Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Visualizing 4D approximation sets of multiobjective optimizers with prosections
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Visualization and exploration of optimal variants in product line engineering
Proceedings of the 17th International Software Product Line Conference
| Hi-index | 0.00 |
In this paper a procedure for the multi-objective optimization of an automotive cooling duct is described. The two objectives considered are the minimization of the pressure drop between the inlet and the outlet of the duct and the maximization of the outlet flow velocity. Since there is no a single optimum to be found, the MOGA-II was used as multi-objective genetic algorithm. The optimization of the duct was obtained employing a parametric model, performing flow analysis with an open source suite and using a multi-objective optimization product. 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. The results obtained are very satisfactory, and the procedure described can be applied to even more complex problems.