A STUDY ON OPTIMIZATION OF SHIP HULL FORM BASED ON NEURO-RESPONSE SURFACE METHOD (NRSM)

Abstract

Building large and eco-friendly ships has become a clear trend in the ship building industry. Research to minimize ship resistance has actively been investigated for energy savings and environmental protection. However, optimization of the full geometry, while taking into account the hydrodynamic performance is difficult because extensive time is needed to calculate the performance factors, such as the resistance and propulsion. Hence we suggest an optimal design framework based on the neuro-response surface method (NRSM) for optimal shape design in consideration of hydrodynamic performance. The optimization algorithm of the constructed framework consists of the back-propagation neural network (BPN) and the non-dominated sorting genetic algorithm-II (NSGA-II). Using the framework, we performed a case study to optimize the hull form of a 4300TEU container ship with consideration of wave resistance, viscous pressure resistance, and wake fraction.