Title :
Pareto optimum design of cyclone separator
Author :
Alitavoli, M. ; Mahmoodabadi, M.J. ; Sahnehsaraei, M. Andalib ; Bagheri, A.
Author_Institution :
Dept. of Mech. Eng., Islamic Azad Univ., Bandar, Iran
Abstract :
In this paper, in order to Pareto design of cyclone separators, pressure drop and collection efficiency Δp and η in a set of cyclones are numerically investigated using Computational Fluid Dynamic (CFD) techniques. Then, the neural network is used to obtain polynomial models for the effects of geometrical parameters of the cyclones on both the pressure drop and the collection efficiency. The obtained simple polynomial models are used to find the best possible combinations of the pressure drop and collection efficiency, known as the Pareto front based on a novel multi-objective algorithm.
Keywords :
Pareto optimisation; computational fluid dynamics; cyclone separators; design engineering; flow separation; mechanical engineering computing; neural nets; polynomials; CFD techniques; Pareto front; Pareto optimum design; collection efficiency; computational fluid dynamics; cyclone separator; multiobjective optimisation; neural network; numerical analysis; polynomial models; pressure drop; Computational fluid dynamics; Cyclones; Data models; Mathematical model; Neural networks; Optimization; Particle separators; GMDH; Gas-solid; Multi-objective optimization; Particle swarm optimization; Two-phase Flow;
Conference_Titel :
Innovations in Intelligent Systems and Applications (INISTA), 2012 International Symposium on
Conference_Location :
Trabzon
Print_ISBN :
978-1-4673-1446-6
DOI :
10.1109/INISTA.2012.6247039
