Prediction of pile group scour in waves using support vector machines and ANN

摘要

Scour around pile groups is rather complicated and not yet fully understood due to the factnthat it arises from the triple interaction of fluid–structure–seabed. In this study, two data miningnapproaches, i.e. Support Vector Machines (SVM) and Artificial Neural Networks (ANN), werenapplied to estimate the wave-induced scour depth around pile groups. To consider variousnarrangements of pile groups in the development of the models, datasets collected in the fieldnand laboratory studies were used and arrangement parameters were considered in the models.nSeveral non-dimensional controlling parameters, including the Keulegan–Carpenter number,npile Reynolds number, Shield’s parameter, sediment number, gap to diameter ratio and numbernof piles were used as the inputs. Performances of the developed SVM and ANN models werencompared with those of existing empirical methods. Results indicate that the data miningnapproaches used outperform empirical methods in terms of accuracy. They also indicate thatnSVM will provide a better estimation of scour depth than ANN (back-propagation/multi-layernperceptron). Sensitivity analysis was also carried out to investigate the relative importance ofnnon-dimensional parameters. It was found that the Keulegan–Carpenter number and gap tondiameter ratio have the greatest effect on the equilibrium scour depth around pile groups.