Constitutive relations for nonlinear modeling of Si/SiGe HBTs using an ANN model

In this article, we demonstrate how the constitutive relations for the nonlinear modeling of hetro-junction bipolar transistors (HBTs) can be based on an artificial neural network (ANN) model representation.. The model is implemented using a commercial microwave simulator, and has been validated by DC and nonlinear measurements. Excellent agreement is obtained as compared with the results of the DC measurements, and the model predicts well the higher-order harmonics in a single tone test.. © 2005 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2005.