This paper describes the hydrodynamic characteristics of a pile-supported vertical wall breakwater, the upper part of which is a vertical wall, and the lower part consisting of an array of vertical piles. For regular waves, using the eigenfunction expansion method, a numerical model has been developed that can compute wave transmission, reflection, and run-up, and wave force acting on the breakwater. For irregular waves, the regular wave model is repeatedly used for each frequency component of the irregular wave spectrum. The wave period is determined according to the frequency of the component wave, while the root-mean-squared wave height is used for all the component waves to compute the energy dissipation between piles. To examine the validity of the developed models, large-scale laboratory experiments have been conducted for pile-supported vertical wall breakwaters with a constant spacing between piles but various drafts of the upper vertical wall. Comparisons between measurement and prediction show t...

In this study, an artificial neural network (ANN) model is developed to predict the stability number of breakwater armor stones based on the experimental data reported by Van der Meer in 1988. The harmony search (HS) algorithm is used to determine the near-global optimal initial weights in the training of the model. The stratified sampling is used to sample the training data. A total of 25 HS-ANN hybrid models are tested with different combinations of HS algorithm parameters. The HS-ANN models are compared with the conventional ANN model, which uses a Monte Carlo simulation to determine the initial weights. Each model is run 50 times and the statistical analyses are conducted for the model results. The present models using stratified sampling are shown to be more accurate than those of previous studies. The statistical analyses for the model results show that the HS-ANN model with proper values of HS algorithm parameters can give much better and more stable prediction than the conventional ANN model.