English

应用科学学报 ›› 1998, Vol. 16 ›› Issue (4): 403-408.

• 论文 • 上一篇    下一篇

基于周期平稳信号特性的神经网络波束形成技术

陈宇欣, 何振亚   

  1. 东南大学
  • 收稿日期:1997-08-20 出版日期:1998-12-31 发布日期:1998-12-31
  • 作者简介:陈宇欣:博士生,东南大学无线电工程系,南京 210096
  • 基金资助:
    国家自然科学基金,国家攀登计划重大关键资助

Neural Network Beamforming Technique for Cyclostationary Signals

CHEN YUXIN, HE ZHENYA   

  1. Southeast University, Nanjing 210096
  • Received:1997-08-20 Online:1998-12-31 Published:1998-12-31

PDF

64

被引次数

5

摘要： 绝大多数通信信号都具有周期平稳信号特性,SCORE算法就是一种利用周期平稳信号特性的优良的波束形成算法.然而,对于矩阵运算和矩阵求逆的巨大运算量的要求限制了它的应用.文中根据神经网络理论提出了一种神经网络波束形成技术(NNBFT),较好地解决了这一问题.仿真结果表明其性能优良,抗干扰性强

关键词: 波束形成, 周期平稳, 神经网络

Abstract: Most of the communication signals have the cyclostationary character. SCORE is an excellent algorithm based on cyclostationary. However, main disadvantage of this algorithm is the huge calculation of the matrix compution and the matrix inverse compution. A neural network beamforming technique which can solve this problem successfully is proposed in this paper. The experiment results have shown that this algorithm has better performance and can reject noise strongly.

Key words: beamforming, neural network, cyclostationary