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.

No abstract

No abstract

No abstract

Situation awareness is of great importance for autonomous ships. One key aspect is to estimate the sea state in a real-time manner. Considering the ship as a large wave buoy, the sea state can be estimated from motion responses without extra sensors installed. However, it is difficult to associate waves with ship motion through an explicit model since the hydrodynamic effect is hard to model. In this paper, a datadriven model is developed to estimate the sea state based on ship motion data. The ship motion response is analyzed through statistical, temporal, spectral, and wavelet analysis. Features from multi-domain are constructed and an ensemble machine learning model is established. Real-world data is collected from a research vessel operating on the west coast of Norway. Through the validation with the real-world data, the model shows promising performance in terms of significant wave height and peak period.