Application of Artificial Neural Networks to investigations of ship seakeeping ability

Abstract

In order to optimize the ship design at its conceptual and preliminary stages with taking into account also seakeeping criteria, simple and simultaneously exact relationships between the basic ship design parameters and seakeeping ability are necessary. The wave induced motions of the ship in irregular waves as well as phenomena accompanying the motions, are determined on the basis of the frequency transfer functions of the ship motions in regular waves. In this paper an approximation method is presented for determination of such transfer functions with the use of the Artificial Neural Networks (ANNs). The attached results of numerical calculations show that the method provides exact data for ships of very different sizes, within wide ranges of ship velocity and direction of wave relative to the ship.