子空间盲辨识的改进算法  

Improved blind identification algorithm based on subspace method

作　　者：蒋静[1] 赵金平[1] 张端金+[1] 

机构地区：[1]郑州大学信息工程学院,河南郑州450001

出　　处：《计算机工程与设计》2010年第22期4773-4776,共4页Computer Engineering and Design

基　　金：国家留学基金项目(2004841035);河南省教育厅自然科学研究计划基金项目(2010A510017);郑州大学研究生教育基金项目(2009164)

摘　　要：针对单输入多输出(SIMO)系统模型参数的盲辨识问题进行了研究,基于二阶统计量,提出一类改进的子空间辨识算法。依据协方差阵的秩对该矩阵进行分块,在此基础上考虑了实际系统中存在的噪声误差,利用总体最小二乘(TLS)得到一个与噪声子空间相关的量,最后对该量进行标准正交化,得到了噪声子空间。与传统子空间方法相比,改进算法不需要对协方差矩阵进行特征值分解,可以减弱噪声及不确定因素的影响,减少了运算量。仿真实验结果表明了该算法的有效性。The problem of blind identification for the single-input multiple-output （SIMO） system is investigated. An improved subspacebased identification algorithm is presented in terms of second order statistics. Firstly, the covariance matrix is transferred to block matrix based on its rank. Considering the existence of noise and any other errors, the proposed method obtain a matrix related to the noise subspace by using the total least squares （TLS）. Finally, the orthonormalization of the above matrix is the noise subspace, which is important for subspace methods. Compared with the traditional subspace method, the proposed algorithm does not need eigenvalue decomposition of the covariance matrix, and can weaken the influence of the noise and the uncertainty, and reduces computation labor. Simulation example is given to demonstrate the performance of the algorithm.

关 键 词：盲辨识 单输入多输出系统 二阶统计量 子空间 总体最小二乘 

分 类 号：TN911.7[电子电信—通信与信息系统]