状态等式约束的最优分布式卡尔曼滤波融合.docVIP

状态等式约束的最优分布式卡尔曼滤波融合 徐杰 ，朱允民 四川大学数学学院，四川成都　610064 摘要：本文给出了一个关于状态等式约束的最优分布式卡尔曼滤波融合算法。新的算法用了凸 组合的融合方法，并且凸组合的融合权重可以递推的计算。数值模拟表明状态等式约束的最优 分布式卡尔曼滤波融合算法可能是和中心式的卡尔曼融合算法性能相同。本文给出的方法不仅 仅适用于不等式状态约束的分布式最优分布式卡尔曼滤波融合算法，而且对于非线性状态等式 约束的分布式最优分布式卡尔曼滤波融合算法同样有效. 关键词：卡尔曼滤波;分布式融合; 状态等式约束. 中图分类号： N941.4 Optimal Distributed Kalman Filtering Fusion with State Equality Constraint Xu Jie , Zhu Yun-Min Department of Mathematics, Sichuan University, Chengdu, Sichuan 610064 Abstract: This short paper proposes an optimal distributed Kalman ?ltering fusion algorithm with state equality constraint. The new algorithm uses the convex combination fusion, whose fusion weights are recursively given. Computer experiments show that the performance of this fusion algorithm is very likely to be equivalent to that of the centralized Kalman ?ltering fusion. The method which is presented in this paper not only the optimal distributed Kalman ?ltering fusion with State inequality constraint is valid, but also the optimal distributed Kalman ?ltering fusion with nonlinear state equality constraint is e?ective too. Key words: Kalman ?ltering; Distributed fusion; State Equality Constraint. 0  Introduction The multisensor Kalman ?ltering fusion has received signi?cant attention from many prac- tical domains in recent years, such as target tracking, remote sensing, battle?eld surveillance, monitoring of manufacturing processes and condition-based maintenance of complex machinery. 基金项目： Specialized Research Fund for the Doctoral Program of Higher Education (200806100001). 作者简介： Xu Jie （1979-），male，major research direction：information fusion, convex optimization, stochastic optimal control. Correspondence author：Zhu Yun-Min（1944-），male，professor，major research direction：stochastic approximations, adapted ?ltering, other stochastic recursive algorithms and their applications in estimations, opti- mization, and decision for dynamic systems as well as signal processing, information compression. -1- For Kalman ?lteri