Hostname: page-component-78c5997874-dh8gc Total loading time: 0 Render date: 2024-11-10T12:03:45.995Z Has data issue: false hasContentIssue false
  • English
  • Français

Machine learning-based broadband GaN HEMT behavioral model applied to class-J power amplifier design

Published online by Cambridge University Press:  14 October 2020

Jialin Cai Open the ORCID record for Jialin Cai [Opens in a new window] ,
Justin King ,
Shichang Chen ,
Meilin Wu ,
Jiangtao Su  and
Jianhua Wang
Jialin Cai*
Affiliation:
Key Laboratory of RF Circuit and System, Ministry of Education, Hangzhou Dianzi University, Hangzhou, China
Justin King
Affiliation:
RF Research Group, Trinity College Dublin, Dublin, Ireland
Shichang Chen
Affiliation:
Key Laboratory of RF Circuit and System, Ministry of Education, Hangzhou Dianzi University, Hangzhou, China
Meilin Wu
Affiliation:
Key Laboratory of RF Circuit and System, Ministry of Education, Hangzhou Dianzi University, Hangzhou, China
Jiangtao Su
Affiliation:
Key Laboratory of RF Circuit and System, Ministry of Education, Hangzhou Dianzi University, Hangzhou, China
Jianhua Wang
Affiliation:
Key Laboratory of RF Circuit and System, Ministry of Education, Hangzhou Dianzi University, Hangzhou, China
*
Author for correspondence: Jialin Cai, E-mail: caijialin@hdu.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

A novel, broadband, nonlinear behavioral model, based on support vector regression (SVR) is presented in this paper. The proposed model, distinct from existing SVR-based models, incorporates frequency information into its formalism, allowing the model to perform accurate prediction across a wide frequency band. The basic theory of the proposed model, along with model implementation and the model extraction procedure for radio frequency transistor devices is provided. The model is verified through comparisons with the simulation of an equivalent circuit model, as well as experimental measurements of a 10 W Gallium Nitride (GaN) transistor. It is seen that the efficiency prediction throughout the Smith chart, for varying fundamental and second harmonic loads, across a wideband frequency range, show excellent fidelity to the measured results. Device dc self-biasing is also modelled to allow prediction of power amplifier (PA) efficiency, which is shown to be highly accurate when compared with corresponding measured data. Finally, a class-J PA is constructed and measured across the frequency with a large-signal input tone. The resulting measured and modelled values of key PA performance figures are shown to be in excellent agreement, indicating the model is suitable for broadband PA design.

Keywords

Behavioral modelingbroadbandclass-JGaN HEMTmachine learningpower amplifiersupport vector regression
Type
Power Amplifiers
Information
International Journal of Microwave and Wireless Technologies , Volume 13 , Issue 5 , June 2021 , pp. 415 - 423
Check for updates
Copyright
Copyright © The Author(s), 2020. Published by Cambridge University Press in association with the European Microwave Association

