Artificial Neural Network for Wind Waves Forecasting
碩士 === 國立中興大學 === 土木工程學系 === 90 === Due to the complexity and randomness of the wind waves, the prediction of waves based on the simplified relationship may obtain substantial error. This study attempts to predict the wind waves by applying the technique of an artificial neural network (ANN), in whi...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2002
|
Online Access: | http://ndltd.ncl.edu.tw/handle/34373055654666368224 |
id |
ndltd-TW-090NCHU0015041 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-090NCHU00150412016-06-27T16:09:32Z http://ndltd.ncl.edu.tw/handle/34373055654666368224 Artificial Neural Network for Wind Waves Forecasting 類神經網路在風浪推測上的研究 Chin-Hsien Tsai 蔡慶賢 碩士 國立中興大學 土木工程學系 90 Due to the complexity and randomness of the wind waves, the prediction of waves based on the simplified relationship may obtain substantial error. This study attempts to predict the wind waves by applying the technique of an artificial neural network (ANN), in which the supervised learning models with back-propagation scheme is adopted. The ANN estimates the interconnection weights between the waves and the corresponding wind speeds by training the past records. The topology of the selection of the neurons of input, outputs and the hidden layers is discussed in detail in the study. Using long-term wind and wave data from one of the National Data Buoy Center (NDBC) buoy stations in the Pacific Ocean, this study examined the validity and accuracy of the ANN model. It is found that the six-hourly average significant wave height and the six-hourly maximum significant wave height can be predicted from training the previous eighteen hours data of waves and wind speeds. The results show that the neural network model can well predict a five-days to fifteen-days of waves using a previous 20-days’ records. Ching-Piao Tsai 蔡清標 2002 學位論文 ; thesis 48 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中興大學 === 土木工程學系 === 90 === Due to the complexity and randomness of the wind waves, the prediction of waves based on the simplified relationship may obtain substantial error. This study attempts to predict the wind waves by applying the technique of an artificial neural network (ANN), in which the supervised learning models with back-propagation scheme is adopted. The ANN estimates the interconnection weights between the waves and the corresponding wind speeds by training the past records. The topology of the selection of the neurons of input, outputs and the hidden layers is discussed in detail in the study. Using long-term wind and wave data from one of the National Data Buoy Center (NDBC) buoy stations in the Pacific Ocean, this study examined the validity and accuracy of the ANN model. It is found that the six-hourly average significant wave height and the six-hourly maximum significant wave height can be predicted from training the previous eighteen hours data of waves and wind speeds. The results show that the neural network model can well predict a five-days to fifteen-days of waves using a previous 20-days’ records.
|
author2 |
Ching-Piao Tsai |
author_facet |
Ching-Piao Tsai Chin-Hsien Tsai 蔡慶賢 |
author |
Chin-Hsien Tsai 蔡慶賢 |
spellingShingle |
Chin-Hsien Tsai 蔡慶賢 Artificial Neural Network for Wind Waves Forecasting |
author_sort |
Chin-Hsien Tsai |
title |
Artificial Neural Network for Wind Waves Forecasting |
title_short |
Artificial Neural Network for Wind Waves Forecasting |
title_full |
Artificial Neural Network for Wind Waves Forecasting |
title_fullStr |
Artificial Neural Network for Wind Waves Forecasting |
title_full_unstemmed |
Artificial Neural Network for Wind Waves Forecasting |
title_sort |
artificial neural network for wind waves forecasting |
publishDate |
2002 |
url |
http://ndltd.ncl.edu.tw/handle/34373055654666368224 |
work_keys_str_mv |
AT chinhsientsai artificialneuralnetworkforwindwavesforecasting AT càiqìngxián artificialneuralnetworkforwindwavesforecasting AT chinhsientsai lèishénjīngwǎnglùzàifēnglàngtuīcèshàngdeyánjiū AT càiqìngxián lèishénjīngwǎnglùzàifēnglàngtuīcèshàngdeyánjiū |
_version_ |
1718325284766220288 |