周卫东1,,
1.哈尔滨工程大学自动化学院 哈尔滨 150001
2.哈尔滨工程大学数学科学学院 哈尔滨 150001
基金项目:国家自然科学基金(61773133)，中央高校基本科研业务费(3072019CF2419)
详细信息
作者简介:王宗原：男，1977年生，讲师，研究方向为统计信号检测与处理
周卫东：男，1966年生，教授，研究方向为卫星导航、组合导航技术
通讯作者:周卫东 zhouweidong@hrbeu.edu.cn
中图分类号:TN911.7计量
文章访问数:1743
HTML全文浏览量:801
PDF下载量:59
被引次数:0
出版历程
收稿日期:2019-03-13
修回日期:2019-07-23
网络出版日期:2019-07-27
刊出日期:2019-12-01
Design and Implementation of Robust Particle Filter Algorithms under Student-t Measurement Distribution
Zongyuan WANG1, 2,Weidong ZHOU1,,
1. College of Automation, Harbin Engineering University, Harbin 150001, China
2. College of Mathematical Sciences, Harbin Engineering University, Harbin 150001, China
Funds:The National Natural Science Foundation of China (61773133), The Fundamental Research Funds of the Central Universities (3072019CF2419)
摘要
摘要:野值是一种异于总体数据的非高斯量测值，在实际传输中野值的加入常使信号出现厚尾特性。粒子滤波是基于贝叶斯框架的适用于非线性/非高斯系统的一种滤波方法。如果在量测噪声中存在野值会使粒子滤波的精度下降。该文利用学生t分布建模量测噪声模型，结合变分贝叶斯(VB)递推方法设计一种新颖的边缘粒子滤波(MPF-VBM)，它在滤波同时可对量测噪声的包括均值在内的全部参数进行实时估计。进一步，利用该估计算法，在量测噪声时变条件下研究了噪声关联的粒子滤波算法(MPF-VBM-COR)。通过对典型单变量增长模型的仿真，验证了所提两种算法相比于已有算法在状态估计上具有更优越的鲁棒性。
关键词:粒子滤波/
变分贝叶斯/
均值估计/
噪声关联/
学生t分布
Abstract:Outliers are non-Gaussian measurement values far from the bulk of data. In practical transmission, the signals added with outlier often have the heavy-tailed property. Particle filter is based on the Bayesian framework and applicable to the non-linear and non-Gaussian system. However, measurement noise with outlier degrades the performance of particle filter. In this paper, student-t distribution is used to model the measurement noise, combined with Variational Bayes (VB), a novel particle filter Marginalized Particle Filter with VB Mean(MPF-VBM) is designed, which can estimate all parameters of t-distributed measurement distribution including mean parameter as well as state. Further, particle filter with noise correlation (MPF-VBM-COR) at the same epoch which is applicable to time variant measurement noise is developed. For verifying the performances of the proposed algorithms, the simulations on the typical univariate non-stationary growth model are performed under the different noise conditions in detail. The outcomes show that the proposed two algorithms of MPF-VBM and MPF-VBM-COR (MPF-VBM-Corrlation) have the superior performances to the compared ones.
Key words:Particle filter/
Variational Bayes(VB)/
Mean estimation/
Noise correlation/
Student-t distribution
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=f2a6752b-e2c4-4ed2-a3d8-c91a65ea9479
