Research on sensitivity analysis method of ship hydrodynamic derivatives based on intelligent control

Abstract

Objectives \xa0In order to obtain a simplified mathematical model of ship motion used for intelligent control, Methods \xa0This paper takes the Mariner class vessel as the research object, and proposes a sensitivity analysis method combining standard maneuverability test and PID heading control test. Compound analysis include the control index, maneuverability index, and the squared loss of typical motion state variables throughout the entire process is performed to obtain a data set containing multi-dimensional sensitivity coefficients. K-means machine learning algorithm is introduced to perform cluster analysis on the data set. The sensitivity division of hydrodynamic derivatives is completed and the model is simplified. Results \xa0The contrastive simulation tests of heading control and track control among the simplified model, the former simplified model and the complete model are carried out, the results show that the sensitivity analysis method proposed in this paper is effective and the model proposed in this paper has higher control prediction accuracy. Conclusions \xa0The research shows that the method proposed in this paper has certain significance for guiding the ship motion modeling for intelligent control.