ABSTRACT:

Parametric roll resonance is a ship stability related phenomenon that generates sudden large amplitude oscillations up to 30–40 degrees of roll. This can cause severe damage, and it can put the crew in serious danger. The need for a parametric rolling real time prediction system has been acknowledged in the last few years. This work proposes a prediction system based on a multilayer perceptron (MP) neural network. The training and testing of the MP network is accomplished by feeding it with simulated data of a three degrees-of-freedom nonlinear model of a fishing vessel. The neural network is shown to be capable of forecasting the ship's roll motion in realistic scenarios.

INTRODUCTION

Parametric roll resonance is a well known phenomenon that has gathered great attention in the last years due to the real threat suffered by container ships in common passage conditions, which were generally considered of no danger. The resonance is most likely to happen when the ship is sailing in head or stern seas under some specific conditions as: the wave encounter frequency is approximately twice the ship's natural roll frequency; the wavelength is almost equal to the ship length; the wave amplitude is larger than a ship dependent threshold. When these conditions are fulfilled, the periodic alternation of wave crests and troughs amidships brings about dramatic changes in ship transverse stability, which in turn determines a sudden and quick growth of roll oscillations. Modern container carriers are particularly prone to parametric roll resonance due to their hull shapes - large bow flare, overhanging stern, wall-sided midship sections - which are designed to achieve an optimal trade-off between high service speed and maximum container payload above deck (Shin et al., 2004, France et al., 2001, Nielsen et al., 2006).

This content is only available via PDF.
You can access this article if you purchase or spend a download.