Autors: Nedelchev, M. V., Kolev, A. N., Zlatica Marinkovic. Title: ANN modelling of planar filters using square open loop DGS resonators Keywords: Artificial neural network, Coupling coefficient, Defected gr Abstract: This paper presents a novel modelling method for planar defected ground structure (DGS) square open loop resonator filters. The increased complexity of the coupling mechanism between the resonators and the impossibility to analytically calculate the coupling coefficients created the need of accurate modelling of the coupled resonators. Design process requires to calculate the filter dimension for the given coupling coefficient. A novel method based on artificial neural networks (ANNs) is proposed in this paper. ANNs are used to develop the filter forward and inverse models aimed to calculate the spacing between the resonators for predetermined coupling coefficients from the approximation. An example filter is designed, simulated and measured. A very good agreement between the measurements and the filter requirements is observed References Issue
|
Вид: пленарен доклад в международен форум, публикация в реферирано издание, индексирана в Scopus и Web of Science