3.3 機率類神經網路判斷流程 4.4 小結 第五章 低壓交流線路串聯電弧故障檢測結果 5.1 前言 5.2 線路供應負載檢測結果 5.2.1 負載一:吹風機 5.2.2 負載二:17顆省電燈泡 5.2.3 負載三:吹風機與17顆省電燈泡 5.2.4 負載四:7顆省電燈泡與17顆省電燈泡 5.2.5 負載五:吹風機與電鍋 5.2.6 負載六:17顆省電燈泡與100 uF電容 5.2.7 負載七:吹風機與100 uF電容 5.2.8 負載八:混合負載 5.3 交流串聯電弧故障檢測結果比較 5.4 小結 第六章 低壓直流線路串聯電弧故障檢測結果 6.1 前言 6.2 線路供應電阻負載檢測結果 6.2.1 不同電源電壓與線路電流大小 6.2.2 不同導線長度 6.3 線路供應透過切換式逆變器接市電 6.3.1 不同電源電壓與線路電流大小 6.3.2 不同導線長度 6.4 線路供應透過線性式逆變器接交流電阻負載 6.4.1 不同線路電流大小 6.4.2 不同導線長度 6.5 直流串聯電弧故障檢測結果比較 6.6 小結 第七章 結論與未來研究方向 7.1 結論 7.2 未來研究方向 參考文獻

    [1]內政部消防署,111年1至12月全國火災次數起火原因及火災損失統計,https://www.nfa.gov.tw/cht/index.php。
    [2]R. Campbell, “Home electrical fires,” National Fire Protection Association(NFPA), November, 2021.
    [3]UL 1699, STANDARD FOR SAFETY Arc-Fault Circuit-Interrupters, Underwriters Laboratories Inc, May 3, 2017.
    [4]D. A. Dini, P. W. Brazis, and K.-H. Yen, “Development of arc-fault circuit-interrupter requirements for photovoltaic systems,” 2011 37th IEEE Photovoltaic Specialists Conference, Seattle, WA, USA, pp. 1790-1794, June, 2011.
    [5]W. Miao, Z. Wang, F. Wang, K. H. Lam, and P. W. T. Pong, “Multicharacteristics arc model and autocorrelation-algorithm based arc fault detector for DC microgrid,” IEEE Transactions on Industrial Electronics, vol. 70, no. 5, May, 2023.
    [6]Q. Xiong, X. Liu, A. L. Gattozzi, Y. Shi, L. Zhu, S. Ji, and R. E. Hebner,
    “Arc fault detection and localization in photovoltaic systems using feature distribution maps of parallel capacitor currents” IEEE Journal of Photovoltaics, vol. 8, no. 4, July, 2018.
    [7]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, Charleston, SC, USA, October, 2010.
    [8]T. Taufik, C. Aarstad, and A. Kean, “Arc Fault Characterization System for the Low Voltage DC Arc Fault Circuit Interrupter,” 2017 25th International Conference on Systems Engineering, Las Vegas, NV, USA, October, 2010.
    [9]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, Harbin, China, July,2017.
    [10]J. Johnson, B. Pahl, C. Luebke, T. Pier, T. Miller, J. Strauch, S. Kuszmaul, and W. Bower, “Photovoltaic DC arc fault detector testing at Sandia National Laboratories,” 2011 37th IEEE Photovoltaic Specialists Conference, June, 2011.
    [11]J. Johnson, S. Kuszmaul, W. Bower, and D. Schoenwald, “Using PV module and line frequency response data to create robust arc fault detectors,” 2011 26th European Photovoltaic Solar Energy Conference and Exhibition, Hamburg, Germany, September, 2011.
    [12]Y. Zhao, X. Zhang, Y. Dong, and W. Li, “Characteristics analysis and detection of AC arv fault in SSPC based on wavelet transform,” 2016 IEEE Internation Conference on Aircraft Utility Systems(AUS), Beijing, China, pp. 476-481, 2016.
    [13]S. Chen, Y. Wang, Y. Meng, X. Li, and S. Ge, “The influence of time-frequency transforms on AC and DC arc fault signal representation,” 2022 IEEE 67th Holm Conference on Electrical Contacts (HLM), Tampa, FL, USA, October, 2022.
    [14]H. Cheng, X. Chen, F. Liu, and C. Wang, “Series arc fault detection and implementation based on the short-time fourier transform,” 2010 Asia-Pacific Power and Energy Engineering Conference, Chengdu, China, March, 2010.
    [15]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。
    [16]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, March, 2012.
