计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (3): 60-63.

• 学术探讨 • 上一篇    下一篇

基于BP神经网络的蜂窝无线定位算法

毛永毅1,2,3,李明远4,张保军3   

  1. 1.中国科学院 国家授时中心,西安 710600
    2.中国科学院 研究生院,北京 100039
    3.西安邮电学院 电信系,西安 710061
    4.西安交通大学,西安 710049
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-01-21 发布日期:2008-01-21
  • 通讯作者: 毛永毅

Cellular localization algorithm based on BP neural network

MAO Yong-yi1,2,3,LI Ming-yuan4,ZHANG Bao-jun3   

  1. 1.National Time Service Center,Chinese Academy of Sciences,Xi’an 710600,China
    2.Graduate School of the Chinese Academy of Sciences,Beijing 100039,China
    3.Dept. of Electronic and Information,Xi’an University of Post and Telecommunications,Xi’an 710061,China
    4.Xi’an Jiaotong University,Xi’an 710049,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-01-21 Published:2008-01-21
  • Contact: MAO Yong-yi

摘要: 为了解决最小二乘法需要测量数据的先验信息来构造协方差矩阵的问题,提出了基于BP神经网络的蜂窝无线定位算法。该算法融合了移动基站提供的AOA、TOA和TDOA测量值来实现移动台的定位,利用神经网络较快的学习特性和逼近任意非线性映射的能力,使其适用于复杂的多径环境。同时充分利用了定位的冗余和互补信息有效地减小了非视距传播的影响。对基于BP神经网络的定位系统性能进行了仿真,结果表明,基于BP网络的蜂窝无线定位算法消除了定位模糊和基站非理想分布对定位精度的影响,在复杂的多径环境下能够有效地提高定位精度。

关键词: 最小二乘法, 蜂窝系统, 神经网络, 非视距传播

Abstract: In order to solve the problem how to construct covariance matrix that used prescient information of measurement data in least-square-method,a cellular localization algorithm based on the BP neural network is proposed.The measurement of AOA,TOA and TDOA provided by mobile base station is fused to locate mobile.The fast study and non-linear approach capacity of the neural network is made use of to apply in complicated multipath environment.At the same time,the location redundancy and complementary information is full used to mitigate the effect of Non-Line-Of-Sight(NLOS) propagation.The location performance of BP neural network is simulated.The simulation results indicate that the uncertainty of location and the effect of bad basement position is avoided while the cellular localization algorithm based on the BP neural network is used.It’s location accuracy is significantly improved under complicated multipath environment.

Key words: least-square-method, cellular system, neural network, Non-Line-Of-Sight(NLOS)