Multi-objective optimization of guide vanes for axial flow cyclone using CFD, SVM, and NSGA II algorithm

Abstract

Guide vanes are the key components of axial flow cyclones (AFCs). The structural parameters of these vanes have a significant impact on the separation performance of the AFC. A multi-objective optimization study of guide vanes was conducted using a computational fluid dynamics (CFD) model previously proposed by the present authors, support vector machine (SVM), and non-dominated sorting genetic algorithm-II (NSGA-II). The obtained Pareto optimal solutions demonstrate that the separation efficiency and pressure drop increase as the number and wrapping angle of the guide vane increase; further, they decrease as the outlet angle and width of the guide vane increase. Moreover, the correlation between the separation efficiency and the pressure drop in the Pareto front was regressed to facilitate the design of the guide vane to achieve the desired separation performance. The research results can provide useful guidance for the design and optimization of AFCs.