Neural space-mapping optimization for EM-based design

We propose, for the first time, neural space-mapping (NSM) optimization for electromagnetic-based design. NSM optimization exploits our space-mapping (SM)-based neuromodeling techniques to efficiently approximate the mapping. A novel procedure that does not require troublesome parameter extraction t o predict the next point is proposed. The initial mapping is established by performing upfront line-model analyses at a reduced number of base points, Coarse-model sensitivities are exploited to select those base points, Hube r optimization is used to train, without testing points, simple SM-based ne uromodels at each NSM iteration. The technique is illustrated by a high-tem perature superconducting quarter-wave parallel coupled-line microstrip filt er and a bandstop microstrip filter with quarter-wave resonant open stubs.