輻狀基底函數類神經網路結合遺傳演算法於河川水位預測之應用

Application of Radial Basis Function Neural Network combined with Genetic Algorithms for river stage prediction

紀昀(Yun Ji)

指導教授 ： 王安培

中原大學/工學院/土木工程研究所/碩士(2013年)

https://doi.org/10.6840/CYCU.2013.00388

摘要

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。

關鍵字

水位預測 ； 輻狀基底函數類神經網路 ； 遺傳演算法

並列摘要

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.

並列關鍵字

Water level prediction ； Genetic Algorithms (GA) ； Radial Basis Function Neural Network(RBFNN)

參考文獻

14. 王安培、張天豪、吳建宏，2009，「模糊決策在洪水期間橋梁安全預警系統之應用－以新海大橋為例」，第17屆模糊理論及其應用研討會，p327-332。

31. 張大元，2003，「類神經網路在水庫放流對河川水位增量之研究」，中原大學土木工程學系，碩士論文。

32. 張天豪，2010，「風險管理在橋梁安全預警之應用－以東勢大橋為例」，中原大學土木工程學系，碩士論文。

34. 張斐章、張雅婷、張麗秋，2004，「結合人工智慧與專家知識之智慧型水庫操作系統」，農業工程學報，第50卷，第4 期，p. 14～27。

1. Alvisi, S. *, Franchini, M.,2011,’’ Fuzzy neural networks for water level and discharge forecasting with uncertainty’’, Environmental Modelling & Software , Vol.26,p523-537.