Modeling of Ship Turning Motion Prediction Based on BP Neural Network

Abstract

Abstract To more correctly grasp the ship turning performance and provide better references for initial design and safe handling of the ship, combined with the ship turning motion characteristics, a simulation prediction model of the ship turning motion is created by using the BP neural network method, which takes the transverse and longitudinal distance of the ship turning motion as the output. Within that study, the neural network model is trained by utilizing 12 real ship motion data as training examples. This research generates predictions using data from two more real ships as test samples once the training is complete. The discrepancy between the estimated and real ship outcomes is also compared, and the error is examined. The results verify that the constructed prediction model has stronger generalization ability and better accuracy, indicating that the model can successfully realize the simulation prediction for the ship turning motion.