Real Time Prediction of Ship Pitch Motion Based on NARX Neural Network

In order to improve the accuracy of ship pitch prediction, a Nonlinear AutoRegressive with eXogenous inputs (NARX) neural network prediction model is proposed, through the introduction of non-linear meteorological data to train the neural network, so that it can obtain the optimal training effect and improve the prediction accuracy. Finally, the model is simulated and tested by using the real ship pitch data of Dalian Maritime University Teaching Experimental ship “YUKUN”, and the results are compared with the Back Propagation (BP) neural network. The experimental results show that the model selected in this paper has high prediction accuracy.