基于奇异值分解的广义系统迭代学习控制算法

Iterative Learning Control Algorithm for Generalized Systems Based on Singular Value Decomposition

在对广义系统进行奇异值分解的基础上,研究了一类广义系统的迭代学习控制问题。针对快子系统和慢子系统的特点,分别利用状态误差代入输出误差,得到了一类新的广义系统迭代学习控制算法结构,这一算法是全新的。然后从理论上对所提出的算法进行完整的收敛性分析。分析结果表明,满足给定的收敛条件,系统输出可以渐近地跟踪给定的期望轨迹。

The problem of iterative learning control for a class of generalized systems was investigated based on singular value decomposition of matrix.According to the different characteristics of fast subsystem and slow subsystem,the state errors were introduced into the output errors respectively,and a class of new iterative learning control algorithm for generalized systems was obtained,which was different from the present algorithm.Then,a complete analysis was made to the convergence of the proposed algorithm theoretically.The results show that the system output can track the desired trajectory asymptotically when the given convergence conditions were satisfied.