A Reliable and Fast ANN Based Behavioral Modeling Approach for GaN HEMT

Ahmad Khusro; Saddam Hussain; Mohammad Hashmi; Medet  Auyenur; Abdul Qayyum Ansari

A Reliable and Fast ANN Based Behavioral Modeling Approach for GaN HEMT

Ahmad Khusro, Saddam Hussain, Mohammad Hashmi, Medet Auyenur , Abdul Qayyum Ansari

Department of Electrical and Computer Engineering

Research output: Contribution to conference › Paper › peer-review

1 Citation (Scopus)

Abstract

The paper proposes an accurate, fast and advanced neural network approach to model the small signal behavior of GaN High Electron Mobility Transistor (HEMT). The presented approach makes use of the nonlinear autoregressive series-parallel and parallel architectures to model a 2×200μm device for a broad frequency range of 1GHz – 18GHz. A comparison is drawn between the two architectures based on the training algorithm, accuracy, convergence rate and number of epochs. An excellent agreement is found between the measured S-parameters and the proposed model for the complete broad frequency range. The proposed model can be embedded into computer aided design tool for an accurate and expedited design process of RF/microwave circuits and systems.

Original language	English
Publication status	Published - Aug 15 2019
Event	16th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design - EPFL, Lausanne, Switzerland Duration: Jul 15 2019 → Aug 18 2019

Conference

Conference	16th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design
Abbreviated title	SMACD
Country	Switzerland
City	Lausanne
Period	7/15/19 → 8/18/19

Fingerprint Dive into the research topics of 'A Reliable and Fast ANN Based Behavioral Modeling Approach for GaN HEMT'. Together they form a unique fingerprint.

Cite this

A Reliable and Fast ANN Based Behavioral Modeling Approach for GaN HEMT. / Khusro, Ahmad; Hussain, Saddam; Hashmi, Mohammad; Auyenur , Medet ; Ansari, Abdul Qayyum.

2019. Paper presented at 16th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design , Lausanne, Switzerland.

Research output: Contribution to conference › Paper › peer-review

@conference{422b0eff79004019ad42f5d389abe4a8,

title = "A Reliable and Fast ANN Based Behavioral Modeling Approach for GaN HEMT",

abstract = "The paper proposes an accurate, fast and advanced neural network approach to model the small signal behavior of GaN High Electron Mobility Transistor (HEMT). The presented approach makes use of the nonlinear autoregressive series-parallel and parallel architectures to model a 2×200μm device for a broad frequency range of 1GHz – 18GHz. A comparison is drawn between the two architectures based on the training algorithm, accuracy, convergence rate and number of epochs. An excellent agreement is found between the measured S-parameters and the proposed model for the complete broad frequency range. The proposed model can be embedded into computer aided design tool for an accurate and expedited design process of RF/microwave circuits and systems.",

author = "Ahmad Khusro and Saddam Hussain and Mohammad Hashmi and Medet Auyenur and Ansari, {Abdul Qayyum}",

year = "2019",

month = aug,

day = "15",

language = "English",

note = "16th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design , SMACD ; Conference date: 15-07-2019 Through 18-08-2019",

}

TY - CONF

T1 - A Reliable and Fast ANN Based Behavioral Modeling Approach for GaN HEMT

AU - Khusro, Ahmad

AU - Hussain, Saddam

AU - Hashmi, Mohammad

AU - Auyenur , Medet

AU - Ansari, Abdul Qayyum

PY - 2019/8/15

Y1 - 2019/8/15

N2 - The paper proposes an accurate, fast and advanced neural network approach to model the small signal behavior of GaN High Electron Mobility Transistor (HEMT). The presented approach makes use of the nonlinear autoregressive series-parallel and parallel architectures to model a 2×200μm device for a broad frequency range of 1GHz – 18GHz. A comparison is drawn between the two architectures based on the training algorithm, accuracy, convergence rate and number of epochs. An excellent agreement is found between the measured S-parameters and the proposed model for the complete broad frequency range. The proposed model can be embedded into computer aided design tool for an accurate and expedited design process of RF/microwave circuits and systems.

AB - The paper proposes an accurate, fast and advanced neural network approach to model the small signal behavior of GaN High Electron Mobility Transistor (HEMT). The presented approach makes use of the nonlinear autoregressive series-parallel and parallel architectures to model a 2×200μm device for a broad frequency range of 1GHz – 18GHz. A comparison is drawn between the two architectures based on the training algorithm, accuracy, convergence rate and number of epochs. An excellent agreement is found between the measured S-parameters and the proposed model for the complete broad frequency range. The proposed model can be embedded into computer aided design tool for an accurate and expedited design process of RF/microwave circuits and systems.

M3 - Paper

T2 - 16th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design

Y2 - 15 July 2019 through 18 August 2019

ER -