Ship motion prediction by radial basis neural networks

摘要

A radial basis function (RBF) artificial neural network (ANN) is proposed to develop a model of short term (50 seconds) prediction of vessel heave motion. This is a cutting edge topic in Ocean Engineering, since it is primary to support marine operations of vessels in harsh sea environment. The present study proposes a combined application of ANN and Hilbert transform. The time series of vessel heave motions, measured by on board Inertial Platform System, are used to train the network and to find the best configuration. The results indicate that RBF networks provide an effective and accurate tool to predict vessel motions produced by waves.