An Empirical Method for Dynamic Stress Prediction in Turbomachinery
The effectiveness of fatigue and life prediction methods depends heavily on accurate knowledge of the static and dynamic stresses acting on a structure. Although stress fields may be calculated from the finite element shape functions if a finite element model is constructed and analyzed, in many cases the cost of constructing and analyzing a finite element model is prohibitive. Modeling errors can severely affect the accuracy of stress simulations. This paper presents an empirical method for predicting a transient dynamic stress response of a structure based on measured load and strain data that can be collected during vibration tests. The method applies the proper orthogonal decomposition to a measured data set to filter noise and reduce the size of the identification problem and then employs a matrix deconvolution technique to decouple and identify the reduced coordinate impulse response functions for the structure. The method is applied to simulation data from an axial compressor blade model and produces accurate stress predictions compared to finite element results.