English  |  正體中文  |  简体中文  |  Items with full text/Total items : 888/888 (100%)
Visitors : 13710012      Online Users : 278
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://ccur.lib.ccu.edu.tw/handle/A095B0000Q/405


    Title: 結合頻譜分析與機器學習方法檢測配電系統之故障位置;A Hybrid Approach for Locating Fault in Distribution System by Measured Frequency Spectra and Learning Algorithm
    Authors: 范維福;Pham, Duy Phuoc
    Contributors: 電機工程研究所
    Date: 2017
    Issue Date: 2019-07-17
    Publisher: 電機工程研究所
    Abstract: Locating the fault in a distribution system is still a challenging reliability issue. It is due to not only the complicated topology such as unbalanced system, DG integration, shunt and series compensation, and laterals but also some fault location parameters such as load variation, fault inception angle (FIA), fault resistance and the presence of DG integration. This thesis proposes an algorithm in which fault location is found by using the hybrid approach of signal analysis approach and learning based approach. The transient signal recorded at the substation will be transferred to the frequency domain by Fourier transform. The frequency spectrum at each location is different due to the system configuration. Support vector machine classifier and regression analysis are used to recognize the fault area and distance, respectively. Particle swarm optimization is used to optimize the parameters of the learning algorithm. Time series forecasting technique ARIMAX is used to forecast short-term load profile in order to select the appropriate model. The simulations have modeled in ATP/EMTP according to IEEE 34-bus, 123-bus benchmark test feeder and Taipower’s distribution system. Test results show that frequency spectrum can overcome most aforementioned obstacles with high accuracy for detecting fault location.
    Locating the fault in a distribution system is still a challenging reliability issue. It is due to not only the complicated topology such as unbalanced system, DG integration, shunt and series compensation, and laterals but also some fault location parameters such as load variation, fault inception angle (FIA), fault resistance and the presence of DG integration. This thesis proposes an algorithm in which fault location is found by using the hybrid approach of signal analysis approach and learning based approach. The transient signal recorded at the substation will be transferred to the frequency domain by Fourier transform. The frequency spectrum at each location is different due to the system configuration. Support vector machine classifier and regression analysis are used to recognize the fault area and distance, respectively. Particle swarm optimization is used to optimize the parameters of the learning algorithm. Time series forecasting technique ARIMAX is used to forecast short-term load profile in order to select the appropriate model. The simulations have modeled in ATP/EMTP according to IEEE 34-bus, 123-bus benchmark test feeder and Taipower’s distribution system. Test results show that frequency spectrum can overcome most aforementioned obstacles with high accuracy for detecting fault location.
    Appears in Collections:[電機工程研究所] 學位論文

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML263View/Open


    All items in CCUR are protected by copyright, with all rights reserved.


    版權聲明 © 國立中正大學圖書館網頁內容著作權屬國立中正大學圖書館

    隱私權及資訊安全政策

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback