High frequency HEMT modeling using artificial neural network technique

Jianjun Gao, Li Shen, Danting Luo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

Accurate high frequency modeling for active devices which includes microwave diodes and transistors are absolutely necessary for computer-aided radio frequency integrated circuit (RFIC) design. This paper aims to provide an overview on small signal and large signal for field effect transistor (FETs) based on the combination of the conventional equivalent circuit modeling and artificial neural network (ANN) modeling techniques. MLPs and Space-mapped neuromodeling techniques have been used for building a small signal model, and the adjoint technique as well as integration and differential techniques are used for building a large signal model. Experimental results, which confirm the validity of the approaches, are also presented.

Original languageEnglish
Title of host publicationProceedings of 2015 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization, NEMO 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479968114
DOIs
StatePublished - 2015
EventIEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization, NEMO 2015 - Ottawa, Canada
Duration: 11 Aug 201514 Aug 2015

Publication series

NameProceedings of 2015 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization, NEMO 2015

Conference

ConferenceIEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization, NEMO 2015
Country/TerritoryCanada
CityOttawa
Period11/08/1514/08/15

Keywords

  • ANN
  • device
  • modeling

Fingerprint

Dive into the research topics of 'High frequency HEMT modeling using artificial neural network technique'. Together they form a unique fingerprint.

Cite this