Identification of a Surface Marine Vessel Using LS-SVM

[摘要] The availability of adequate system models to reproduce, as faithfully as possible, the actual behaviour ofthe experimental systems is of key importance. In marine systems, the changing environmental conditions and thecomplexity of the infrastructure needed to carry out experimental tests call for mathematical models for accuratesimulations. There exist a wide number of techniques to define mathematical models from experimental data. Support Vector Machines (SVMs) have shown a great performance in pattern recognition and classification researchareas having an inherent potential ability for linear and nonlinear system identification. In this paper, this abilityis demonstrated through the identification of the Nomoto second-order ship model with real experimental dataobtained from a zig-zag manoeuvre made by a scale ship. The mathematical model of the ship is identified usingLeast Squares Support Vector Machines (LS-SVMs) for regression by analysing the rudder angle, surge and swayspeed, and yaw rate. The coefficients of the Nomoto model are obtained with a linear kernel function. The modelobtained is validated through experimental tests that illustrate the potential of SVM for system identification.

[学科分类] 应用数学