English  |  正體中文  |  简体中文  |  Items with full text/Total items : 52047/87178 (60%)
Visitors : 8718844      Online Users : 163
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU 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://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/54724

    Title: 淹水潛勢圖應用科技之研究-淹水預警系統更新(2/2)
    Authors: 張麗秋;賴進松;潘宗毅
    Contributors: 淡江大學水資源及環境工程系
    Keywords: 淹水潛勢圖;淹水預警系統;類神經網路;Applying potential inundation maps;Inundation warning system;Artificial neural networks
    Date: 2010
    Issue Date: 2011-07-06 22:32:28 (UTC+8)
    Abstract: 本計畫第一年已在宜蘭縣、雲林縣、屏東縣等三個區域進行測試,並完成倒傳遞類神經網路(BPNN)與調適模糊推論系統(ANFIS)對未來1~6小時之淹水預測結果,淹水預測正確率皆以BPNN模式優於ANFIS模式。BPNN模式在三個測試區預測效果不錯,淹水預測正確率大多高於70%;雨型比較法以10種雨型特徵值探討雨型特徵值之線性關係,找出評估雨型因子之線性模式;修正因子推估方法之研擬,則分別以潮汐變化、地形情況、抽水機數等不同之設計情況探討淹水情況之變化,並建立淹水面積及淹水體積與潮汐水位、抽水機數之關係曲線。 本年度計畫將研析預測雨型,並延續第一年度所研擬之淹水預警模式,在全台各縣市選擇1~3個易淹水地區作為預警點,並雨型比較法、BPNN及ANFIS等模式建置降雨-淹水預測模式;修正因子法則以去年研擬方法在宜蘭縣、雲林縣與屏東縣進行測試;為了將本計畫所提出的方法落實於防災預警單位,本年度將建立淹水預警模組與成果展示功能,並製作淹水預警警報單。本年度將全台各縣市測試之研究成果進一步地整理完成一篇期刊論文,並選擇合適的國際期刊(SCI或EI)投稿之,期以更廣泛的接受各界的指教。
    This project had built the back-propagation neural network (BPNN) and the adaptive network-based fuzzy inference system (ANFIS) to forecast one to six-hour-ahead flood depths of the Yilan, Yunlin and Pingtung counties in the first year. The results show the BPNN models perform superior to the ANFIS model and the correct percentages of forecasting inundation are above 70%. The rainfall hyetograph comparative method is to investigate the linear relationship of rainfall characteristics from 10 different rainfall hyetographs and to evaluate the linear model of rainfall hyetograph factors. For the effect of the hydrological and geomorphologic factors, three different tidal waves, different surface features and the different number of pumps were designed to investigate the variation of the inundation area, then to find the curves of the inundation areas and volumes versus tidal waves and the number of pumps. In second year, this project will investigate the forecasted rainfall hyetograph, and build BPNN, ANFIS and rainfall hyetograph comparative models based on the proposed methodologies in the fist year. In each county, one to three security spots will be choice to build the above-mentioned models for forecasting flood depths. Moreover, the effect of the hydrological and geomorphologic factors is tested in Yilan, Yunlin and Pingtung counties. For applicability of the proposed methods, this project will establish the inundation warning system with the display interface, and automatically generate the flood warning reports. Finally, we will submit this methodology to the international journals.
    Appears in Collections:[水資源及環境工程學系暨研究所] 研究報告

    Files in This Item:

    There are no files associated with this item.

    All items in 機構典藏 are protected by copyright, with all rights reserved.

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