RBF intelligent model of rectangular PDGS-LPF

Microwave low-pass filter (LPF) is a kind of device which can separate different signals within microwave frequency range, widely used in microwave communication system. Periodic defected ground structures (PDGS) with rectangular defected areas has excellent low-pass properties when periodic unit amounts and structure sizes meet definite conditions. According to RBF artificial neural network (ANN) theory, RBF intelligent model of PDGS-LPF with etched rectangles is developed for the first time on the basis of FDTD analysis. The structure sizes of rectangular PDGS-LPF and the frequency are defined as the input samples of the RBF, transmission coefficient (S21) are defined as the output samples. After the RBF has been successfully trained with improved Gaussian algorithm, S21 at any arbitrary parameters can be obtained quickly from RBF intelligent model within training values range. Finally, RBF intelligent model has been approved by FDTD results. It is also showed that RBF intelligent model is very effective, which will provide powerful approach for the precise analysis and quick design of rectangular PDGS-LPF.