| 线性多变量系统的辨识规范型及结构辨识算法 |
| |
| 引用本文： | 谢新民,丁锋.线性多变量系统的辨识规范型及结构辨识算法[J].清华大学学报(自然科学版),1992(1). |
| |
| 作者姓名： | 谢新民 丁锋 |
| |
| 作者单位： | 自动化系
(谢新民)，自动化系(丁锋) |
| |
| 摘 要： | 从线性多变量系统状态空间规范型导出了系统的新输入输出辨识规范型，该模型直接与系统的输入输出数据相联系，且待辨识的参数较少，与现在的Ｇｕｉｄｏｒｚｉ辨识模型相比，大大减少了各子系统输出间的重迭（ｏｖｅｒｌａｐｐｉｎｇ）数目。给出了确定其结构指标的算法。数值实例表明了算法的有效性。
|
| 关 键 词： | 线性系统 规范型 结构辨识 |
A canonical identification model for linear multivariable systems and its structural identification algorithm |
| |
| Xie Xinmin,Ding Feng.A canonical identification model for linear multivariable systems and its structural identification algorithm[J].Journal of Tsinghua University(Science and Technology),1992(1). |
| |
| Authors: | Xie Xinmin Ding Feng |
| |
| Institution: | Department of Automation |
| |
| Abstract: | In this paper, a new input-output canonical identification model for linear multivariable systems is derived from its state-space canonical form. This canonical model with fewer parameters to be identified is directly related to the input-output of the system. Compared with the Guidorzi identification model, this canonical model greatly reduces the occurrence of overlapping in outputs of various subsystems. The algorithm for determining its structural indices is given. The numerical example shows that the algorithm works quite well. |
| |
| Keywords: | linear system canonical form structure identification |
| 本文献已被 CNKI 等数据库收录！ |
