Adaptive Online Modeling of Ship Maneuvering Motion Based on Error Monitoring

Objectives Aiming to address the problem of model inaccuracy caused by ship dynamic changes during actual navigation, this study proposes an adaptive online modelling method for ship manoeuvring motion based on an error monitoring mechanism. Methods The method determines the timing of model update through the model prediction error monitoring mechanism, and realizes adaptive retraining update of the model based on voyage data by combining the sliding window technique and support vector machine. Taking the KCS container ship as the research object, the method is tested and validated under the zigzag and turning circle motion scenarios with variable speed, and the influence of the hyperparameter selection in the error monitoring mechanism on the online modeling is analyzed. Results The simulation results show that the error detection mechanism can effectively reduce the frequency of online model update and save computational resources. Compared with the offline method, this method can update the model in time when the dynamic characteristics of the ship change, which guarantees the prediction accuracy. Conclusions The proposed method is applicable to scenarios where the dynamic characteristics of ships change due to their own attributes, environmental changes, etc. It provides a technical method for online modeling and prediction of ship motion and has practical engineering significance.