A machine learning (ML) approach is developed to predict effects of blend repairs on airfoil frequency, modal assurance criterion (MAC), and modal displacement. The method is demonstrated on a transonic compressor rotor airfoil. A parametric blend geometry is developed that encompassing a large range of blend geometries. This repair geometry is used to modify the airfoil surface definition and a mesh morphing process transforms the nominal finite element model to the repaired configuration. A multi-level full factorial sampling of the blend repair design space provides training data to a Guassian stochastic process (GSP) regressor. Frequency and MAC results create a vector of training data for GSP calibration, but the airfoil mode shapes require further mathematical manipulation to avoid GSP models for each nodal displacement. This paper develops a method to reduce blended airfoil mode shape emulation cost by transforming the mode shape data into a reduced basis space using principal component analysis (PCA). The coefficients of this reduced basis train a GSP that predicts results for new blended airfoils. The emulated coefficients are used with the reduced basis vectors in a reconstruction of blended airfoil mode shape. Validation data is computed at a full-factorial design that maximizes the distance from training points. It is found that large variations in modal properties from large blend repairs can be accurately emulated with a reasonable number of training points. The reduced basis approach of mode shape variation is found to more accurately predict MAC variation when compared to direct MAC emulation.

This content is only available via PDF.
You do not currently have access to this content.