双率时变系统遗忘因子最小二乘参数估计

Parameter estimation for the forgotten factor least squares algorithm for dual-rate time-varying systems

针对一类双采样率随机时变系统,应用多项式变换技术和随机过程理论,在强持续激励条件下,研究了双率时变遗忘因子最小二乘法(dual-rate forgotten factor least squares,DR-FFLS)的参数估计收敛性,得到了参数估计误差上界的精确表达式。分析表明,随着数据长度k的增加,DR-FFLS算法的参数估计误差上界收敛到常数。同时分析了双率确定性时不变系统、随机时不变系统、确定性时变系统的参数估计误差上界。仿真实例验证了对于随机时变与不变双率系统,同样可得参数估计误差小于参数估计误差上界,并且随着k的增大,参数估计误差上界趋于常数。

The convergence properties of the forgotten factor least squares algorithm for dual-rate time-varying systems are studied for strong persistent excitation based on the polynomial transform technique and stochastic system theory.The upper-bound of the parameter estimation error (PEE) is presented.The analysis indicates that the mean square PEE upper-bound of the algorithm approaches a finite positive constant as the data length increases.The PEE upper-bounds of deterministic time-invariant dual-rate systems,...