Stability of rubble-mound breakwater using H50 wave height parameter

Abstract The prediction of rubble mound breakwaters' stability is one of the most important issues in coastal and maritime engineering. The stability of breakwaters strongly depends on the wave height. Therefore, selection of an appropriate wave height parameter is very vital in the prediction of stability number. In this study, H 50 , the average of the 50 highest waves that reach the breakwater in its useful life, was used to predict the stability of the armor layer. First, H 50 was used instead of the significant wave height in the most recent stability formulas. It was found that this modification yields more accurate results. Then, for further improvement of the results, two formulas were developed using model tree. To develop the new formulas, two experimental data sets of irregular waves were used. Results indicated that the proposed formulas are more accurate than the previous ones for the prediction of the stability parameter. Finally, the proposed formulas were applied to regular waves and a wide range of damage levels and it was seen that the developed formulas are applicable in these cases as well.

[1]  J. W. van der Meer,et al.  Wave run-up and wave overtopping at dikes and revetments , 2007 .

[2]  A. Etemad-Shahidi,et al.  COMPARISON BETWEEN M5 MODEL TREE AND NEURAL NETWORKS FOR PREDICTION OF SIGNIFICANT WAVE HEIGHT IN LAKE SUPERIOR , 2009 .

[3]  D. M. Thompson,et al.  Riprap design for wind-wave attack, a laboratory study in random waves , 1975 .

[4]  J. V. D. Meer,et al.  Rock slopes and gravel beaches under wave attack , 1988 .

[5]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[6]  Dong Hyawn Kim,et al.  Application of probabilistic neural network to design breakwater armor blocks , 2008 .

[7]  R. Y. Hudson,et al.  DESIGN OF QUARRY-STONE COVER LAYERS FOR RUBBLE-MOUND BREAKWATERS , 1958 .

[8]  Jentsje W. van der Meer,et al.  Stability of breakwater armour layers — design formulae , 1987 .

[9]  Tarkan Erdik,et al.  Fuzzy logic approach to conventional rubble mound structures design , 2009, Expert Syst. Appl..

[10]  M. Davies,et al.  BREAKWATER STABILITY UNDER REGULAR AND IRREGULAR WAVE ATTACK , 1997 .

[11]  Ian H. Witten,et al.  Induction of model trees for predicting continuous classes , 1996 .

[12]  Hajime Mase,et al.  NEURAL NETWORK FOR STABILITY ANALYSIS OF RUBBLE-MOUND BREAKWATERS , 1995 .

[13]  M. Losada,et al.  Suitable Wave-Height Parameter for Characterizing Breakwater Stability , 1995 .

[14]  Amir Etemad-Shahidi,et al.  Design of rubble-mound breakwaters using M5 ′ machine learning method , 2009 .

[15]  Roland K. Price,et al.  Machine Learning Approach to Modeling Sediment Transport , 2007 .

[16]  Roland K. Price,et al.  Application of model trees and other machine learning techniques for algal growth prediction in Yongdam reservoir, Republic of Korea , 2010 .

[17]  R. Medina,et al.  Wave height parameter for damage description of rubble-mound breakwaters , 2006 .

[18]  Stanisław Ryszard Massel,et al.  Ocean Surface Waves: Their Physics and Prediction , 1996 .

[19]  Dong Hyawn Kim,et al.  Neural network for design and reliability analysis of rubble mound breakwaters , 2005 .