Prediction of leeway and drift angle based on back propagation neural network

This paper analyzes the difficult problems in ship track control under wind flow conditions, and proposes a back propagation neural network based prediction method to predict in advance the rudder angle of the planned trajectory and the heading required to maintain the wind direction. Wind speed, flow direction, flow velocity, ship speed and course are input, wind pressure differential angle and pressure rudder angle are output, and the structure consists of three layers of neural network structure including input layer, hidden layer and output layer, and navigation simulator of Dalian Maritime University Maritime University. The experimental data is used to train the neural network for the sample. Finally, the actual ship data collected by MV KOTA CAHAYA is used as the actual sample for testing, and the test results are compared with the collected data. The comparison results verify the feasibility of the prediction method for the next step. The ship's track controller is designed to be prepared.