An identification method for MIMO continuous‐time systems via iterative learning control concepts
An identification method for MIMO continuous‐time systems via iterative learning control concepts
复制标题
DOI：
10.1002/asjc.265
复制
发表时间：
2011-01
影响因子：
2.4
通讯作者：
F. Sakai;T. Sugie
中科院分区：
文献类型：
--
作者：
F. Sakai;T. Sugie
本文提出了一种基于迭代学习控制（ILC）概念的多变量连续时间系统的辨识方法。为此，投影型迭代学习控制，它更新在一个适当的参数空间的输入，被扩展到多变量系统的情况下。通过将连续时间I/O信号投影到有限维空间和噪声容忍学习算法来实现对测量噪声的鲁棒性。最后，通过一个数值例子说明了在强测量噪声的情况下，如何通过所提出的辨识方法实现参数估计。
This paper presents an identification method based on an iterative learning control (ILC) concept for the multivariable continuous‐time system. For this purpose a projection type ILC, which updates the input in an appropriate parameter space, is extended to the case of multivariable systems. The robustness against measurement noise is achieved through both projection of continuous‐time I/O signals onto a finite dimensional space and noise tolerant learning algorithms. Finally, a numerical example is given to demonstrate how the parameter estimation can be achieved through the proposed identification method in the presence of heavy measurement noises.