Manoeuvring modelling of a containership in shallow water based on optimal truncated nonlinear kernel-based least square support vector machine and quantum-inspired evolutionary algorithm

Abstract

Nonlinear implicit models are proposed for manoeuvring simulation of a container model in shallow water. A series of Planar Motion Mechanism tests of the DTC ship model carried out in a towing tank with shallow water is used for training the nonlinear implicit manoeuvring model. A novel method, nonlinear kernel-based Least Square Support Vector Machine (LS-SVM), is proposed to approximate the nonlinear manoeuvring model. It is a robust method for regression modelling with a low computational cost by reducing the dimensionality of the kernel matrix. The radial basis function kernel is employed in the SVMs to guarantee the performance of the approximation. The quantum-inspired evolutionary algorithm (QEA) is used to search the optimal value of the predefined parameters of the nonlinear kernel-based LS-SVM. The optimal truncated LS-SVM is used to train the nonlinear regression models for ship manoeuvring, and the generalization performance of the obtained nonlinear manoeuvring models is further tested against the validation set. The R2 goodness-of-fit criterion is used to demonstrate the accuracy of the obtained models.