Design A KL-Band Power Divider Using EC-ANN Models for BGCPW Discontinuities

Novel accurate and efficient equivalent circuit trained artificial neural-network (EC-ANN) models, which inherit and develop EC model and EM-ANN model´s advantages, have been developed for back-grounded coplanar waveguide (BGCPW) discontinuities. Modeled discontinuities include BGCPW bend and BGCPW symmetric T-junction, for which the validation tests are performed. These models allow for circuit design, simulation, and optimization within CAD simulator. A KL-band 4dB power divider on GaAs substrate is designed using the developed BGCPW EC-ANN models.