具有间歇性观测的无线传感器网络分布式容错目标跟踪  

Fault tolerant distributed target tracking with intermittent observations in wireless sensor networks

作　　者：杨小军[1] 单博炜[1] 梁中华[1] 徐先峰[2] 

机构地区：[1]长安大学信息工程学院,西安710064 [2]长安大学电子与控制工程学院,西安710064

出　　处：《控制与决策》2016年第6期1032-1036,共5页Control and Decision

基　　金：国家自然科学基金项目(61473047;61271262;61201407);陕西省科技计划项目(2015JM6356;2014k-025)

摘　　要：针对具有随机间歇性观测的无线传感器网络,基于多模型估计方法和一致性信息滤波器,提出一种对观测节点故障容错的自适应分布式目标跟踪方法.将传感器节点随机间歇性观测丢失和到达过程建模为马尔科夫切换系统,在容积信息滤波器框架下,估计传感器节点的观测丢失和到达的后验概率.通过观测状态概率组合计算每个局部传感器节点的信息贡献,基于自适应多模型估计方法,实现对间歇性观测的容错性.仿真结果表明了所提出算法的有效性和对间歇性观测的自适应容错性.This paper presents an adaptive fault tolerant distributed target tracking algorithm for wireless sensor networks with intermittent observation based on the multi-model method and consensus information filtering. The loss and arrival of the observation are modeled as a Markov process. The posterior probabilities of intermittent observation loss and arrival are estimated in the framework of Cubature information filtering. The information contributions of each local sensor are calculated via the combination of measurement model probability. The fault tolerance to intermittent observations is obtained based on multi-model estimation. Simulation results show the effectiveness and fault tolerance of the proposed algorithm.

关 键 词：目标跟踪 多模型估计 分布式估计 容积卡尔曼滤波器 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]