On the identification of coupled pitch and heave motions using support vector machine

Abstract

This paper studies support vector machine (SVM) for the parametric identification of ship coupled heave and pitch motions with real oceanic conditions. The simulation results are based on a mathematical model of a ship model in the simulated marine environment. By analyzing the identification precision of the equation parameters of coupled heave-pitch motions, this paper presents the proper numbers of data for identifying. Moreover, by analyzing the influence of sea states, the accurate results illustrate that the characteristics of coupled heave and pitch motions can be fully represented by the motion responses at high sea states. The mathematical model of coupled pitch-heave motion constructed with the estimated parameters is used for predicting the heave and pitch motion responses at different sea conditions. The prediction results illustrate that the effectiveness and generalization of the identification method based on SVM are very good.