Modeling and Design of Microstrip Coupled Resonator Filters based on ANNs.

The paper presents a design method for microstrip square open loop resonator filters on the main commercial substrate materials available. This method is based on developing an artificial neural network (ANN) to calculate the spacing between the resonators for given coupling coefficients of the filter, which results in the filter characteristics according to the design requirements. The proposed approach is used in the design of a filter example. The designed filter is manufactured and its response is measured. There is a good agreement between the simulations of the filter designed by the proposed method and the measurements.