An improved adaptive navigation control model for state prediction of the forward vessel

Aiming at the problem of poor model prediction performance caused by the uncertainty of the forward vessel's speed in the ship adaptive navigation system, temporal convolution network (TCN) is used to predict future acceleration based on the actual speed and acceleration of the forward vessel, and the predicted acceleration is used as a disturbance to construct improved forward vessel adaptive navigation state prediction model.Historical data verification shows that compared to the Univariate long short-term memory network model (LSTM), the new model has an R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> value 0.75 and an RMSE value of 2.48, indicating that the new model has better fit and higher prediction accuracy.