Fully complex-valued radial basis function networks for prediction of wind force and moment co-efficients on marine structures

In this paper, a Fully Complex-Valued Radial Basis Function (FC-RBF) network is used to predict the wind force and moment co-efficients of marine structures. The paper aims to provide an universal approach to study the wind force and moments on the ships. The force and moment co-efficient estimated in literature using regression analysis involves the ship dimensions. These dimensions can be represented in complex-valued number format, which makes it an ideal approximation problem from FC-RBF. The study considers various types of marine vessels at different loading conditions, with a total of 22 marine vessels. Of these, 18 are used to train FC-RBF. The network thus developed is tested for generalization on 2 new type of vessels at 2 different loading conditions. Thus, the developed model is capable of predicting the wind force and moment coefficients, irrespective of the type of vessel used. Performance study to predict the wind force and moment coefficients of marine vessels show that the FC-RBF has superior prediction performance, compared to state of the art results for this problem.