Fast Stochastic Surrogate Modeling via Rational Polynomial Chaos Expansions and Principal Component Analysis

This paper introduces a fast stochastic surrogate modeling technique for the frequency-domain responses of linear and passive electrical electromagnetic systems based on polynomial chaos expansion (PCE) principal component analysis (PCA). A rational PCE model provides high accuracy, whereas PCA allows compressing model, leading to reduced number coefficients estimate thereby improving overall training efficiency. Furthermore, compression is shown provide additional accuracy improvements thanks its intrinsic regularization properties. The effectiveness proposed method illustrated by means several application examples.