淡江大學機構典藏:Item 987654321/68088
English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 62822/95882 (66%)
造訪人次 : 4028327      線上人數 : 571
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/68088


    題名: 蘭陽溪—水文防洪預測模式之建置
    其他題名: Building a Flood Forecasting Model for Lan-yang River
    作者: 張麗秋;蔡亞欣;邱昱禎;張斐章
    貢獻者: 淡江大學水資源及環境工程學系
    關鍵詞: 調適性網路模糊推論系統;神經網路;水位預測;ANFIS;Neural network;Water level forecasting
    日期: 2005-10-13
    上傳時間: 2011-10-23 09:48:38 (UTC+8)
    出版者: 臺北市:中國農業工程學會
    摘要: 本研究將針對蘭陽溪流域建置一智慧型之河川防災預警系統,預警系統可預報至少未來三小時之水位以作為決策支援。洪水預報的模式以具人工智慧(AI)之類神經網路(Artificial Neural Network)為主,配合水利署水文觀測現代化多工多埠傳輸系統,取得各水文站即時傳回之資料,並加強自動化減少人工輸入使智慧型系統即時預測的能力更加穩健。透過網際網路以Web型式展示即時觀測值及洪水預報功能,達成水文資訊之即時化,以擴大水文資訊之範疇與提昇服務的品質與精確度。研究中分別利用ANFIS 網路模式推估未來一至三小時之河川水位,研究成果顯示,於蘭陽溪流域上游牛鬥橋水位站水文資料有限,使得網路無法得到適度的資訊用來訓練,故效果未如預期;反觀下游蘭陽大橋水位站,其1~3小時的預報則有高度的精確性。
    In this study, the artificial neural networks (ANNs) is used to modelthe multistep ahead rainfall-runoff processes and implemented inLan-yang watershed. For the practicable purpose, the forecasting modeland the coming data are integrated to provide the flood informationfor the decision-maker through on-line facility, such as internet orintranet. In this project, the one-, two-, and three-hour-ahead waterlevels of Lan-yang river basins are forecasted by utilizing ANFISnetwork. The performances can be concluded as follows. In Lan-yangriver basin, due to the limited data in the upstream for training thenetwork, the results are not as agood as expected, while the resultsof one to three hour ahead predictions in downstream Lan-yang gaugestation, which has enough data for training, are highly accuracy.
    關聯: 九十四年度農業工程研討會論文集,12頁
    顯示於類別:[水資源及環境工程學系暨研究所] 會議論文

    文件中的檔案:

    沒有與此文件相關的檔案.

    在機構典藏中所有的資料項目都受到原著作權保護.

    TAIR相關文章

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