Analysis and modeling of the kink effect in S22 based on support vector machine for GaN HEMTs
Анализ и моделирование эффекта излома в S22 на основе метода опорных векторов для GaN HEMT
2022-02-17
SCID: 54.1/aze9c5mp
Discuss with AI
GaN HEMTsS22 modelingequivalent circuit modelingkink effectsupport vector regression
Figures from the paper
Abstract (AI)
Abstract 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 × 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.
Key Findings
1
Support vector regression achieves higher fitting accuracy than equivalent circuit modeling across the complete frequency band.
2
The kink effect in the S22 parameter of a GaN HEMT is analyzed and modeled using equivalent circuit modeling and support vector regression.
3
The proposed analysis identifies how bias voltage and extrinsic elements influence the shape of the S22 kink effect.
4
The study examines a GaN HEMT with dimensions of 8 × 125 μm and a 0.25 μm gate feature size.
Research Object
GaN high electron mobility transistor (HEMT) exhibiting the kink effect in S22
Research Subject
S22 kink-effect behavior and its dependence on bias voltage and extrinsic elements, including modeling accuracy across the frequency band
Publication Details
Publication Date
2022-02-17
Journal
Publisher
ISSN
Cited by
8
Access Type
Author Information
Download PDF
Subscribe to digest