Dynamic Behavioral Modeling of Nonlinear Microwave Devices Using Real-Time Recurrent Neural Network

被引:42
作者
Cao, Yazi [1 ,2 ]
Chen, Xi [3 ]
Wang, Gaofeng [3 ]
机构
[1] Wuhan Univ, Sch Elect Informat, Wuhan 430072, Peoples R China
[2] Carleton Univ, Dept Elect, Ottawa, ON K1S 5B6, Canada
[3] Wuhan Univ, Inst Microelect & Informat Technol, Wuhan 430072, Peoples R China
基金
中国国家自然科学基金;
关键词
pHEMTs; power amplifiers (PAs); real-time recurrent learning (RTRL); recurrent neural network (RNN); POWER-AMPLIFIERS;
D O I
10.1109/TED.2009.2016029
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A novel real-time recurrent neural network (RTRNN) approach is presented for dynamic behavioral macromodeling of nonlinear microwave devices. A modified real-time recurrent learning algorithm is developed to train the neural network model. This proposed RTRNN model can directly be developed from input-output waveform data without having to rely on the internal details of the devices. Once trained, this model provides fast and accurate prediction on the analog behaviors of the nonlinear microwave devices under modeling, which can readily be incorporated into high-level circuit simulation and optimization. This RTRNN approach enhances the neural modeling speed and accuracy. Moreover, it also provides additional flexibility in handing diverse needs of nonlinear microwave circuit designs in the time domain, such as single-tone and multiple-tone simulations and large-signal simulations by comparison to the previously published neural models. The validity of this proposed approach is illustrated through behavioral macromodeling of two typical microwave devices: power amplifiers and pHEMTs.
引用
收藏
页码:1020 / 1026
页数:7
相关论文
共 12 条
[1]  
*AG TECHN, 2006, ADS VERS 2006
[2]   Global modeling strategies for the analysis of high-frequency integrated circuits [J].
Ciampolini, P ;
Roselli, L ;
Stopponi, G ;
Sorrentino, R .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 1999, 47 (06) :950-955
[3]   Backpropagation algorithms for a broad class of dynamic networks [J].
De Jesus, Orlando ;
Hagan, Martin T. .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (01) :14-27
[4]   A new macromodeling approach for nonlinear microwave circuits based on recurrent neural networks [J].
Fang, YH ;
Yagoub, MCE ;
Wang, F ;
Zhang, QJ .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2000, 48 (12) :2335-2344
[5]   Wide-band dynamic modeling of power amplifiers using radial-basis function neural networks [J].
Isaksson, M ;
Wisell, D ;
Rönnow, D .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2005, 53 (11) :3422-3428
[6]   Behavioral modeling of nonlinear RF power amplifiers considering memory effects [J].
Ku, HC ;
Kenney, JS .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2003, 51 (12) :2495-2504
[7]   Dynamic behavioral modeling of 3G power amplifiers using real-valued time-delay neural networks [J].
Liu, TJ ;
Boumaiza, S ;
Ghannouchi, FM .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2004, 52 (03) :1025-1033
[8]   A comparative overview of microwave and wireless power-amplifier behavioral modeling approaches [J].
Pedro, JC ;
Maas, SA .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2005, 53 (04) :1150-1163
[9]  
Schmidt S.R., 1992, Understanding industrial designed experiments, V3rd
[10]   A large-signal characterization of an HEMT using a multilayered neural network [J].
Shirakawa, K ;
Shimiz, M ;
Okubo, N ;
Daido, Y .
IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 1997, 45 (09) :1630-1633