多传感器分布式区间估计融合

Multisensor distributed interval estimation fusion

考虑了对未知参数θ的多传感器分布式区间估计融合问题 .建立了一种最优区间估计融合模型———凸线性组合融合 ,并给出搜索最优权系数的Gauss Seidel迭代算法 ,另外 ,给出了一种近似的区间估计融合 ,它能减少大量的计算量 ,并且在某些情况下可以达到最优的估计性能 .最后采用计算机数值模拟 ,用以上方法得到的融合区间估计均优于每个传感器的区间估计的性能 .

This paper deals with multisensor statistical interval estimation fusion for the purpose of estimation of a parameter θ. A multisensor optimal convex linear fusion model for interval estimation fusion is established.A Gauss-Seidel iteration computation method for searching for the fusion weights is suggested. In particular, we suggest convex combination minimum variance fusion that reduces huge computation of fusion and yields approximately optimal estimate performance generally, moreover, may achieves exactly optimal performance in some cases. The above results are supported by simulations.