Prediction of the vertical vibration of ship hull based on grey relational analysis and SVM method

Abstract

There are certain limitations when empirical formulas are used to predict the ship hull vertical vibration. Natural frequency of ship’s vertical vibration is predicted by support vector machine (SVM), which possesses many characteristics such as small sample learning, global optimization and strong generalization. Considering the parameters that influence the natural frequency of ship’s vertical vibration are much more, a grey relation model between ship’s main parameters and natural frequency of ship’s vertical vibration is established by grey relational analysis theory to get the grey correlation degree of each parameter. The parameters with greater correlation degree are used as input data and the measured values of natural frequency of vertical vibration are used as output data in SVM to build the nonlinear regression model of the natural frequency of vertical vibration. Natural frequencies of eight ships’ vertical vibration are predicted by the nonlinear regression model, and the results are coincident with the measured values. The proposed method in this paper is proved to be accurate and feasible, which provides a new idea to the prediction of natural frequency of ship’s overall vertical vibration.