Microwave nonlinear device modelling by using an artificial neural network

An approach for the microwave nonlinear device modelling technique based on a combination of the conventional equivalent circuit model and artificial neural network (ANN) is presented in this paper. The main advantage of the proposed method is that the integration and differential of an ANN can directly be carried out from the original ANN. The proposed technique is very useful for neural-based microwave computer-aided design, and for analytically unified dc, small signal and nonlinear device modelling. Examples of the Schottky diode and PHEMT linear/nonlinear modelling utilizing the proposed integration and differential technique are demonstrated.