Microwave noise modeling for PHEMT using artificial neural network technique

An improved noise model for pseudomorphic high electron mobility transistors (PHEMT) based on the conventional equivalent circuit modeling and artificial neural network (ANN) modeling technique is presented. The frequency dispersion of the noise model parameters which including noise parameters (P,R, imaginary and real parts of C) have taken into account by using an ANN model. The noise model parameters are determined directly from noise parameters on wafer measurement based on the noise correlation matrix technique. Good agreement is obtained between the measured and calculated results up to 26 GHz for 2 times 40 mum gate width (number of gate fingers times unit gate width) 0.25 mum double heterojunction delta-doped PHEMTs over a wide range of bias points.