Small Signal Equivalent Circuit Modeling for AlGaN/GaN HFET: Hybrid Extraction Method for Determining Circuit Elements of AlGaN/GaN HFET

The developments in AlGaN/GaN heterojunction field effect transistors (HFETs) are beginning to allow harnessing of the great potential of this technology in high-power radio-frequency (RF) applications. However, the integration of HFET into a circuit environment requires accurate small and large signal modeling of the device operating under various biasing conditions. The conventional small signal equivalent circuit modeling methods consist of "cold" measurements for extracting parasitic elements, and on-bias measurements in determining the intrinsic device circuit elements. Also, the optimization routines are often explored directly using the "hot" measurement data to minimize errors. In this paper, an 18-element small signal equivalent circuit model for AlGaN/GaN HFET is proposed and implemented, and contrasted to various de-embedding methods. Among the methods treated, the hot-FET optimization extraction based on the parasitic capacitances obtained from cold measurements leads to the smallest error between the simulated S-parameters and the measured ones at all bias points employed, with an average error of about 5%. This hybrid extraction algorithm is strengthened by imposing constraints to avoid any nonphysical convergence. We note that the extrinsic parasitics determined by this method differ considerably from the values obtained by cold-FET measurements, which implies that the assumption on the bias independency for extrinsic parameters in the latter method might be questionable for AlGaN/GaN HFET.