Pareto based multi-objective optimization of a cyclone vortex finder using CFD, GMDH type neural networks and genetic algorithms

In the present study, multi-objective optimization of a cyclone vortex finder is performed in three steps. In the first step, collection efficiency (η) and the pressure drop (Δ p) in a set of cyclones with different vortex finder shapes are numerically investigated using CFD techniques. Two meta-models based on the evolved group method of data handling (GMDH) type neural networks are obtained in the second step, for modelling of η and Δ p with respect to geometrical design variables. Finally, using the obtained polynomial neural networks, multi-objective genetic algorithms are used for Pareto-based optimization of a vortex finder considering two conflicting objectives, η and Δ p.