Extreme short-term prediction of ship motion based on chaotic theory and RBF neural network

Based on the reconstruction of the chaotic dynamic space, the correlation dimension method and Lyapunov exponent method are applied to identify the chaos characteristic of ship motion time series. Extreme short-term prediction model of ship motion is established based on phase space reconstruction and RBF neural network. The test results show that this prediction model produces excellent performance, which is able to predict the ship motion satisfactorily for up to 10 seconds.