Multi-objective optimization of asymmetric v-shaped ribs in a cooling channel using CFD, artificial neural networks and genetic algorithms

This study aims to investigate the multi-objective optimization of airflow within a ribbed channel to achieve the maximum heat transfer and minimum pressure drop. Two rib legs angles with lateral axis of channel, alpha and beta and dimensionless distance of apex of asymmetric v-shaped rib with midline are three design variables. We have calculated the area-averaged Nusselt number on ribbed walls and friction coefficient of flow for various geometries of ribbed channel using CFD simulations. Then we prepared the required data for optimization using GMDH type artificial neural networks (ANN). Pareto optimal points have been obtained by multi-objective optimization of NSGA II and those points with particular characteristics are further examined and analyzed. The optimal points obtained by the Pareto front and neural networks were validated through CFD simulations. Using CFD simulations in conjunction with neural networks and NSGA II optimization, very valuable and useful results are obtained, which cannot be obtained without the simultaneous use of these methods.