计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (8): 125-127.

• 数据库、信号与信息处理 • 上一篇    下一篇

基于RBF神经网络的射频功放行为模型研究

南敬昌1,赵景梅1,袁 杰2   

  1. 1.辽宁工程技术大学 电子与信息工程学院,辽宁 葫芦岛 125105
    2.中国人民解放军72241部队
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-03-11 发布日期:2011-03-11

Research on behavioral models for RF power amplifier based on RBF neural network

NAN Jingchang1,ZHAO Jingmei1,YUAN Jie2   

  1. 1.School of Electrics and Information Engineering,Liaoning Technical University,Huludao,Liaoning 125105,China
    2.Unit 72241 of PLA,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-03-11 Published:2011-03-11

摘要: 为了设计和优化高线性功率放大器和通信子系统,在系统级仿真中,构建功率放大器精确的行为模型是极为重要的。应用实际功率放大器晶体管测试板,通过ADS(Advanced Design System)仿真得到大量功放输入输出数据,建立了一个基于RBF(Radial Basis Function)神经网络的行为模型,给出了RBF 神经网络的结构设计及K-均值聚类算法和共轭梯度优化算法,并进行了模型检验。结果表明,基于RBF神经网络的功放行为模型具有较高的精度,相对于BP 神经网络模型具有更高的逼近能力和速度。

关键词: 径向基函数(RBF)神经网络, 功率放大器, 行为模型

Abstract: In order to design and optimize high-linearity Power Amplifier(PA) and communication subsystem,it is very important to build correct PA behavioral model in system-level simulation.Applying actual transistor testing board of PA,a great amount of input-output data of PA are collected from ADS simulation,it constructs a behavioral model based on RBF(Radial Basis Function) neural network.The structure design and two kinds of learning algorithm of RBF network are presented,and the model is tested.Results show that the PA behavioral model based on RBF has efficient precision,it has better approach activity and speed compared with the BP neural network.

Key words: Radial Basis Function(RBF) neural network, power amplifier, behavioral model