Parameter identification of ship manoeuvring model under disturbance using support vector machine method

Demanding marine operations increase the complexity of manoeuvring. A highly accurate ship model promotes predicting ship motions and advancing control safety. It is crucial to identify the unknown hydrodynamic coefficients under environmental disturbance to establish accurate mathematical models. In this paper, the identification procedure for a 3 degree of freedom hydrodynamic model under disturbance is completed based on the support vector machine with multiple manoeuvres datasets. The algorithm is validated on the clean ship model and the results present good fitness with the reference. Experiments in different sea states are conducted to investigate the effects of the turbulence on the identification performance. Generalisation results show that the models identified in the gentle and moderate environments have less than 10% deviations and are considered allowable. The higher perturbations, the lower fidelity the identified model has. Models identified under disturbance could provide different levels of reliable support for the operation decision system.