In order to rapidly forecast added wave resistance in the ship design stage, this paper proposes a neural network based on point cloud feature extraction.

Taking the Series 60 as an example, the corresponding added wave resistance prediction model is set up and compared with the traditional model based on the principal design parameters. By referring to S60 ship tests, the characteristics of the point cloud prediction model in terms of accuracy and stability are discussed, as well as the method of pre-training and optimizing the model using ship calm-water resistance data.

The prediction results indicate that the proposed model can perform well in all five S60 ships, with the coefficient of determination R² ranging from 0.74 to 0.90, while the traditional model based on the design parameters fails to make the correct prediction in some case.

This study provides new insights and a new approach to predicting added resistance in ship design, and may help to optimize ship forms by fully considering the impact of added wave resistance in the design phase.