Ship resistance prediction with Artificial Neural Networks

Abstract

The paper is dedicated to a new method of ship's resistance prediction using Artificial Neural Network (ANN). In the initial stage selected ships parameters are prepared to be used as a training and validation sets. Next step is to verify several network structures and to determine parameters with the highest influence on the result resistance. Finally, other parameters expected to impact the resistance are proposed. The research utilizes parameters of 7 already built off-shore vessels, with model parameters available as a result of tests conducted on European towing tanks. Thus, the reference is used to assess ship resistance prediction with the artificial neural network approach.