Real-time prediction of ship maneuvering motion in waves based on an improved reduced-order model

Abstract

Accurate and efficient real-time prediction of ship maneuvering motion in waves is essential for designing the motion controller to realize the autonomous navigation function of maritime autonomous surface ship (MASS) at sea. This study innovatively proposes an improved reduced-order model (ROM) based on higher order dynamic mode decomposition (HODMD) to predict ship maneuvering motion in waves for at least one wave period. Specifically, the improved ROM is built based on the original ROM by dividing the 6-DOF maneuvering motion in waves into two subsets, i.e., the low-frequency one and the high-frequency one, which are then predicted separately. Notably, neither the original ROM nor the improved ROM requires online updates of the model structure and the hyperparameters during the real-time prediction of ship maneuvering motion. Taking the KCS container ship as the study object and using the proposed method, the real-time prediction of turning circle maneuver in regular waves is carried out. The results indicate that the improved ROM has higher accuracy and stronger robustness compared to the original ROM.