Thermal Modeling of the GaN HEMT Device Using Decision Tree Machine Learning Technique

In this paper, we have proposed electrothermal modeling of GaN-based HEMT devices. A data-driven approach has been implemented for a temperature range varying from 300 to 600 K, based on one of the core methods of machine learning techniques based on decision tree (DT). The performance of the proposed models was validated through the simulated test examples. The attained outcomes depicted that the developed models predict the HEMT device characteristics accurately depending on the determined mean-squared error (MSE) between the actual and anticipated characteristics. The paper also indicates that the decision tree technique could be specifically beneficial when data are nonlinear and multidimensional, with the different process parameters exhibited profoundly complex interactions.

[1]  Alexander A. Balandin,et al.  Electrothermal simulation of the self-heating effects in GaN-based field-effect transistors , 2006 .

[2]  Syed K. Islam,et al.  Temperature dependent analytical model for current-voltage characteristics of AlGaN/GaN power HEMT , 2009 .

[3]  M. Shur,et al.  Monte Carlo simulation of electron transport in gallium nitride , 1993 .

[4]  V. Palankovski,et al.  High-temperature modeling of AlGaN/GaN HEMTs , 2009, 2009 International Semiconductor Device Research Symposium.

[5]  S. D. Wolter,et al.  High temperature Pt Schottky diode gas sensors on n-type GaN , 1999 .

[6]  Leo Breiman,et al.  Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author) , 2001 .

[7]  Leo Breiman,et al.  Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author) , 2001, Statistical Science.

[8]  G. Vanko,et al.  AlGaN/GaN HEMT Based Hydrogen Sensors With Gate Absorption Layers Formed by High Temperature Oxidation , 2012 .

[9]  K. Brennan,et al.  Electron transport characteristics of GaN for high temperature device modeling , 1998 .

[10]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

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

[12]  K. Y. Tong,et al.  Numerical simulation of current–voltage characteristics of AlGaN/GaN HEMTs at high temperatures , 2005 .

[13]  R. Dimitrov,et al.  Two dimensional electron gases induced by spontaneous and piezoelectric polarization in undoped and doped AlGaN/GaN heterostructures , 2000 .

[14]  Polarization effects and energy band diagram in AlGaN/GaN heterostructure , 2007 .

[15]  Juin J. Liou,et al.  An Explicit Surface Potential Calculation and Compact Current Model for AlGaN/GaN HEMTs , 2015, IEEE Electron Device Letters.

[16]  Basit Qureshi,et al.  bSSA: Binary Salp Swarm Algorithm With Hybrid Data Transformation for Feature Selection , 2021, IEEE Access.

[17]  Improved temperature model of AlGaN/GaN HEMT and device characteristics at variant temperature , 2007 .

[18]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[19]  Armin Shmilovici,et al.  On the use of decision tree induction for discovery of interactions in a photolithographic process , 2003 .

[20]  R. J. Shul,et al.  GAN : PROCESSING, DEFECTS, AND DEVICES , 1999 .

[21]  I. Angelov,et al.  Semi-physical nonlinear model for HEMTs with simple equations , 2010, 2010 Workshop on Integrated Nonlinear Microwave and Millimeter-Wave Circuits.

[22]  Marcio C. Schneider,et al.  Mosfet Modeling for Circuit Analysis and Design , 2007 .

[23]  Sandeep Kumar,et al.  Plant leaf disease identification using exponential spider monkey optimization , 2020, Sustain. Comput. Informatics Syst..

[24]  Jose E. Schutt-Aine,et al.  AN IMPROVED NONLINEAR CURRENT MODEL FOR GAN HEMT HIGH POWER AMPLIFIER WITH LARGE GATE PERIPHERY , 2012 .

[25]  Liu Linsheng.  An improved nonlinear model of HEMTs with independent transconductance tail-off fitting , 2011 .

[26]  J. Massies,et al.  Electron mobility and transfer characteristics in AlGaN/GaN HEMTs , 2005 .

[27]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[28]  P. Neudeck,et al.  High-temperature electronics - a role for wide bandgap semiconductors? , 2002, Proc. IEEE.

[29]  Dan Braha.  Data mining for design and manufacturing: methods and applications , 2001 .

[30]  M. Shur,et al.  Properties of advanced semiconductor materials : GaN, AlN, InN, BN, SiC, SiGe , 2001 .

[31]  Sandeep Kumar,et al.  Automated soil prediction using bag-of-features and chaotic spider monkey optimization algorithm , 2018, Evolutionary Intelligence.