    [17]張鶴亭,應用類神經網路與訊號處理技術於低壓線路串聯電弧故障檢測,碩士學位論文,國立臺灣科技大學,臺北,2022。
    [18]鄭家誠,應用電流失真功率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,2020。
    [19]M.Naidu, T.J. Schoepf, and S. Gopalakrishnan, “Arc fault detection scheme for 42-V automotive DC networks using current shunt,” IEEE Transactions on Power Electronics, vol. 21, no. 3, May, 2006.
    [20]蔡佳縉,應用支持向量機於直流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。
    [21]賴德欣,設計一直流串聯電弧故障偵測器於太陽光電系統之保護,碩士學位論文,國立臺灣科技大學,臺北,2017。
    [22]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。
    [23]陳又琨,應用小波轉換於直流電力系統之串聯電弧故障偵測,碩士學位論文,國立臺灣科技大學,臺北,2014。
    [24]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。
    [25]F. Wang, Z. Wang, and W. Miao, “Characteristic study and non-invasive detection of DC arc-fault in microgrid,” 2021 6th International Conference on Power and Renewable Energy (ICPRE), Shanghai, China, September, 2021.
    [26]F. M. Uriarte, A. L. Gattozzi, J. D. Herbst, H. B. Estes, T. J. Hotz, A. Kwasinski, and R. E. Hebner, “A DC arc model for series faults in low voltage microgrids,” IEEE Transactions on Smart Grid, vol. 3, no. 4, December, 2012.
    [27]X. Yao, L. Herrera, S. Ji, K. Zou, and J. Wang, “Characteristic study and time-domain discrete-wavelet-transform based hybrid detection of series DC arc faults,” IEEE Transactions on Power Electronics, vol. 29, no. 6, June, 2014.
    [28]NEC Section 690.11 Arc Fault Cricuit Protection, National Electrical Code, 2011.
    [29]「用戶用電設備裝置規則」,中華民國經濟部,三月,民國110年。
    [30]UL 1699B, Outline of Investigation for Photovoltaic(PV) Dc Arc-Fault Circuit Protection, Issue Number 1, Underwriters Laboratories Inc., April, 2011.
    [31]NEC Section 690.11 Arc Fault Cricuit Protection, National Electrical Code, 2011.
    [32]5SM Arc Fault Detection Unit for Photovoltaics, Siemens, April, 2015.
    [33]Firefighter Switch with Arc Fault Detection PVSEC-AF, E-T-A Engineering Technology, USA, pp. 1-6, 2015.
    [34]B. Novak, Implementing Arc Detection in Solar Applications: Achieving Compliance with the New UL 1699B Standard, Texas Instruments, August, 2012.
    [35]K. J. Lippert and T. A. Domitrovich, “AFCIs-from a standards perspective,” IEEE Transactions on Industry Applications, vol. 50, no. 2, pp. 1478-1482, Mar/Apr, 2014.
    [36]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, Jul-Aug, 2004.
    [37]A. V. Oppenheim and R. W. Schafer, Discrete-Time Signal Processing. 3rd edition, Prentice Hall, 2010.
    [38]劉鈺韋,運用小波轉換與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。
    [39]江國銘,以FPGA為設計晶片之電壓閃爍計算,碩士學位論文,國立臺灣科技大學,臺北,2011。
    [40]林銀議,信號與系統,五南圖書出版股份有限公司,2009。
    [41]K. Sayood, Introduction to Data Compression, 2nd edition, Morgan Kaufmann, California, USA, 2000.
    [42]R. M. Rao and A. S. Bopardikar, Wavelet Transfrom: Introduction to Theory and Applications, Addison-Wesley, California, USA, 1998.
    [43]W. G. Morsi, and M. E. EI-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, Jul. 2007.
    [44]陳慶芳,心音訊號之分割與特徵擷取,碩士學位論文,義守大學,高雄,2012。
    [45]余兆棠、陳順智,數位信號處理-使用MATLAB,新加坡商亞洲湯姆國際出版有限公司,2000。
    [46]程佩青,數字信號處理教程(第五版),清華大學出版社,2011。
    [47]黃子庭,應用基因演算法於單純貝氏分類器預測之研究,碩士學位論文,元智大學,桃園,2021。
    [48]姚昌辰,以最小平均平方學習法增強貝氏分類器之研究,碩士學位論文,國立臺灣科技大學,台北,2014。
    [49]張結雄,使用主成分分析及貝氏網路方法於離子植入製程之錯誤偵測與診斷,碩士學位論文,國立交通大學,新竹,2001。

    QR CODE