A Novel 4-D Artificial-Neural-Network-Based Hybrid Large-Signal Model of GaAs pHEMTs

Yunshen Long; Zheng Zhong; Yong-Xin Guo

doi:10.1109/TMTT.2016.2555948

A Novel 4-D Artificial-Neural-Network-Based Hybrid Large-Signal Model of GaAs pHEMTs

Yunshen Long, Zheng Zhong, Yong-Xin Guo

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

28 Citations (Scopus)

Abstract

A novel hybrid large-signal model of GaAs pseudomorphic HEMTs (pHEMTs) is proposed for monolithic microwave integrated circuit design. This new model is based upon accurate electromagnetic (EM) description and creative multi-path artificial neural network (ANN) optimization. To precisely describe the EM effect in the high-frequency range, the extrinsic part of this model includes both lumped and distributed components. In order to re-grid the discrete data, the bias-dependent intrinsic elements are determined by ANNs rather than traditional interpolations. The dispersion effect is represented by nonlinear sources with the multi-path-dependent integration technique, which is described by processed multi-bias S-parameters. This proposed approach can be applicable to different bias conditions, which is also verified by different types of GaAs pHEMTs with good agreement. In addition, a class-AB Ka-band power amplifier and a Ka-band switch using a 0.15-μm GaAs pHEMT process were designed based on the novel hybrid model for further practical verification. © 2016 IEEE.

Original language	English
Article number	7462273
Pages (from-to)	1752-1762
Journal	IEEE Transactions on Microwave Theory and Techniques
Volume	64
Issue number	6
DOIs	https://doi.org/10.1109/TMTT.2016.2555948
Publication status	Published - 1 Jun 2016
Externally published	Yes

Bibliographical note

Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

Research Keywords

Artificial neural network (ANN) three-dimensional nonlinear function
hybrid large-signal model
inconsistency between RF and dc current
integration path independence

Access Output

10.1109/TMTT.2016.2555948

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{404dd8fb94ee4d89bd3831b6608ebbd7,

title = "A Novel 4-D Artificial-Neural-Network-Based Hybrid Large-Signal Model of GaAs pHEMTs",

abstract = "A novel hybrid large-signal model of GaAs pseudomorphic HEMTs (pHEMTs) is proposed for monolithic microwave integrated circuit design. This new model is based upon accurate electromagnetic (EM) description and creative multi-path artificial neural network (ANN) optimization. To precisely describe the EM effect in the high-frequency range, the extrinsic part of this model includes both lumped and distributed components. In order to re-grid the discrete data, the bias-dependent intrinsic elements are determined by ANNs rather than traditional interpolations. The dispersion effect is represented by nonlinear sources with the multi-path-dependent integration technique, which is described by processed multi-bias S-parameters. This proposed approach can be applicable to different bias conditions, which is also verified by different types of GaAs pHEMTs with good agreement. In addition, a class-AB Ka-band power amplifier and a Ka-band switch using a 0.15-μm GaAs pHEMT process were designed based on the novel hybrid model for further practical verification. {\textcopyright} 2016 IEEE.",

keywords = "Artificial neural network (ANN) three-dimensional nonlinear function, hybrid large-signal model, inconsistency between RF and dc current, integration path independence",

author = "Yunshen Long and Zheng Zhong and Yong-Xin Guo",

note = "Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].",

year = "2016",

month = jun,

day = "1",

doi = "10.1109/TMTT.2016.2555948",

language = "English",

volume = "64",

pages = "1752--1762",

journal = "IEEE Transactions on Microwave Theory and Techniques",

issn = "0018-9480",

publisher = "IEEE",

number = "6",

}

TY - JOUR

T1 - A Novel 4-D Artificial-Neural-Network-Based Hybrid Large-Signal Model of GaAs pHEMTs

AU - Long, Yunshen

AU - Zhong, Zheng

AU - Guo, Yong-Xin

N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].

PY - 2016/6/1

Y1 - 2016/6/1

N2 - A novel hybrid large-signal model of GaAs pseudomorphic HEMTs (pHEMTs) is proposed for monolithic microwave integrated circuit design. This new model is based upon accurate electromagnetic (EM) description and creative multi-path artificial neural network (ANN) optimization. To precisely describe the EM effect in the high-frequency range, the extrinsic part of this model includes both lumped and distributed components. In order to re-grid the discrete data, the bias-dependent intrinsic elements are determined by ANNs rather than traditional interpolations. The dispersion effect is represented by nonlinear sources with the multi-path-dependent integration technique, which is described by processed multi-bias S-parameters. This proposed approach can be applicable to different bias conditions, which is also verified by different types of GaAs pHEMTs with good agreement. In addition, a class-AB Ka-band power amplifier and a Ka-band switch using a 0.15-μm GaAs pHEMT process were designed based on the novel hybrid model for further practical verification. © 2016 IEEE.

AB - A novel hybrid large-signal model of GaAs pseudomorphic HEMTs (pHEMTs) is proposed for monolithic microwave integrated circuit design. This new model is based upon accurate electromagnetic (EM) description and creative multi-path artificial neural network (ANN) optimization. To precisely describe the EM effect in the high-frequency range, the extrinsic part of this model includes both lumped and distributed components. In order to re-grid the discrete data, the bias-dependent intrinsic elements are determined by ANNs rather than traditional interpolations. The dispersion effect is represented by nonlinear sources with the multi-path-dependent integration technique, which is described by processed multi-bias S-parameters. This proposed approach can be applicable to different bias conditions, which is also verified by different types of GaAs pHEMTs with good agreement. In addition, a class-AB Ka-band power amplifier and a Ka-band switch using a 0.15-μm GaAs pHEMT process were designed based on the novel hybrid model for further practical verification. © 2016 IEEE.

KW - Artificial neural network (ANN) three-dimensional nonlinear function

KW - hybrid large-signal model

KW - inconsistency between RF and dc current

KW - integration path independence

UR - http://www.scopus.com/inward/record.url?scp=84976333426&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84976333426&origin=recordpage

U2 - 10.1109/TMTT.2016.2555948

DO - 10.1109/TMTT.2016.2555948

M3 - RGC 21 - Publication in refereed journal

SN - 0018-9480

VL - 64

SP - 1752

EP - 1762

JO - IEEE Transactions on Microwave Theory and Techniques

JF - IEEE Transactions on Microwave Theory and Techniques

IS - 6

M1 - 7462273

ER -

A Novel 4-D Artificial-Neural-Network-Based Hybrid Large-Signal Model of GaAs pHEMTs

Abstract

Bibliographical note

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this