A grey-box modelling incorporating mechanism and data is presented in this paper to predict the ship manoeuvering motion. The traditional mathematical model in three degrees of freedom is adopted to reveal the known movement mechanism, in which an additional hydrodynamic correction term is developed by Neural Network (NN) based on the data to adaptively estimate the errors induced by the idealised approximation. The KRISO Container Ship (KCS) is taken as the study object and the free-running model tests are carried out to obtain the data for establishing the NN model of hydrodynamic correction terms. The typical manoeuvers (tactical circles, zigzags, Williamson turns) are simulated by the grey-box model and the mathematical model, respectively. The results indicate that the grey-box modelling method proposed in this paper can not only improve the prediction accuracy but also demonstrate a good generalisation performance.
Prediction of ship maneuvering motion with grey-box modelling incorporating mechanism and data
SHIPS AND OFFSHORE STRUCTURES
Y. HAN ET AL.
Ships and Offshore Structures ; 19 , 8 ; 1196-1209
02.08.2024
14 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Some Notes on Prediction of Ship Maneuvering Motion
British Library Conference Proceedings | 1992
|Ship Maneuvering Prediction Using Grey Box Framework via Adaptive RM-SVM with Minor Rudder
DOAJ | 2019
|Ship Maneuvering Prediction Using Grey Box Framework via Adaptive RM-SVM with Minor Rudder
Online Contents | 2019
|