Multi-Objective Surrogate Based Optimization of Gas Cyclones Using Support Vector Machines and CFD Simulations

Abstract

In order to accurately predict the complex nonlinear relationships between the cyclone performance parameters (The Euler and Stokes numbers) and the four significant geometrical dimensions (the inlet section height and width, the vortex finder diameter and the cyclone total height), the support vector machines approach has been used. Two support vector regression surrogates (SVR) have been trained and tested by CFD datasets. The result demonstrates that SVR can offer an alternative and powerful approach to model the performance parameters. The SVR model parameters have been optimized to obtain the most accurate results from the cross validation steps. SVR (with optimized parameters) can offer an alternative and powerful approach to model the performance parameters better than Kriging. SVR surrogates have been employed to study the effect of the four geometrical parameters on the cyclone performance. The genetic algorithms optimization technique has been applied to obtain a new geometrical ratio for minimum Euler number and for minimum Euler and Stokes numbers. New cyclones over-perform the standard Stairmand design performance. Pareto optimal solutions have been obtained and a new correlation between the Euler and Stokes numbers is fitted.