Shape optimization of turbomachinery blade using multiple surrogate models

Performances of multiple surrogate models are evaluated in a turbomachinery blade shape optimization. The basic models, i.e., Response Surface Approximation, Kriging and Radial Basis Neural Network models as well as weighted average models are tested for shape optimization. Global data based errors for each surrogates are used to calculate the weights. These weights are multiplied with the respective surrogates to get the final weighted average models. Sequential Quadratic Programming is used to search the optimal point from these constructed surrogates. Use of multiple surrogates via weighted averaged surrogates gives more robust approximation than individual surrogates. Three design variables are selected to enhance the performance of transonic axial compressor (NASA rotor 37) blade and the design points are selected using three level fractional factorial D-optimal designs. The performance of compressor is improved by optimization because of reduction of losses and movement of separation line towards down stream directions. The present approach can help address the multi-objective design on a rational basis with quantifiable cost-benefit analysis.