多传感器ARMA信号自校正分布式融合Kalman滤波器  

Self-tuning Distributed Fusion Kalman Filter for Multisensor ARMA Signals

作　　者：揭慧[1] 张明波[1] 邓自立[1] 

机构地区：[1]黑龙江大学自动化系,哈尔滨150080

出　　处：《科学技术与工程》2011年第3期443-447,460,共6页Science Technology and Engineering

基　　金：国家自然科学基金(60874063);黑龙江大学自动控制重点实验室项目资助

摘　　要：对含未知模型参数和未知噪声方差的多传感器自回归滑动平均(ARMA)信号,应用递推辅助变量(RIV)算法得到局部模型参数估值器。用相关方法得到局部噪声方差估值器,然后用取局部估值器的平均得到信息融合估值器。将这些融合估值器代入ARMA信号的全局最优分布式融合Kalman滤波器,提出了一种自校正分布式融合Kalman滤波器。用动态误差分析方法证明了它收敛于全局最优分布式Kalman滤波器,因而它具有渐近全局最优性。一个目标位置跟踪系统仿真例子说明了其有效性。For the multisensor autoregressive moving average（ARMA）signals with unknown model parameters and unknown noise variance,using the recursive instrumental variable（RIV）method,the local estimators of the unknown parameters are obtained.Using correlation method,the local estimations of noise variances are obtained,and by averaging the local estimators,the information fusion estimators can be obtained.Substituting these fused estimators into the global optimal distributed Kalman filter of the ARMA signals,a self-tuning fusion distributed fusion Kalman filter is presented.By the dynamic error system analysis（DESA）method,it is peoved that it converges to the global optimal distributed fusion Kalman filter,so that they have asymptotical global optimality.A simulation example for a tracking system with respect to the target position shows its effectiveness.

关 键 词：多传感器信息融合 分布式融合 自校正Kalman滤波器 收敛性 渐近全局最优 

分 类 号：O211.64[理学—概率论与数理统计]