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Dunleavy, L, Baylis, C, Curtice, W and Connick, R (2010) Modeling GaN: powerful but challenging. IEEE Spectrum 11, 82–96.Google Scholar
Eastman, L and Mishra, U (2002) The toughest transistor yet [GaN transistors]. IEEE Spectrum 39, 28–33.CrossRefGoogle Scholar
Whelan, CS, Kolias, NJ, Brierley, S, MacDonald, C and Bernstein, S (2012) GaN technology for radars. in the International Conference on Compound Semiconductor Manufacturing Technology, Apr. 2012, pp. 1–4.Google Scholar
Trew, R (2000) Wide bandgap semiconductor transistors for microwave power amplifiers. IEEE Microwave 1, 46–54.CrossRefGoogle Scholar
Shen, L, Heikman, S, Moran, B, Coffie, R, Zhang, N, Buttari, D, Smorchkova, I, Keller, S, DenBaars, S and Mishra, U (2001) Algan/AlN/GaN high-power microwave HEMT. IEEE Electron Device Letters 22, 457–459.CrossRefGoogle Scholar
Cripps, SC (2006) RF Power Amplifier for Wireless Communications, 2nd Edn. Boston, MA, USA: Artech House.Google Scholar
Root, D, Verspecht, J, Horn, J and Marcu, M (2013) X-Parameters. New York: Cambridge.CrossRefGoogle Scholar
Verspecht, J and Root, DE (2006) Poly harmonic distortion modeling. IEEE Microwave Magazine 7, 44–57.CrossRefGoogle Scholar
Qi, H, Benedikt, J and Tasker, PJ (2009) Nonlinear data utilization: from direct data lookup to behavioral modeling. IEEE Transactions on Microwave Theory and Techniques 57, 1425–1432.CrossRefGoogle Scholar
Woodingon, SP, Saini, R, Williams, D, Lees, J, Benedikt, J and Tasker, PJ (2010) Behavioral model analysis of active harmonic load-pull measurements. Microwave Symposium Digest (MTT), 2010 IEEE MTT-S International. 23–28 May 2010, pp. 1688–1691.CrossRefGoogle Scholar
Root, DE and Verspecht, J (2005) Broad-Band Poly-Harmonic Distortion(PHD) behavioral models from fast automated simulations and large-signal vectorial network measurements. IEEE Transactions on Microwave Theory and Techniques 53, 3656–3664.CrossRefGoogle Scholar
Verspecht, J, Root, DE, Wood, J and Cognata, A (2005) Broad-band multi-harmonic frequency domain behavioral models from automated large-signal vectorial network measurements. IEEE MTT-S International Microwave Symposium Digest Long Beach, CA, June, 2005.CrossRefGoogle Scholar
Cai, J, King, J, Merrick, B and Brazil, TJ (2013) Pade-approximation-based behavioral modeling. IEEE Transactions on Microwave Theory and Techniques 61, 4418–4427.CrossRefGoogle Scholar
Jardel, O, Groote, FD, Reveyrand, T, Jacquet, JC, Charbonniaud, C, Teyssier, J, Floriot, D and Quere, R (2007) An electrothermal model for AlGaN/GaN power HEMTs including trapping effects to improve large-signal simulation results on high VSWR. IEEE Transactions on Microwave Theory and Techniques 55, 2660–2669.CrossRefGoogle Scholar
King, JB and Brazil, TJ (2013) Nonlinear electrothermal GaN HEMT model applied to high-efficiency power amplifier design. IEEE Transactions on Microwave Theory and Techniques 61, 444–454.CrossRefGoogle Scholar
Raffo, A, Bosi, G and Vadala, V (2013.) And Giorgio Vannini “Behavioral modeling of GaN FETs: a load-line approach,”. IEEE Transactions on Microwave Theory and Techniques 61, 444–454.Google Scholar
Crupi, G, Schreurs, DM and Caddemi, A (2010) On the small signal modeling of advanced microwave FETs: a comparative study. International Journal of RF and Microwave Computer-Aided Engineering 18, 417–25.CrossRefGoogle Scholar
Ko, Y, Roblin, P, Landa, AZ-d, Reynose-Hernandez, JA, Nobbe, D, Olson, C and Martinez, FJ (2014) Artificial neural network model of SOS-MOSFETs based on dynamic large-signal measurements. IEEE Transactions on Microwave Theory and Techniques 62, 491–501.CrossRefGoogle Scholar
Liu, T, Boumaiza, S and Ghannouchi, FM (2004) Dynamic behavioral modeling of 3G power amplifier using real-valued time delay neural networks. IEEE Transactions on Microwave Theory and Techniques 52, 1025–1033.CrossRefGoogle Scholar
Xu, J, Halder, S, Kharabi, F, McMacken, J, Gering, J and Root, D (2014) Global dynamic FET model for GaN transistors: DynaFET model validation and comparison to locally tuned models. in 83rd ARFTG Conference Digest, June 2014.CrossRefGoogle Scholar
Gao, J, Lei, Z, Xu, J and Zhang, Q (2005) Nonlinear HEMT modeling using artificial neural network technique. Microwave Symposium Digest, IEEE MTT-S International June 2005, pp. 2–4.Google Scholar
Huang, A, Zhong, Z, Wu, W and Guo, Y (2016) An artificial neural network-based electrothermal model for GaN HEMTs with dynamic trapping effects consideration. IEEE Transactions on Microwave Theory and Techniques 64, 2519–2527.CrossRefGoogle Scholar
Angiulli, G, Cacciola, M and Versaci, M (2007) Microwave device and antennas modeling by support vector regression machines. IEEE Transactions on Magnetics 43, 1589–1592.CrossRefGoogle Scholar
Cai, J, Yu, C, Sun, L, Chen, S and King, JB (2019) Dynamic behavioral modeling of RF power amplifier based on time-delay support vector regression. IEEE Transactions on Microwave Theory and Techniques 67, 533–543.CrossRefGoogle Scholar
Bishop, CM (2006) Patern Recognition and Machine Learning. NewYork, NY, USA: Springer.Google Scholar
Chen, P, Merrick, BM and Brazil, TJ (2015) Bayesian Optimization for broadband high-efficiency power amplifier designs. IEEE Transactions on Microwave Theory and Techniques 63, 4263–4272.CrossRefGoogle Scholar
Cai, J, King, J, Yu, C, Liu, J and Sun, L (2018) Support vector regression-based behavioral modeling technique for RF power transistors. IEEE Microwave and Wireless Component Letters 28, 428–430.CrossRefGoogle Scholar
Drucker, H, Burges, C, Kaufman, L, Smola, A and Vapnik, V. Support vector regression machines. In Mozer, M, Jordan, M and Petsche, T (eds), Advances in Neural Information Processing Systems 9, NIPS 1996. Massachusetts: MIT Press, pp. 155–161.Google Scholar
Wright, P, Lees, J, Benedikt, J, Tasker, PJ and Cripps, SC (2009) A methodology for realizing high efficiency class-J in a linear and broadband PA. IEEE Transactions on Microwave Theory and Techniques 57, 3196–3204.CrossRefGoogle Scholar
Roff, C, Benedikt, J, Tasker, PJ, Wallis, DJ, Hilton, KP, Maclean, JO, Hayes, DG, Uren, MJ and Martin, T (2009) Analysis of DC-RF dispersion in ALGaN/GaN HFETs using RF waveform engineering. IEEE Transactions on Electron Devices 56, 13–19.CrossRefGoogle Scholar
Yarman, BS (2010) Design of Ultra Wideband Power Transfer Networks, 1st Edn. Hoboken, NJ: Wiley.CrossRefGoogle Scholar