Intelligent Model of Microwave Band-Stop Filter in Microwave Communication System

Microwave filter is a kind of device which can separate microwave signals with different frequencies, and the filter has widely been utilized in a great many fields such as communication, signal processing, radar etc. Combinatorial non-periodic defected ground structures (CNPDGS) can be used to prohibit the propagation of electromagnetic waves within a certain band of frequencies because of special form being etched on the circuit´s ground plane. In this paper, Radial basis function (RBF) artificial neural networks of CNPDGS are developed on the basis of FDTD (finite-difference time-domain method) analysis for the first time. The transmission coefficient of the CNPDGS at any arbitrary sizes and the frequencies within region trained can be obtained quickly from intelligent mode after having been successfully trained. Finally, intelligent model has been approved by results of experimentation. It is also showed that intelligent model is very effective. Intelligent model will provide powerful approach for intelligent design of microwave band-stop filter in microwave communication system.