Sea state level acquisition and division based on Hilbert transform

This paper focuses on the deep learning convolution neural network, based on the ship motion response real-time rapid prediction of the current sea state information. Firstly, the time series of ship motion response is transformed into two-dimensional signal scatter diagram by Hilbert transform. Secondly, the color dimension is introduced into the two-dimensional scatter diagram, and the scatter diagram is colored according to the density of points. Furthermore, through image recognition classification to achieve the classification of sea state level. Finally, the correctness and feasibility of the method are verified by simulation.