Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
| Hi-index | 0.00 |
This paper introduces a procedure for using genetic multi-objective optimization in yacht design. The problem described consists on the optimization of a bulb shape to improve the performance of the yacht. The two objectives considered are the minimization of the drag in calm water together with the minimization of the Vertical Center of Gravity (VCG), all the configurations should satisfy length and volume constraints. Since there is no a single optimum to be found, the MOGA-II was used as multi-objective genetic algorithm. The distributed optimization search exploited the parallelization capabilities of the MOGA-II algorithm which allowed the evaluation of several designs configurations by running concurrent threads of the flow analysis solver. Three bulb shapes of different length are selected between the non-dominated solutions. Using these three solutions, seakeeping tests of a fully appended scale model have been carried out at the towing tank of the University of Trieste. A single hull has been tested for each bulb configurations to check the influence of the bulb shape on the performance of the yacht in waves. The results obtained are very satisfactory, and the procedure described can be applied to even more complex yacht design problems.