Effective Design of Cross-Coupled Filter Using Neural Networks and Coupling Matrix

In this paper, neural network modeling techniques are applied to the design of waveguide dual-mode pseudo-elliptic filter. A hybrid modeling approach is developed where neural networks and filter coupling matrix are combined in an innovative way to deliver speed and accuracy of the overall filter design. Filter structure is decomposed into modules representing each coupling mechanism. Generalized scattering matrices (GSM) of the modules are calculated using mode-matching method. Equivalent circuit parameters, such as coupling value and insertion phase lengths are then extracted from EM data. Neural models are developed for circuit parameters for each individual module instead of direct modeling of GSM. Good agreement is obtained between neural models and EM-based data. A narrow-bandwidth four-pole Ku band bandpass filter is designed using the trained NN models, and simulated and optimized using full EM model (HFSS). The difference between the optimized dimensions and NN model is within 0.01" for all dimensions, which demonstrates that the developed NN models are capable of achieving the accuracy of EM-based model with superior computation speed