噪声相关时多通道带乘性噪声系统最优滤波  

Optimal Filtering of Multi-Channel System with Multiplicative Noise During the Noises Relevant

作　　者：褚东升[1] 韩慧[1] 刘滨[1] 

机构地区：[1]青岛海洋大学工程学院,青岛266003

出　　处：《青岛海洋大学学报（自然科学版）》2001年第5期782-788,共7页Journal of Ocean University of Qingdao

基　　金：教育部高等学校骨干教师资助计划项目

摘　　要：针对多通道乘性噪声系统问题的实际需要 ,推广 Rajasekaran滤波算法 ,利用线性最小方差的概念和投影公式 ,导出含有乘性噪声统计特性参数阵特殊乘法运算的新息协方差矩阵 ,并利用这个中间矩阵 ,在观测为多通道 ,且各个通道的乘性噪声不同 ,以及系统的动态噪声和观测噪声同时刻相关的情况下 ,导出状态递推滤波算法 ,该算法在线性最小方差意义下是最优的。并对该算法进行仿真研究 。Owing to the practical requirement of mult i-channel system with multiplicative noise, the Rajasekaran filtering algorithm is broadened. Use of the concept of linear minimum variance and projection form ula deduce the covariance matrix of the innovation sequence, which contains spec ial multiplicative operation of the statisticly characteristic parameter matrix with multiplicative noise. The state recursive-filtering algorithm is daduced b y applying the covariance and according to the multi-channel observation and th e different multiplicative noise of each observation channel and the relevance o f system and observaed noise in the same time. This algorithm is optimal under t he linear Aminimum variance. A number of simulations are performed.

关 键 词：随机系统 乘性噪声 最优滤波 新息序列 协方差矩阵 地震勘探 信噪比 线性最小方差 

分 类 号：P631.4[天文地球—地质矿产勘探]