On the large-signal modeling of AlGaN/GaN devices using genetic neural networks

An accurate large-signal model for AlGaN-GaN HEMT is presented. This model is derived from a distributed small-signal model that efficiently describes the physics of the device. A genetic neural network based model for the gate and drain currents and charges is presented along with its parameters extraction procedure. The model shows very good results for simulating the high-power operation of a 8×125-μm gate width AlGaN/GaN HEMT and the associated nonlinearities even beyond the 1-dB gain compression point.