This paper presents the results of the application of an Artificial Neural Network for the prediction of the wave transmission coefficient from low crested structures. The model essentially works with 13 input parameters, which describe the wave attack conditions and the main feature of the structures. It has been firstly created to estimate the wave reflection coefficient, by training and validating the model against nearly 6’000 data, including a wider range of coastal and harbor structures under perpendicular and oblique wave attacks. Afterwards, the Artificial Neural Network has been employed for the prediction of the wave transmission coefficient, by training it against 3’379 additional tests on low crested structures. The results of this application are pretty satisfactory, also in comparison with another existing Artificial Neural Network.

PREDICTION OF WAVE TRANSMISSION TROUGH A NEW ARTIFICIAL NEURAL NETWORK DEVELOPED FOR WAVE REFLECTION

FORMENTIN, SARA MIZAR;ZANUTTIGH, BARBARA
In corso di stampa

Abstract

This paper presents the results of the application of an Artificial Neural Network for the prediction of the wave transmission coefficient from low crested structures. The model essentially works with 13 input parameters, which describe the wave attack conditions and the main feature of the structures. It has been firstly created to estimate the wave reflection coefficient, by training and validating the model against nearly 6’000 data, including a wider range of coastal and harbor structures under perpendicular and oblique wave attacks. Afterwards, the Artificial Neural Network has been employed for the prediction of the wave transmission coefficient, by training it against 3’379 additional tests on low crested structures. The results of this application are pretty satisfactory, also in comparison with another existing Artificial Neural Network.
Coastal Dynamics 2013 - 7th International Conference on Coastal Dynamics
-
-
Formentin S. M.; Zanuttigh B.
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11585/148956
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact