Design Optimization of a Centrifugal Compressor Impeller by Multi-Objective Genetic Algorithm

Abstract

This paper presents design optimization of a centrifugal compressor impeller with hybrid multi-objectives evolutionary algorithm (hybrid MOEA). Reynolds-averaged Navier-Stokes equations with shear stress transport turbulence model are discretized by finite volume approximations and solved on hexahedral grids for flow analyses. Latin hypercube sampling of design of experiments is used to generate design points within the selected design space. Two objectives, i.e., isentropic efficiency and total pressure ratio are selected with four design variables defining impeller hub and shroud contours in meridional contours to optimize the system. Non-dominated Sorting of Genetic Algorithm (NSGA-II) with ε-constraint strategy for local search coupled with surrogate model is used for multi-objective optimization. The surrogate model, Radial Basis Neural Network is trained on the numerical solutions by carrying out leave-one-out cross-validation for the data set. The trade-off between the two objectives has been found out and discussed in light of the Pareto-optimal solutions. The optimization results show that isentropic efficiencies and total pressure ratios of the cluster points at the Pareto-optimal solutions are enhanced by multi-objective optimization.