臺灣國際港區船舶動態管理特性及颱風波浪資料補遺研究(I)

Abstract

本計畫利用花蓮港港務局所提供85年~92年之船隻動態記錄，分析異常波浪與颱風對港內外造成的影響，並從波浪之觀測與船舶動態資料分析並建立預警模式予以港灣管理單位做即時的判斷與反應。另外，在颱風強大的波浪作用下，量測儀器可能受損或遺失，導致量測資料失去連續性，使得估計的設計波浪發生誤差，所以必須建立精確的資料補遺系統，以為港灣擴建發展及防災的重要依據。所以本次計畫將利用類神經網路等技術，建立一個以台灣港灣為主的颱風波浪、暴潮與船舶動態關係之模式，並針對颱風動態參數與觀測資料進行統計分析與分類，以期能建立有系統之颱風波浪、暴潮資料補遺，並藉由相關颱風與船舶資料之模式，進而能提高預警防災的能力。

An ANN alert model of ship escape from Hua-Lien harbor during typhoon period will be developed in this project. The conditions of official annual ship escape reports from 1996 to 2003 are collected and classified into four grades and related to the corresponding typhoon position and scale. Typhoon？HH？HHs path, scale, maximum wind speed and position are the dominant affecting factors to be the input parameters in the present ANN model. Another aims of this project is to hindcast the missing data of typhoon waves due to instrument loss or damages. The missing data maybe happen at the time of the strongest typhoon that can cause the maximum wave heights. Thus, it is very important to evaluate the possible maximum wave heights during the period of each typhoon, even when the instrument for waves is not workable. The integrated ANN model has some functions that are to calculate typhoon？HH？HHs wave, storm surge; to hindcast the missing wave or tidal data; and to alarm the ship to escape from Hua-Lien harbor. The proposed integrated ANN alarm model can provide a good reference for harbor managements on ship mooring safety and is available for reducing harbor damages due to the typhoons.