|
基于子空间方法的非均匀多采样率系统辨识 |
Subspace-based Method for the Identification of Non-uniformly Multirate Sampling Systems |
投稿时间:2013-07-28 修订日期:2013-09-03 |
DOI: |
中文关键词: 非均匀多采样率系统,状态空间模型,子空间方法,系统辨识 |
英文关键词: non-uniformly multirate sampling systems,state space model,Subspace-based method,system identification |
基金项目: |
|
摘要点击次数: 1428 |
全文下载次数: 0 |
中文摘要: |
针对非均匀多采样率系统的建模问题,根据因果关系,建立了非均匀多采样率系统的状态空间模型。对于含有提升变量的状态空间模型,提出基于子空间技术的辨识方法。首先,由系统的输入输出数据建立由Hankel矩阵组成的扩展状态空间方程;第二,利用斜交投影的原理,以及奇异值分解,通过子空间辨识算法确定增广观测矩阵和状态向量;最后,通过最小二乘方法确定模型的参数矩阵。该算法简单有效且对初值具有鲁棒性。仿真实例验证了算法的有效性。 |
英文摘要: |
A state space model is derived for non-uniformly multirate sampling system due to the casual relationship.Subspace -based identification is developed for state space models,which have lifting variabels.We establish an extended state space equation formed by input-output Hankel matrices,then extended observability matrices and state vector are obtained by oblique projection and singular decomposition.We can determine the parameter matrices using least square algorithm.A simulation example is presented to illustrate the performance of the proposed algorithm. |
View Fulltext
查看/发表评论 下载PDF阅读器 |
关闭 |
|
|
|