Comparative analysis of parameter extraction techniques for AlGaN/GaN HEMT on silicon/sapphire substrate

Abstract We report a comparative study of artificial neural network (ANN) model and small signal model (SSM) based on extracted parameters. ANN model training is done using Levenberg-Marquardt back propagation algorithm, whereas SSM is formed by extracting circuit parameters from measured S-parameters of GaN HEMT on Silicon and Sapphire. It has been found that, for the GaN HEMT parameter extraction, it takes 85 hidden layer neurons to produce the output with higher accuracy. The optimized test and training error/performance are found to be 1.12 × 10− 8/0.97 and 1 × 10− 8/0.99, respectively.

[1]  M. Boussouis,et al.  Neuro‐space mapping modeling approach for trapping and self‐heating effects on GaAs and GaN devices , 2017 .

[2]  J.E. Rayas-Sanchez,et al.  EM-based optimization of microwave circuits using artificial neural networks: the state-of-the-art , 2003, IEEE Transactions on Microwave Theory and Techniques.

[3]  Zlatica Marinkovic,et al.  Wave approach for noise modeling of gallium nitride high electron‐mobility transistors , 2017 .

[4]  T. Slonczewski.  Transconductance as a criterion of electron tube performance , 1949, Bell Syst. Tech. J..

[5]  Herbert Zirath,et al.  Accurate small-signal modeling of HFET's for millimeter-wave applications , 1996 .

[6]  Naofumi Okubo,et al.  Structural determination of multilayered large-signal neural-network HEMT model , 1998 .

[7]  Manfred Berroth,et al.  High-frequency equivalent circuit of GaAs FETs for large-signal applications , 1991 .

[8]  Zlatica Marinkovic,et al.  Comparison between analytical and neural approaches for multibias small signal modeling of microwave‐scaled FETs , 2010 .

[9]  Mauro Mongiardo,et al.  A review of artificial neural networks applications in microwave computer-aided design , 1999 .

[10]  M. Berroth,et al.  Broad-band determination of the FET small-signal equivalent circuit , 1990 .

[11]  P.M. White,et al.  Improved equivalent circuit for determination of MESFET and HEMT parasitic capacitances from "Coldfet" measurements , 1993, IEEE Microwave and Guided Wave Letters.

[12]  Ulrich L. Rohde,et al.  A new and reliable direct parasitic extraction method for MESFETs and HEMTs , 1993, 1993 23rd European Microwave Conference.

[13]  F. Diamand,et al.  Measurement of the Extrinsic Series Elements of a Microwave Mesfet Under Zero Current Conditions , 1982, 1982 12th European Microwave Conference.

[14]  T. Brazil,et al.  An Improved Small-Signal Parameter-Extraction Algorithm for GaN HEMT Devices , 2008, IEEE Transactions on Microwave Theory and Techniques.

[15]  Diego Marti,et al.  Transistor Modeling: Robust Small-Signal Equivalent Circuit Extraction in Various HEMT Technologies , 2013, IEEE Microwave Magazine.

[16]  W. R. Curtice,et al.  Self-Consistent GaAs FET Models for Amplifier Design and Device Diagnostics , 1984 .

[17]  G. Dambrine,et al.  A new method for determining the FET small-signal equivalent circuit , 1988 .

[18]  Zlatica Marinkovic,et al.  Small-signal and noise modeling of class of HEMTs using knowledge-based artificial neural networks , 2013 .

[19]  Zlatica Marinkovic,et al.  Temperature-dependent models of low-noise microwave transistors based on neural networks , 2005 .

[20]  Franco Giannini,et al.  Neural network modeling of microwave FETs based on third‐order distortion characterization , 2006 .

[21]  Michael Georgiopoulos,et al.  Applications of Neural Networks in Electromagnetics , 2001 .

[22]  Valeria Vadala,et al.  Empowering GaN HEMT models: The gateway for power amplifier design , 2017 .

[23]  Qi-Jun Zhang,et al.  Neural Networks for RF and Microwave Design , 2000 .

[24]  Wei-Cheng Lin,et al.  An improved large-signal model by artificial neural network for the MOSFETs operating in the breakdown region , 2017 .

[25]  Yu Wang,et al.  AlGaN/GaN high electron mobility transistors on Si(111) substrates , 2001 .

[26]  Antonio Raffo,et al.  Neural approach for temperature‐dependent modeling of GaN HEMTs , 2015 .

[27]  Dhrubes Biswas,et al.  Artificial neural network modelling of ADS designed Double Pole Double Throw switch , 2014, 18th International Symposium on VLSI Design and Test.

[28]  R. Anholt,et al.  Equivalent-circuit parameter extraction for cold GaAs MESFET's , 1991 .

[29]  Lester F. Eastman,et al.  An improved small-signal equivalent circuit model for III-V nitride MODFET's with large contact resistances , 1997 .

[30]  R. Quéré,et al.  Small signal modeling of high electron mobility transistors on silicon and silicon carbide substrate with consideration of substrate loss mechanism , 2016 .

[31]  Lining Zhang,et al.  Artificial neural network design for compact modeling of generic transistors , 2017 .

[32]  Ruimin Xu,et al.  An efficient parameter extraction method for GaN HEMT small‐signal equivalent circuit model , 2017 .

[33]  Dominique Schreurs,et al.  Constitutive relations for nonlinear modeling of Si/SiGe HBTs using an ANN model , 2005 .

[34]  R. Anholt,et al.  Measurement and analysis of GaAs MESFET parasitic capacitances , 1991 .

[35]  Weicong Na,et al.  A Wiener-Type Dynamic Neural Network Approach to the Modeling of Nonlinear Microwave Devices , 2017, IEEE Transactions on Microwave Theory and Techniques.

[36]  Zlatica Marinkovic,et al.  Microwave FinFET modeling based on artificial neural networks including lossy silicon substrate , 2011 .

[37]  R. A. Minasian,et al.  Simplified GaAs m.e.s.f.e.t. model to 10 GHz , 1977 .

[38]  Shubhankar Majumdar,et al.  Evaluating substrate's effect on RF switch performance via Verilog-A GaN HEMT model , 2017, Microelectron. J..

[39]  Zlatica Marinkovic,et al.  Analysis and validation of neural network approach for extraction of small-signal model parameters of microwave transistors , 2013, Microelectron. Reliab..