基于实时中值估计的分布式稳健滤波融合方法

A Distributed Robust Filtering and Fusion Method Based on Real-time Median Estimation

针对电子信息装备运动目标多源测量数据加权融合中的复杂电磁环境影响,提出了基于实时中值估计的分布式稳健滤波融合方法。该方法以稳健统计理论为基础,首先给出基于实时中值估计和匀速模型的稳健滤波方法,并将稳健滤波残差刻度应用于权值最优分配原则下的融合权重动态计算,最终得到稳健加权融合结果。典型运动目标实测数据测试结果表明,该方法具有较高的样本崩溃点,能有效处理含一定长度连续粗差的测量数据,且能用于弱机动情形。

In view of the influence of complicated electromagnetic environment on the weighted fusion of multi-source electronic measurement data of moving target,this paper proposed a distributed robust filtering and fusion method based on real-time median estimation.In which,with robust statistics theory as a guide,a robust filter method based on real-time median estimation and constant velocity model was given,and the robust filter residual error scale was applied to the dynamic fusion weights calculation under the optimal weight assignment principle.Then the result of robust weighted fusion could be obtained.The results of the test with typical measured data of moving target showed that the proposed method had higher sample breakdown point,which could work normally under the condition of continuous gross error of a certain length and was still effective for weak maneuvering target.