近年來,台灣跨河橋梁每逢颱風來襲時常有斷橋之疑慮,為確保橋梁上行人及車輛安全,橋梁預警的發展日趨重要。在橋梁預警中,洪水位的預報是一大重要環節,因此,本研究目的為建立一套有系統且完整的橋梁水位預測模式。 本研究以新海大橋為案例,收集1996-2010年侵台颱風資料,利用遺傳演算法結合輻狀基底函數類神經網路(GA-RBFNN)建立新海大橋水位模式,預測未來一~三小時之橋梁水位。 GA-RBFNN模式使用三鶯大橋水位、石門水庫放流量、上游三個雨量站資料以及下游淡水河口水位為輸入資料,輸出資料為新海大橋預測水位。 預測未來一小時水位精確度CC值可達0.984,預測未來三小時精確度CC值也在0.7以上,皆有不錯的預測結果;研究成果可望為橋梁安全預警所使用。
Recently, there are worried about the collapsed of bridges in Taiwan during Typhoons period. To ensure the safety of the people and vehicles on the bridges, it’s getting important to develop a safety warning system of bridges. Water level prediction is one of the most important parts in this system. Therefore, This study for establishing a systematic model of integrated performance for the water level forecasting models. In this study, choosing Xin-hai Bridge as study case. Collecting typhoon data in Taiwan during 1996 to 2010. Using Radial Basis Function Neural Network to create Xin-hai Bridge water level forecasting mode combined with Genetic Algorithms (GA-RBFNN) to forecast water level of Xin-hai Bridge after one to three hours. In GA-RBFNN mode, choosing water level of San-ying Bridge, Shi-men Reservoir releasing, three rainfall stations data of upstream and tidal at estuary of Tam-sui River as input data, and the output data are the prediction of water level for Xin-hai Bridge. The result of prediction at one hour later, the Correlation Coefficient is up to 0.984. And the results of prediction at three hours later, the Correlation Coefficient were higher than 0.7, the prediction data were nearly successful achievement. The result of study is expected to be used for safety warning system of bridges in the future.