Linearization design method in class-F power amplifier using artificial neural network

This paper represents the design of a class-F power amplifier (PA), its artificial neural network (ANN) model and a PA linearization method. The designed PA operates at 1.8 GHz with gain of 12 dB and 1dB output compression point (P1dB) of 36 dBm. The proposed ANN model is used to predict the output power of designed class-F PA as a function of input and DC power. This model utilizes the designed class-F PA as a block, which could be used in a desired linearization circuit. In addition, the power added efficiency (PAE) and the other specifications of a PA, related to power can be predicted using the proposed model. A simple feedforward technique is used to improve the linearity of designed PA. For verification, this linearization method is compared with presented neural network model simulations. The results show the improvement of P1dB from 36 to 41 dBm, which is predicted using the proposed model. Also, the PAE of the final linearized circuit PA is predicted.

[1]  D. Wisell,et al.  Wide-band dynamic modeling of power amplifiers using radial-basis function neural networks , 2005, IEEE Transactions on Microwave Theory and Techniques.

[2]  Slim Boumaiza,et al.  Behavioral modeling and digital predistortion of Power Amplifiers with memory using Two Hidden Layers Artificial Neural Networks , 2010, 2010 IEEE MTT-S International Microwave Symposium.

[3]  Chan-Wang Park,et al.  FPGA-implementation of an adaptive neural network for RF power amplifier modeling , 2011, 2011 IEEE 9th International New Circuits and systems conference.

[4]  Gholamreza Karimi,et al.  Designing and modeling of ultra low voltage and ultra low power LNA using ANN and ANFIS for Bluetooth applications , 2013, Neurocomputing.

[5]  Dennis R. Morgan,et al.  A robust digital baseband predistorter constructed using memory polynomials , 2004, IEEE Transactions on Communications.

[6]  Gholamreza Moradi,et al.  An analytic approach for CDMA output of feedforward power amplifier , 2011 .

[7]  Fang Wang,et al.  A new macromodeling approach for nonlinear microwave circuits based on recurrent neural networks , 2000, IMS 2000.

[8]  Jangheon Kim,et al.  Power Efficiency and Linearity Enhancement Using Optimized Asymmetrical Doherty Power Amplifiers , 2011, IEEE Transactions on Microwave Theory and Techniques.

[9]  F. Raab.  Class-F power amplifiers with maximally flat waveforms , 1997 .

[10]  M. G. Chandrasekhar,et al.  ANN modeling for design of a matched low noise pHEMT amplifier for mobile application , 2013 .

[11]  Jungsang Kim,et al.  Digital predistortion of wideband signals based on power amplifier model with memory , 2001 .

[12]  T.J. Brazil,et al.  An efficient Volterra-based behavioral model for wideband RF power amplifiers , 2003, IEEE MTT-S International Microwave Symposium Digest, 2003.

[13]  Peter Gardner,et al.  Neuro-fuzzy approach to adaptive digital predistortion , 2004 .

[14]  Andrei Grebennikov,et al.  RF and Microwave Power Amplifier Design , 2004 .

[15]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[16]  Mingyu Li,et al.  Complex-Chebyshev Functional Link Neural Network Behavioral Model for Broadband Wireless Power Amplifiers , 2012, IEEE Transactions on Microwave Theory and Techniques.

[17]  S.M. El-Ghazaly,et al.  A global modeling approach using artificial neural network , 1999, 1999 IEEE MTT-S International Microwave Symposium Digest (Cat. No.99CH36282).

[18]  F. Raab,et al.  Power amplifiers and transmitters for RF and microwave , 2002 .

[19]  S. Gao,et al.  High efficiency class-F RF/microwave power amplifiers , 2006, IEEE Microwave Magazine.

[20]  M. G. Xibilia,et al.  Advanced Simulation of Semiconductor Devices by Artificial Neural Networks , 2003 .

[21]  Mohsen Hayati,et al.  Modeling of compact microstrip resonator using neural network: Application to design of compact low-pass filter with sharp cut-off frequency , 2011 .

[22]  Michel Nakhla,et al.  A neural network modeling approach to circuit optimization and statistical design , 1995 .

[23]  W. McFarland,et al.  An IC for linearizing RF power amplifiers using envelope elimination and restoration , 1998, 1998 IEEE International Solid-State Circuits Conference. Digest of Technical Papers, ISSCC. First Edition (Cat. No.98CH36156).

[24]  Michel Nakhla,et al.  Analysis and optimization of microwave circuits and devices using neural network models , 1994, 1994 IEEE MTT-S International Microwave Symposium Digest (Cat. No.94CH3389-4).

[25]  Wei Hong,et al.  The Dynamic Behavioral Model of RF Power Amplifiers With the Modified ANFIS , 2009, IEEE Transactions on Microwave Theory and Techniques.

[26]  Giulio Antonini,et al.  Gradient evaluation for neural-networks-based electromagnetic optimization procedures , 2000 .

[27]  William Liu,et al.  MOSFET Models for SPICE Simulation: Including BSIM3v3 and BSIM4 , 2001 .

[28]  F.M. Ghannouchi,et al.  Dynamic behavioral modeling of 3G power amplifiers using real-valued time-delay neural networks , 2004, IEEE Transactions on Microwave Theory and Techniques.

[29]  Ganesh Kothapalli.  Artificial neural networks as aids in circuit design , 1995 .

[30]  Quanyuan Feng,et al.  Behavioral Modeling of RF Power Amplifiers with Memory Effects Using Orthonormal Hermite Polynomial Basis Neural Network , 2013 .

[31]  F.M. Ghannouchi,et al.  Study and Design Optimization of Multiharmonic Transmission-Line Load Networks for Class-E and Class-F $K$-Band MMIC Power Amplifiers , 2007, IEEE Transactions on Microwave Theory and Techniques.

[32]  L.L. Liou,et al.  Input variable space reduction using dimensional analysis for artificial neural network modeling [of MMICs] , 1999, 1999 IEEE MTT-S International Microwave Symposium Digest (Cat. No.99CH36282).

[33]  F Mkadem,et al.  Physically Inspired Neural Network Model for RF Power Amplifier Behavioral Modeling and Digital Predistortion , 2011, IEEE Transactions on Microwave Theory and Techniques.

[34]  Mohsen Hayati,et al.  A broadband Doherty power amplifier with harmonic suppression , 2014 .

[35]  Qi-Jun Zhang,et al.  Neural Network Training-Driven Adaptive Sampling Algorithm for Microwave Modeling , 2000, 2000 30th European Microwave Conference.

[36]  Andrei Grebennikov,et al.  TFA: RF and microwave power amplifier design , 2004, Intelligent Memory Systems.

[37]  D.C. Streit,et al.  A 94-GHz monolithic balanced power amplifier using 0.1-μm gate GaAs-based HEMT MMIC production process technology , 1995, IEEE Microwave and Guided Wave Letters.