Abstract
A new system identification scheme based on model reference and random forest(RM-RF), was used to model ship maneuvering. First, the scheme establishes the relationship between a ship and the RM using the similarity rule. Second, a suitable RM was selected from public ship maneuvering models to avoid the tuning process in the empirical Maneuvering Modeling Group(MMG) model. Third, RF creates a relationship to map accelerations between the ship and the RM. Finally, the study case was implemented with fewer free running model test data. The results show the feasibility of the identification modeling scheme and validated the generalizability of the proposed approach.
Funding Information
  • National Natural Science Foundation of China (51579025)
  • Natural Science Foundation of Liaoning Province (20170540090)
  • Fundamental Research Funds for the Central Universities (3132018306)

This publication has 35 references indexed in Scilit: