The potential of support vector machines and Kriging in modelling the gas cyclone performance

The gas cyclone two performance parameters, the Euler and Stokes numbers, are highly affected by the variations in the geometrical parameters. To accurately predict the complex non-linear relationships between the cyclone performance and the seven geometrical parameters, the support vector machines approach has been applied. The support vector regression surrogate (SVR) has been trained and tested by an experimental dataset for the Euler number and Iozia and Leith model for the Stokes number. The result demonstrates that SVR can offer an alternative and powerful approach to model the two performance parameters. The SVR models parameters have been optimized to get 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 geometrical parameters on the cyclone performance. The genetic algorithms optimization technique has been applied to produce a new geometrical ratio for minimum Euler number. The new cyclone over-perform the standard Stairmand design performance. The multi-objective genetic algorithms optimization technique has been applied to obtain the optimum cyclone design. A Pareto front solution has been obtained from which the cyclone designer can select the suitable design.

Jaar van publicatie:2014

Trefwoorden:Support vector machines, Kriging, Gas cyclone