Rapid surrogate-assisted statistical analysis of compact microstrip couplers

In this paper, a technique for low-cost statistical analysis and yield estimation of compact microwave couplers has been presented. The analysis is executed at the level of a fast surrogate model representing selected characteristic points of the coupler response that are critical to determine satisfaction/violation of the prescribed design specifications. Because of less nonlinear dependence of the characteristic points on geometry parameters of the structure at hand (compared to the original response, i.e., S-parameters versus frequency), only a small number of training points is necessary to setup the surrogate. Our approach is demonstrated using a compact rat-race microstrip coupler at a design corresponding to the operating frequency of 1 GHz. Numerical verification involving direct Monte Carlo analysis of the EM simulation model of the coupler confirms reliability of the proposed technique.