论文部分内容阅读
多传感器系统由于具有较高的精度及可靠性日益受到研究者的重视。本文针对多传感器观测下的带乘性噪声系统 ,分别给出了集中式与分布式滤波融合算法。这 2种算法在数学上完全等价 ,在线性最小方差意义上均是最优的。但对于工程实际问题 ,分布式的融合策略在计算、可靠性、故障的检测与隔离等方面更具有优势。文中举例验证了这 2种融合算法的有效性。
Multi-sensor systems are gaining more and more attention by researchers due to their high accuracy and reliability. In this paper, aiming at the multiplicative noise system with multisensor observation, a fusion algorithm of centralized and distributed filtering is presented respectively. These two algorithms are completely equivalent mathematically and are optimal in the sense of linear minimum variance. However, for practical engineering problems, the distributed fusion strategy has more advantages in terms of calculation, reliability, fault detection and isolation. An example is given to verify the validity of these two fusion algorithms.