Bagged neural network for estimating the scour depth around pile groups
Autor: | Rashed Hosseini, Ramin Fazloula, Mojtaba Saneie, Ata Amini |
---|---|
Rok vydání: | 2017 |
Předmět: |
Pier
Engineering Artificial neural network business.industry 0208 environmental biotechnology 02 engineering and technology Structural engineering Overfitting 020801 environmental engineering 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Geotechnical engineering Sensitivity (control systems) business Pile Water Science and Technology |
Zdroj: | International Journal of River Basin Management. 16:401-412 |
ISSN: | 1814-2060 1571-5124 |
Popis: | Contrary to the single pier, due to the complexity of scour mechanism around pile groups, empirical methods do not give a satisfactory prediction for the scour depth around pier with multiple piles. It was shown recently that artificial neural networks have better prediction performance than empirical methods. In order to exploit the full potential of neural network procedure for predicting scour depth around pile groups, “Bagging” technique is adopted in this paper. The comparison between several different approaches for improving the gener-alization performance of neural networks shows that “Bagging” is the most reliable method. Furthermore, the sensitivity analysis is performed on the data to determine the effect of different inputs on the scour depth around pile groups. This analysis shows that pile diameter and pile spacing are dominant contributors. |
Databáze: | OpenAIRE |
Externí odkaz: |