测绘学报 ›› 2021, Vol. 50 ›› Issue (12): 1762-1771.doi: 10.11947/j.AGCS.2021.20210233

• 导航卫星系统 • 上一篇    下一篇

GNSS多径信号3种非监督学习法分析与比较

朱彬, 杨诚, 刘岩   

  1. 中国地质大学(北京)土地科学技术学院, 北京 100089
  • 收稿日期:2021-04-30 修回日期:2021-10-08 发布日期:2022-01-08
  • 通讯作者: 杨诚 E-mail:ych8410@163.com
  • 作者简介:朱彬(1997—),男,硕士生,研究方向为GNSS多路径及机器学习。
  • 基金资助:
    国家自然科学基金(41804036;41974033);基科研费优秀教师基金(35832019073)

Analysis and comparison of three unsupervised learning clustering methods for GNSS multipath signals

ZHU Bin, YANG Cheng, LIU Yan   

  1. School of Land Science and Technology, China University of Geosciences(Beijing), Beijing 100089, China
  • Received:2021-04-30 Revised:2021-10-08 Published:2022-01-08
  • Supported by:
    The National Natural Science Foundation of China (Nos. 41804036;41974033);Excellent Teachers Fund Project Based on Scientific Research Funds (No. 35832019073)

摘要: 城市复杂环境中GNSS信号容易被遮挡、反射,导致定位精度下降,定位不连续。本文综合考虑伪距残差、信噪比、高度角和伪距率一致性特征值对GNSS信号的影响,采用k-means++、高斯混合聚类(GMM)和模糊c-均值(FCM)3种非监督学习聚类方法,试图分离视线信号(LOS)、多路径和非视线信号(NLOS)。利用已知坐标的静态GPS/BDS多系统伪距单点定位对3种聚类效果进行了验证。结果表明,3种方法中FCM的轮廓系数最大,聚类性能最好;剔除NLOS信号后,3种方法的定位效果都得到了显著提升。在对比3种方法的RMSE后发现,k-means++和FCM在3个方向的精度提升最好,约为50%。相比于监督分类方法,非监督分类方法剔除NLOS信号方法易于实现,无须先验信息,能降低运算负荷和设备成本,在改善定位精度方面有一定优势。

关键词: 多径信号, 非监督聚类, k-means++, GMM, FCM, 多系统

Abstract: In urban environments, the GNSS signals could be easily blocked and reflected by buildings, which leads to low positioning accuracy and discontinuity. This paper employs k-means++, Gaussian mixed clustering (GMM) and fuzzy c-means (FCM) clustering methods to separate the line-of-sight signals (LOS), multi-path and non-line-of-sight signals (NLOS). The pseudorange residuals, signal-to-noise ratio, elevation angle, as well as pseudorange rate consistency are considered in the three methods. The performance comparisons of the three methods are carried out by static testing of GPS/BDS integrated system in known position point. The results show that FCM has the greatest silhouette coefficient and the best clustering performance. The positioning performance is therefore been greatly improve by eliminating the NLOS. The root mean squares error (RMSE) of point positioning indicates that positioning results can be improved by 50% after NLOS been eliminated by k-means++ and FCM. Compared with the supervised clustering methods, the unsupervised clustering is easy to implement without prior information, has lower computation burden and has certain advantages in improving the positioning accuracy.

Key words: multipath signals, unsupervised clustering, k-means++, GMM, FCM, multiple systems

中图分类号: