[1] Zhai Jianfeng, Zhou Jianyi, Zhao Jianing, Zhang Lei, et al. Behavioral modeling of RF power amplifierswith time-delay feed-forward neural networks [J]. Journal of Southeast University (English Edition), 2008, 24 (1): 6-9. [doi:10.3969/j.issn.1003-7985.2008.01.002]
Copy
Behavioral modeling of RF power amplifierswith time-delay feed-forward neural networks(
)
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 24
- Issue:
- 2008 1
- Page:
- 6-9
- Research Field:
- Electromagnetic Field and Microwave Technology
- Publishing date:
- 2008-03-30
Info
- Title:
- Behavioral modeling of RF power amplifierswith time-delay feed-forward neural networks
- Author(s):
- Zhai Jianfeng; Zhou Jianyi; Zhao Jianing; Zhang Lei; Hong Wei
- State Key Laboratory of Millimeter Waves, Southeast University, Nanjing 210096, China
- PACS:
- TN830.6
- DOI:
- 10.3969/j.issn.1003-7985.2008.01.002
- Abstract:
- A novel behavioral model using three-layer time-delay feed-forward neural networks(TDFFNN)is adopted to model radio frequency(RF)power amplifiers exhibiting memory nonlinearities.In order to extract the parameters, the back-propagation algorithm is applied to train the proposed neural networks.The proposed model is verified by the typical odd-order-only memory polynomial model in simulation, and the performance is compared with different numbers of taped delay lines(TDLs)and perceptrons of the hidden layer.For validating the TDFFNN model by experiments, a digital test bench is set up to collect input and output data of power amplifiers at a 60×106 sample/s sampling rate.The 3.75 MHz 16-QAM signal generated in the vector signal generator(VSG)is chosen as the input signal, when measuring the dynamic AM/AM and AM/PM characteristics of power amplifiers.By comparisons and analyses, the presented model provides a good performance in convergence, accuracy and efficiency, which is approved by simulation results and experimental results in the time domain and frequency domain.
References:
[1] Saleh A.Frequency-independent and frequency-dependent nonlinear models of TWT amplifiers [J].IEEE Trans Commun, 1981, 29(11):1715-1720.
[2] Zhu A, Wren M, Brazil T J.An efficient Volterra-based behavioral model for wideband RF power amplifiers [C]//IEEE MTT-S Int Microwave Symp Dig. Philadelphia, PA, USA, 2003, 2:787-790.
[3] Schetzen M.The Volterra and Wiener theories nonlinear systems [M].New York:Wiley, 1980.
[4] Clark C J, Chrisikos G, Muha M S, et al.Time-domain envelope measurement technique with application to wideband power amplifier modeling [J].IEEE Trans Microwave Theory Tech, 1998, 46(12):2531-2540.
[5] Hyunchui K, Mckinley M D, Kenney J S.Extraction of accurate behavioral models for power amplifiers with memory effects using two-tone measurements [C]//IEEE MTT-S Int Microwave Symp Dig. Seattle, WA, USA, 2002, 1:139-142.
[6] Kim J, Konstantinou K.Digital predistortion of wideband signals based on power amplifier model with memory [J]. Electron Lett, 2001, 37(23):1417-1418.
[7] Ding L, Zhou G T, Morgan D R, et al.A robust digital baseband predistorter constructed using memory polynomials [J].IEEE Trans Commun, 2004, 52(1):159-164.
[8] Ibnkahla M, Sombrin J, Castanie F, et al.Neural networks for modeling nonlinear memoryless communication channels [J].IEEE Trans Commun, 1997, 45(7):768-771.
[9] Liu T J, Boumaiza D R, Ghannouchi M.Dynamic behavioral modeling of 3G power amplifiers using real-valued time-delay neural networks [J].IEEE Trans Microwave Theory Tech, 2004, 52(3):1023-1033.
[10] Luongvinh D, Kwon Y.A fully recurrent neural network-based model for predicting spectral regrowth of 3G handset power amplifiers with memory effects [J].IEEE Microwave and Wireless Components Letters, 2006, 16(11):621-623.
[11] Isaksson M, Wisell D, Ronnow D.Wide-band dynamic modeling of power amplifiers using radial-basis function neural networks [J].IEEE Trans Microwave Theory Tech, 2005, 53(11):3422-3428.
[12] Lee K C, Gardner P.Neuro-fuzzy approach to adaptive digital predistortion [J].Electron Lett, 2004, 40(3):185-186.
[13] Hagan M T, Demuth H B, Beale M H.Neural network design [M].Beijing:China Machine Press, 2003.
[14] Zhai Jianfeng, Xie Ningde, Zhou Jianyi, et al.A novel adaptive baseband digital predistortion technique [J].International Journal of Microwave and Optical Technology, 2007, 2(2):119-123.
[15] Zhou Jianyi, Zhang Lei, Hong Wei, et al.Design of a wideband adaptive linear amplifier with a DSB pilot and complex coherent detection method [J].Microwave Journal, 2006, 49(4):104-114.
[16] Xie Ningde.Investigations on digital predistortion for RF power amplifier [D].Nanjing:School of Information Science and Engineering of Southeast University, 2006.(in Chinese)
Memo
- Memo:
-
Biographies: Zhai Jianfeng(1981—), male, graduate;Zhou Jianyi(corresponding author), male, doctor, professor, jyzhou@ seu.edu.cn.
Foundation items: The National Natural Science Foundation of China(No.60621002), the National High Technology Research and Development Program of China(863 Program)(No.2007AA01Z2B4).
Citation: Zhai Jianfeng, Zhou Jianyi, Zhao Jianing, et al.Behavioral modeling of RF power amplifiers with time-delay feed-forward neural networks[J].Journal of Southeast University(English Edition), 2008, 24(1):6-9.