Novel Approach to Ship Multidisciplinary Design and Optimization Using Genetic Algorithm and Response Surface Method

Ship design is a complex engineering effort required excellent coordination between the various disciplines and essentially applies iteration to satisfy the relevant requirements, such as stability, power, weight, and strengths. Through, all-in-one Multidisciplinary Design Optimization (MDO) approach is proposed to get the optimum performance of the ship considering three disciplines, power of propulsion, ship loads and structure. In this research a Latin Hypercube Sampling (LHS) is employed to improve the space filling property of the design and explore it to sample data for covering the design space. To avoid the problem of huge calculation time and saving the develop time, a quadratic Response Surface Method (RSM) is adopted as an approximation model to study the relation between a set of design variables and the system output for solving the system design problems. A genetic algorithm (GA) is adopted as search technique used in computing to find exact or approximate solutions to optimize and search problems and appropriate design result in MDO in ship design. Finally, the validity of the proposed approach is proven by a case study of a bulk carrier.