This paper presents a design optimization of an axial compressor with NASA Rotor 37 and five circumferential casing grooves for enhancement of stall margin. Three-dimensional Reynolds-averaged Navier-Stokes equations with the shear stress transport turbulence model are discretized by finite volume approximations and solved on hexahedral grids for the flow analyses. The validation of the numerical results is performed in comparison with experimental data for pressure ratio and adiabatic efficiency. The Latin-hypercube sampling as design-of-experiments is used to generate the twelve design points within the design space. A stall margin parameter is considered as an objective function with two design variables defining the geometry of the circumferential casing grooves. The radial basis neural network method employed as a surrogate model for the design optimization of the circumferential casing grooves is trained on the numerical solutions by carrying out leave-one-out cross-validation for the data set. The results show that the stall margin of the optimum shape is enhanced considerably by the design optimization compared to the cases with smooth casing and the reference grooves.
展开▼
