Accurate simulation-driven modeling and design optimization of compact microwave structures

Cost efficient design optimization of microwave structures requires availability of fast yet reliable replacement models so that multiple evaluations of the structure at hand can be executed in reasonable timeframe. Direct utilization of full-wave electromagnetic (EM) simulations is often prohibitive. On the other hand, accurate data-driven modeling normally requires a very large number of training points and it is virtually infeasible for structures that exhibit highly nonlinear responses (e.g. filters or couplers). In this paper, we propose a design-oriented modeling technique where good accuracy is achieved by (i) careful non-uniform design space sampling that accounts for nonlinear relationship between the operating frequency of the structure and its geometry parameters, and (ii) carries out the modeling process only for selected characteristic points of the structure responses (those that determine satisfaction/violation of given design specifications). Our approach is demonstrated using a compact microstrip rat-race coupler modeled in a wide range of geometry parameters. The model is subsequently used to design the structure for various sets of design specifications. Comparison with standard data-driven modeling techniques is also provided.