|
|
论文:2014,Vol:32,Issue(6):967-973 |
|
|
引用本文: |
|
|
张烈, 冯燕. 一种优化的神经网络数字预失真方法[J]. 西北工业大学学报 |
|
|
Zhang Lie, Feng Yan. An Optimized Digital Pre-distortion Method Based on Neural Network[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
一种优化的神经网络数字预失真方法 |
|
张烈, 冯燕 |
|
西北工业大学 电子信息学院, 陕西 西安 7100129 |
摘要: |
提出一种基于遗传算法和低阶广义记忆多项式实值神经网络的射频功率放大器数字预失真方法。该方法将遗传算法优化的低阶广义记忆多项式模型与神经网络模型进行级联来增强校正模型与功放失真的匹配程度。它不仅可以提升模型的校正能力,同时可以加快网络的收敛速度。采用60MHz的三载波LTE信号进行实验,通过与实值延时线神经网络模型对比,在收敛速度上有显著提升,同时在邻道功率泄露ACLR指标上有6 d B左右改善。 |
关键词:
射频功率放大器
数字预失真
神经网络模型
广义记忆多项式模型
实值延时线神经网络模型
遗传算法
|
|
An Optimized Digital Pre-distortion Method Based on Neural Network |
|
Zhang Lie, Feng Yan |
|
Department of Electronics Engineering, Northwestern Polytechnical University, Xi'an 710129, China |
Abstract: |
An optimized digital predistortion (DPD) approach of radio frequency (RF) power amplifier (PA) isproposed; It employs real-valued neural network model based on low-order generalized memory polynomial,whichis optimized with genetic algorithm. It cascades genetic algorithm optimized low-order generalized memorypolynomial and neural network model to increase matched degree between correction model and distortion of the PA.It can not only improve the correction ability of the model but also accelerate convergence speed of the model. The60MHz LTE 3 carrier signal is employed to do measurement. Results show that the proposed approach is 6 dB betterthan real-valued focused time delay neural network model in ACLR and gives faster convergence speed. |
Key words:
artificial intelligence
backpropagation algorithms
convergence of numerical methods
flowcharting
generic algorithms
mathematical models
matrix algebra
mean square error
measurements
neuralnetworks
optimization
polynomials
power amplifiers
radio frequency amplifiers
schematic dia-grams
time delay
vectors
digital pre-distortion
RF power amplifiers
generalized memory polyno-mial
real-valued focused time delay neural network model
|
|
收稿日期: 2014-04-12
修回日期:
|
DOI: |
通讯作者:
Email: |
作者简介: 张烈(1981-),西北工业大学博士研究生,主要从事射频功率放大器行为建模与数字预失真研究。
|
|
相关功能 |
|
|
|
作者相关文章 |
|
张烈 在本刊中的所有文章 |
冯燕 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Kang J,Yu D,Min K,et al. A UltraHigh PAE Doherty Amplifier Basedon 0.13-m CMOS process[J]. IEEE Microwave Wire-less Components Letters,2006,16(9): 505-507 [2] Eun C,Powers E J. A New Volterra Predistorter Based on the Indirect Learning Architecture[J]. IEEE Trans on Signal Process-ing,1997,45: 223-227 [3] Morgan D,Ma Z,Zierdt M,Pastalan J. A Generalized Memory Polynomial Model for Digital Predistortion of RF Power Ampli-fiers[J]. IEEE Trans on Signal Processing,2006,54(10): 3852-3860 [4] Lee Kok Chew,Gardner Peter. Adaptive Neuro-Fuzzy Inference System (ANFIS) Digital Predistorter for RF Power AmplifierLinearization[J]. IEEE Trans on Vehicular Technology,2006,55(1):43-50 [5] 唐成凯, 廉保旺, 张玲玲. 卫星通信中动态神经网络预失真算法研究[J]. 西北工业大学学报,2013,31(1): 34-39Tang Chengkai,Lian Baowang,Zhang Lingling. Dynamic Neural Network Based Pre-Distortion in Satellite Communication[J].Journal of Northwestern Polytechnical University,2013,31(1): 34-39 (in Chinese) [6] Liu T, Boumaiza S, Ghannouchi F. Dynamic Behavioral Modeling of 3G Power Amplifiers Using Real-Valued Time-Delay NeuralNetworks[J]. IEEE Trans on Microwave Theory Techniques,2004,52(3): 1025-1033 [7] Isaksson M,Wisell D,Rnnow D. Wide-Band Dynamic Modeling of Power Amplifiers Using Radial-Basis Function Neural Net-works[J]. IEEE Trans on Microwave Theory Techniques,2005,53(11):3422-3428 [8] Danh Luongvinh,Youngwoo Kwon. A Fully Recurrent Neural Network-Based Model for Predicting Spectral Regrowth of 3GHandset Power Amplifiers with Memory Effects[J]. IEEE Microwave Wireless Components Letters,2006,16(11): 621-623 [9] Rawat M,Rawat K,Ghannouchi F M. Adaptive Digital Predistortion of Wireless Power Amplifiers/Transmitters Using DynamicReal-Valued Focused Time-Delay Line Neural Networks[J]. IEEE Trans on Microwave Theory Techniques,2010,58(1):95-104 [10] Farouk Mkadem,Slim Boumaiza. Physically Inspired Neural Network Model for RF Power Amplifier Behavioral Modeling andDigital Predistortion[J]. IEEE Trans on Microwave Theory Techniques,2011,59(4): 913-923 [11] Li Mingyu,Liu Jinting,Jiang Yang,et al. Complex-Chebyshev Functional Link Neural Network Behavioral Model for BroadbandWireless Power Amplifiers[J]. IEEE Trans on Microwave Theory Techniques,2012,60(6): 1979-1989 [12] Sheng Chen, Xia Hong, Yu Gong, et al. Digital Predistorter Design Using B-Spline Neural Network and Inverse of De Boor Algo-rithm[J]. IEEE Trans on Circuits and System-I Regular Papers,2013,60(6): 1584-1594 [13] Meenakshi Rawat,Fadhel M Ghannouchi,Karun Rawat. Three-Layered Biased Memory Polynomial for Dynamic Modeling andPredistortion of Transmitters With Memory[J]. IEEE Trans on Circuits and System-I Regular Papers,2013,60(3): 768-777 [14] Holland J H. Adaptation in Natural and Artificial Systems[M]. Ann Arbor: University of Michigan Press,1975 [15] Sperlich R, Sills J A, Kenney J S. Closed-Loop Digital Pre-Distortion for Power Amplifier Linearization Using Genetic Algorithms[C] ∥Proc of IEEE MTT-S International Microwave Symposium Digest,2003: 768-777 [16] Hagan M T,Demuth H B,Beale M H. 神经网络设计[M]. 北京: 机械工业出版社,2006: 197-255Hagan M T,Demuth H B,Beale M H. Neural Network Design[M]. Beijing,China Machine Press,2006: 197-255 (in Chi-nese) |
|
|
|
|
|
|
|