This study presents the design of a windshield for a 12,000 TEU container ship using a multidisciplinary optimization system aimed at enhancing its aerodynamic performance. The framework integrates parametric modeling, design of experiment (DOE), numerical simulation, support vector regression (SVR)-based approximation, and a genetic algorithm (GA). Initially, the flow field around the ship is predicted using Reynolds-averaged Navier–Stokes (RANS) equations, with accuracy validated against computational fluid dynamics (CFD) and experimental fluid dynamics (EFD) results. The windshield’s shape is then defined by three Bezier curves, and six design variables are selected based on these curves to ensure smooth deformation. Subsequently, 120 sample points are chosen within the design space using the DOE method, and an SVR-based surrogate model is established. Optimization is performed using the multi-island genetic algorithm to determine the windshield configuration. Validation tests confirm the robustness of the optimization process. On this basis, the drag reduction mechanism of the windshield is summarized and analyzed. Results demonstrate that the optimization system effectively enhances the aerodynamic performance of the container ship, achieving a maximum drag reduction rate of 20.67% under headwind conditions and significant improvement across wind angles from 0° to 60°.
Read full abstract