随机多变量系统的结构与参数不变量辨识

IDENTIFICATION OF STRUCTURE AND PARAMETER INVARIANTS FOR MULTIVARIABLE STOCHASTIC LINEAR SYSTEMS

引入多变量系统Ｍａｒｋｏｖ参数矩阵相关分析下的最优输入设计向量，得到Ｍａｒｋｏｖ参数矩阵估计．在此基础上，推导出有色噪声干扰下多变量线性系统Ｋｒｏｎｅｃｋｅｒ结构不变量与参数不变量的递推辨识算法．

Firstly, this paper introduces the optimal input vector for identifying Markov parameter matrices of multivariable linear systems with correlation analysis method. Based on all of the estimated Markov parameters, then, a recursive algorithm is derived for identifying the Kronecker invariants and parameter invariants of multivariable linear systems in the presence of colored noises.