A NOVEL MODELING OF MILLIMETERWAVE Al_(0.27)Ga_(0.73)N/AlN/GaN HEMT BASED ON ARTIFICIAL NEURAL NETWORK

摘要

An artificial neural network (ANN) was used for modeling millimeter-wave Al_(0.27)Ga_(0.73)N/AlN/GaN high electron mobility transistor (HEMT) with multi-biases in this article. Millimeter-wave Al_(0.27)Ga_(0.73)N/AlN/GaN HEMT with gate width of 2 × 75 mm and gate length of 0.3 mm was designed and fabricated at first, and then its performance was measured for modeling. NeuroModelerPlus_V2.1E software was trained to learn the input-output relationship from the data about DC and AC performances of proposed device. ANN DC model and AC model were set up and embedded in software of ADS together to form a model of millimeter-wave Al_(0.27)Ga_(0.73)N/AlN/GaN HEMT, which can be used in circuit design. The results of the simulation of the model showed that it corresponded with the measurement results.