Reliability analysis of rubble mound breakwaters by neural network model

Abstract

Artificial intelligence techniques were applied to the preliminary design of rubble mound breakwaters. Wave parameters of Alanya region (significant wave height, period and direction) were simultaneously predicted by using feed forward and recurrent neural networks. Artificial intelligence technique of feed forward neural network was applied to the stability and reliability analyses of Mersin yacht harbor main breakwater, as a case study. In predicting wave parameters, neural networks can obtain a better performance than stochastic models and recurrent neural networks were appropriate for multi step predictions. A "design artificial neural network" which uses Van der Meer's hydraulic model test data, was developed for the preliminary design of rubble mound coastal structures and it was verified for the design applications. In the reliability-based design, more reliable results can be obtained for the optimum global solutions by using artificial intelligence, when compared to the second-order methods. Artificial intelligence techniques can handle more accurately the uncertainties inherent in the design of rubble mound breakwaters; hence the need of complex models generally used for the reliability-based design has been significantly decreased.