The invention discloses a physical informed enhanced
marine equipment hydrodynamic performance efficient forecasting method and
system, and relates to the technical field of ship
engineering, and the method comprises the steps: simulating and generating still
water resistance data of a ship type sample based on a CFD method, comparing the still
water resistance data with an experimental value, and verifying the reliability of the data; the original ship type parameters are converted into dimensionless derivative features, and an original sample set is generated; identifying a parameter blank interval of the original sample set through clustering analysis, generating a supplementary sample based on a potential flow theory
boundary element method, and obtaining an extended
data set in combination with the original sample set; a density adaptive regularization mechanism and a deviation penalty term are embedded in an XGBoost framework, an EPK-XGBoost model is constructed, an extended
data set is used for model training and performance evaluation, and a still
water resistance coefficient is predicted through a prediction model with optimal performance. According to the method, the prediction precision of the hydrostatic resistance coefficient can be improved, and the generalization
bottleneck of a traditional model in a
small sample scene is broken through.