A virtual laboratory for stability tests of rubble-mound breakwaters |
| |
| Authors: | G. Iglesias, J. Rabu al, M.A. Losada, H. Pach n, A. Castro,R. Carballo |
| |
| Affiliation: | aDepartment of Agroforestry Engineering, University of Santiago de Compostela, E.P.S., Campus Universitario s/n, 27002 Lugo, Spain;bUniversity of A Coruña, CITEEC, Campus de Elviña s/n, 15192 A Coruña, Spain;cUniversity of Granada, CEAMA, Avda. Mediterráneo s/n, 18006 Granada, Spain |
| |
| Abstract: | The prediction of rubble-mound breakwater damage under wave action has usually relied on costly and time-consuming physical model tests. In this work, artificial neural networks (ANNs) are applied to estimate the outcome of a physical model throughout an experimental campaign comprising of 127 stability tests. In order to choose the network best suited to the problem data, five different activation function options and 38 network architectures are compared. The good agreement found between the physical model and the neural network shows that an ANN may well serve as a virtual laboratory, reducing the number of physical model tests necessary for a project. |
| |
| Keywords: | Artificial intelligence Artificial neural networks Coastal engineering Coastal structures Breakwater Armor damage |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
