ONLINE GREY PREDICTION OF SHIP ROLL MOTION USING VARIABLE RBFN

Ship's roll motion at sea is a complex system featured by nonlinearity, uncertainty, and time-varying dynamics. In this paper, a grey neural prediction scheme is presented for online ship roll motion prediction. The grey data processing approach is employed to alleviate the unfavorable effects of the uncertainty exhibited in measurement data, and grey relational analysis method is also involved to determine the structure of the grey prediction scheme. To represent the time-varying dynamics of nonlinear system, a variable structure radial basis function network (RBFN) is online constructed by learning samples in a sliding data window sequentially. Simulations of ship roll motion prediction are conducted via different approaches to validate the effectiveness of the proposed variable-RBFN-based grey prediction method. Measurement data employed in simulation is obtained during sea trials of the scientific research and training ship Yu Kun. Simulation results demonstrate the efficiency and accuracy of the proposed prediction method.