To address the issues of high training costs and low efficiency in conventional manual hull modeling methods, an intelligent software for 3D geometric hull model generation from 2D lines plan has been developed, enhancing the automation of modeling and production efficiency. This modeling software, which is developed and designed using python, simulates the human visual system to extract, analyze and interpret the hull lines information from 2D drawings in units of pixel clusters. First, it reads, identifies and processes 2D lines plan (JPEG or PNG format) obtained from screenshots or scans, and maps the 2D profile points to 3D point cloud data according to the spatial relationships among the three views. Then, it generates the hull surface through information densification, thereby simplifying the modeling process from 2D plans to 3D models. Finally, accuracy verification results show that the modeling software based on computer vision technology can quickly convert the 2D lines plan in image form into the 3D hull models, demonstrating its reliability.

The computational fluid dynamics (CFD) method has been adopted to optimize the twin-skeg hull line of the twin-skeg Ro-Ro ship from the wake uniformity and the resistance in view of the technical problem that it is difficult to optimize the stern line of the twin-skeg ships. The wake objective function and the average wake fraction proposed by MARIN are used as the evaluation criterion for the wake uniformity. It analyzes the effects of the angle of run of the skeg at 0.8 R above the stern shaft, the fillet radius for the skeg, and the distance between the propeller disk and the stern shaft outlet on the wake uniformity and the resistance. The results show that with the basically constant ship form parameters, the variation of the skeg characteristic parameters will cause the change of the wake uniformity, average wake fraction and resistance. The twin-skeg hull lines are also optimized by the comparative analysis.