基于正交投影的滚动窗口递推闭环子空间辨识

Scroll-Window Recursive Subspace Identification Methods for Closed-loop System Based on Orthogonal Projection

提出了一种基于正交投影的滚动窗口递推闭环子空间的辨识算法.它引入正交投影(QR)分解来进行正交投影、特征值分解,从而实现奇异值分解,并使用了bona fide递推算法来更新QR分解.然后根据投影变量选取原则选用了两个不同的投影变量W1和W2,推导并提出了基于正交投影的两种递推闭环子空间辨识方法.最后,数值仿真表明:提出的递推闭环子空间辨识方法是有效的、可行的.

A novel scroll-window recursive subspaee identification algorithm for a closed-loop system is proposed based on orthogonal projection （Qlt） , which introduces QR decomposition to implement the QR and eigenval- ue decompositon and achieve a singular value deeomposition. In addition, a bona fide reeursive algorithm is used to update Ihe QR decomposition. Then, two different projection variables W1 and W2 are considered ac- cording to the selection principle, and two recursive subspace identification algorithms based on QR are de- rived and proposed. Finally, the numerical simulation results show that the proposed method is ettieient and feasible.