Please use this identifier to cite or link to this item:
標題: 類神經網路在暴風型海灘斷面預測之應用
Prediction of Storm-Built Beach Profile Using Artificial Neural Network
作者: 潘冠龍
Pan, Kuan-Long
關鍵字: Artificial Neural Network;類神經網路;Storm-Built Beach;暴風型海灘
出版社: 土木工程學系
本文旨在利用倒傳遞網路,建立暴風型海灘斷面之預測模式。研究中係以往昔文獻於大型波浪試驗水槽所得之18組暴風型海灘斷面實驗資料作為類神經網路的學習,並藉由學習過程調整各人工神經元相關之權重,使預測值與實際值的誤差達到最小化,同時以求得之權重進行演算,由類神經網路之回想過程輸入波浪資料如深海入射波高、週期、底質粒徑、底質沈降速度、原始坡度等四種參數即可預測暴風型海灘斷面重要之物理參數及剖面形狀。研究顯示,由於類神經網路模式具有解決非線性問題的能力,於暴風型海灘剖面重要物理參數剖面形狀之預測上,由本研究與Silvester and Hus(1993)和Hus and Wang(1997)比較的結果,本模式的預測效果可獲得最佳之準確度。在暴風型海灘剖面形狀的預測上,到傳遞類神經網路模式亦有良好的預測表現。

This study aims to investigate the applicability of the artificial neural network for predicting the major pertinent parameters of a storm-built beach profile. The prediction model is performed from learning 18 model bar profiles selected from previous large wave tank test. A back-propagation procedure was used to adjust the weights of the connections in the neural network and to minimize the error between the desired outputs and the observed values.
Base on the proposed neural network model, the major geometric parameters for a storm-built bar are predicted well as the wave condition is given. The results show that the neural network model works better then the previous empirical predictions of Silvester and Hsu (1993) and Hsu and Wang (1997). In addition, the neural network also has good performance in the prediction of the storm-built beach profile.
Appears in Collections:土木工程學系所

Show full item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.