Accurate Modeling of GaN HEMTs Oriented to Analysis of Kink Effects in S<sub>22</sub> and h<sub>21</sub>: An Effective Machine Learning Approach
In this work, for the first time, a machine learning behavioral modeling methodology based on gate recurrent unit (GRU) is developed and used to model and then analyze the kink effects (KEs) in the output reflection coefficient <inline-formula> <tex-math notation="LaTeX">$(S_{2...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of the Electron Devices Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10433010/ |
| _version_ | 1797269135138226176 |
|---|---|
| author | Zegen Zhu Gianni Bosi Antonio Raffo Giovanni Crupi Jialin Cai |
| author_facet | Zegen Zhu Gianni Bosi Antonio Raffo Giovanni Crupi Jialin Cai |
| author_sort | Zegen Zhu |
| collection | DOAJ |
| description | In this work, for the first time, a machine learning behavioral modeling methodology based on gate recurrent unit (GRU) is developed and used to model and then analyze the kink effects (KEs) in the output reflection coefficient <inline-formula> <tex-math notation="LaTeX">$(S_{22})$ </tex-math></inline-formula> and the short-circuit current gain <inline-formula> <tex-math notation="LaTeX">$(h_{21})$ </tex-math></inline-formula> of an advanced microwave transistor. The device under test (DUT) is a 0.25-<inline-formula> <tex-math notation="LaTeX">$\mu \text{m}$ </tex-math></inline-formula> gallium nitride (GaN) high electron mobility transistor (HEMT) on silicon carbide (SiC) substrate, which has a large gate periphery of 1.5 mm. The scattering (S-) parameters of the DUT are measured at a frequency up to 65 GHz and at an ambient temperature up to 200°C. The proposed model can accurately reproduce the KEs in <inline-formula> <tex-math notation="LaTeX">$S_{22}$ </tex-math></inline-formula> and in <inline-formula> <tex-math notation="LaTeX">$h_{21}$ </tex-math></inline-formula>, enabling an effective analysis of their dependence on the operating conditions, bias point and ambient temperature. It is worth noticing that the proposed transistor model shows also good performance in both interpolation and extrapolation test. |
| first_indexed | 2024-04-25T01:43:33Z |
| format | Article |
| id | doaj.art-c0ed1c01d72b468fb27c1aa3558028dc |
| institution | Directory Open Access Journal |
| issn | 2168-6734 |
| language | English |
| last_indexed | 2024-04-25T01:43:33Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of the Electron Devices Society |
| spelling | doaj.art-c0ed1c01d72b468fb27c1aa3558028dc2024-03-08T00:00:12ZengIEEEIEEE Journal of the Electron Devices Society2168-67342024-01-011220121010.1109/JEDS.2024.336480910433010Accurate Modeling of GaN HEMTs Oriented to Analysis of Kink Effects in S<sub>22</sub> and h<sub>21</sub>: An Effective Machine Learning ApproachZegen Zhu0Gianni Bosi1Antonio Raffo2https://orcid.org/0000-0002-8228-6561Giovanni Crupi3https://orcid.org/0000-0002-6666-6812Jialin Cai4https://orcid.org/0000-0001-8621-1105Key Laboratory of RF Circuit and System, Ministry of Education, College of Electronics and Information, Hangzhou Dianzi University, Hangzhou, ChinaDepartment of Engineering, University of Ferrara, Ferrara, ItalyDepartment of Engineering, University of Ferrara, Ferrara, ItalyBIOMORF Department, University of Messina, Messina, ItalyKey Laboratory of RF Circuit and System, Ministry of Education, College of Electronics and Information, Hangzhou Dianzi University, Hangzhou, ChinaIn this work, for the first time, a machine learning behavioral modeling methodology based on gate recurrent unit (GRU) is developed and used to model and then analyze the kink effects (KEs) in the output reflection coefficient <inline-formula> <tex-math notation="LaTeX">$(S_{22})$ </tex-math></inline-formula> and the short-circuit current gain <inline-formula> <tex-math notation="LaTeX">$(h_{21})$ </tex-math></inline-formula> of an advanced microwave transistor. The device under test (DUT) is a 0.25-<inline-formula> <tex-math notation="LaTeX">$\mu \text{m}$ </tex-math></inline-formula> gallium nitride (GaN) high electron mobility transistor (HEMT) on silicon carbide (SiC) substrate, which has a large gate periphery of 1.5 mm. The scattering (S-) parameters of the DUT are measured at a frequency up to 65 GHz and at an ambient temperature up to 200°C. The proposed model can accurately reproduce the KEs in <inline-formula> <tex-math notation="LaTeX">$S_{22}$ </tex-math></inline-formula> and in <inline-formula> <tex-math notation="LaTeX">$h_{21}$ </tex-math></inline-formula>, enabling an effective analysis of their dependence on the operating conditions, bias point and ambient temperature. It is worth noticing that the proposed transistor model shows also good performance in both interpolation and extrapolation test.https://ieeexplore.ieee.org/document/10433010/GaN HEMTGRUkink effectmachine learning methodssemiconductor device modelingscattering parameter measurements |
| spellingShingle | Zegen Zhu Gianni Bosi Antonio Raffo Giovanni Crupi Jialin Cai Accurate Modeling of GaN HEMTs Oriented to Analysis of Kink Effects in S<sub>22</sub> and h<sub>21</sub>: An Effective Machine Learning Approach IEEE Journal of the Electron Devices Society GaN HEMT GRU kink effect machine learning methods semiconductor device modeling scattering parameter measurements |
| title | Accurate Modeling of GaN HEMTs Oriented to Analysis of Kink Effects in S<sub>22</sub> and h<sub>21</sub>: An Effective Machine Learning Approach |
| title_full | Accurate Modeling of GaN HEMTs Oriented to Analysis of Kink Effects in S<sub>22</sub> and h<sub>21</sub>: An Effective Machine Learning Approach |
| title_fullStr | Accurate Modeling of GaN HEMTs Oriented to Analysis of Kink Effects in S<sub>22</sub> and h<sub>21</sub>: An Effective Machine Learning Approach |
| title_full_unstemmed | Accurate Modeling of GaN HEMTs Oriented to Analysis of Kink Effects in S<sub>22</sub> and h<sub>21</sub>: An Effective Machine Learning Approach |
| title_short | Accurate Modeling of GaN HEMTs Oriented to Analysis of Kink Effects in S<sub>22</sub> and h<sub>21</sub>: An Effective Machine Learning Approach |
| title_sort | accurate modeling of gan hemts oriented to analysis of kink effects in s sub 22 sub and h sub 21 sub an effective machine learning approach |
| topic | GaN HEMT GRU kink effect machine learning methods semiconductor device modeling scattering parameter measurements |
| url | https://ieeexplore.ieee.org/document/10433010/ |
| work_keys_str_mv | AT zegenzhu accuratemodelingofganhemtsorientedtoanalysisofkinkeffectsinssub22subandhsub21subaneffectivemachinelearningapproach AT giannibosi accuratemodelingofganhemtsorientedtoanalysisofkinkeffectsinssub22subandhsub21subaneffectivemachinelearningapproach AT antonioraffo accuratemodelingofganhemtsorientedtoanalysisofkinkeffectsinssub22subandhsub21subaneffectivemachinelearningapproach AT giovannicrupi accuratemodelingofganhemtsorientedtoanalysisofkinkeffectsinssub22subandhsub21subaneffectivemachinelearningapproach AT jialincai accuratemodelingofganhemtsorientedtoanalysisofkinkeffectsinssub22subandhsub21subaneffectivemachinelearningapproach |