A novel, modified small signal behavioral modeling methodology for gallium nitride (GaN) high electron-mobility transistors (HEMTs), based on the support vector regression (SVR) technique, is presented in this paper. Compared with the classic equivalent small-signal circuit model, the proposed model adds an error correction technique, which is developed using SVR techniques. The proposed model maintains accuracy across a broad frequency range, from 1 GHz to 10 GHz. The verification is performed through comparisons with measured multibias S-parameter data performed on an 8 Â 125 μm GaN HEMT device with a 0.25 μm gate feature size. The modified model shows a significant improvement in S-parameter prediction accuracy when compared with the classic equivalent circuit modeling approach.
This paper presents a novel nonlinear behavioral modeling methodology based on long-shortterm memory (LSTM) networks for gallium nitride (GaN) high-electron-mobility transistors (HEMTs). There are both theoretical foundations and practical implementations of the modeling procedure provided in this paper. To determine the most appropriate optimizer algorithm for the model presented in this work, four different optimization algorithms are examined. The results of both simulation and experimental validation are provided based on a 10-W GaN HEMT device. According to the developed investigation, the model is capable of extrapolating and interpolating over multiple input power levels and frequencies, including linear, weakly nonlinear, and strongly nonlinear areas. The analysis of the simulated and measured results shows that the developed model has superior performance also when considering the DC drain current (Ids.). Compared with the existing support vector regression (SVR) based model and the Bayesian based model, the proposed approach shows a significantly improved extrapolation capability.INDEX TERMS behavioral modeling, black box model, gallium nitride (GaN), high-electron-mobility transistor (HEMT), long-short term memory (LSTM), microwave frequency, power transistor.
In this work, the kink effect (KE), typically visible in S22, is analyzed and modeled. Two different modeling techniques: equivalent circuit modeling (ECM) method and machine learning method which based on support vector regression (SVR) technique are presented and compared, when applied to the S22 behavior of a Gallium Nitride (GaN) high electron mobility transistor (HEMT). The device under test (DUT) has a width of 8 Â 125 μm, with a gate feature size of 0.25 μm. The proposed method identifies the effect that the bias voltage and extrinsic elements have on the S22 kink shape. Additionally, compared to ECM, the SVR model attains a superior fitting accuracy across the complete frequency band.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.