多模型多传感器标量加权信息融合

Multi-model multi-sensor information fusion weighted by scalars

随着生产系统越来越复杂,多传感器的应用也越来越广泛。本文基于标量加权的线性最小方差最优信息融合算法,针对多模型多传感器离散线性随机系统,给出了一种分布式标量加权信息融合Kalman滤波器。它只需要计算标量加权系数,可减小在融合中心的计算负担,并通过仿真例子验证算法的有效性。

Abstract： As production systems become more complex, multi-sensor applications also tend to be more extensive. Based on the optimal information fusion algorithm weighted by scalars in the linear minimum variance sense, a distributed information fusion fixed-lag Kalman filter predictor smoother weighted by scalars is given for discrete linear stochastic system with multiple model and multiple sensors. It only requires for the computation of scalar weights. So the calculated burden in the fusion center can be reduced. A simulation example shows its effectiveness.