离散系统参数自适应辨识的最小二乘正交变换方法  

An Adaptive ldentification Method with Orthogonal MatrixTransformation Based on Least Square Approximation

作　　者：倪筱颖[1,2] 魏明国[1,2] 木壮志 

机构地区：[1]哈尔滨理工大学应用科学学院 [2]武汉水利电力大学基础部

出　　处：《哈尔滨理工大学学报》1999年第2期88-90,共3页Journal of Harbin University of Science and Technology

摘　　要：基于最小二乘法在消除干扰方面的应用，应用矩阵变换及数值拟合的原理，充分考虑随机信号的影响，给出了一种正交变换的离散差分模型自适应辨识方法，它能自动判别模型的阶，还能体现模型参数随信息更新而实时更新的动态过程。提出了渐近消除记忆的时变离散系统参数自适应辨识方法。Based on the application of least spure approximation method in eliminatingdisturbance, using the principles of matrix transmation and numerical fitting, considering the in-fluence of random signals, a kind of adaptive identification method for estimating parameters inone-dimensional discrete system is given, by which the rank of the models can be identifiedautomatically, and the dynamic process of the model parameters updating together withinformation can b e reflected. Meanwhile, the adaptive identification method of approximatingmemory-eliminating for estimating parameters in time-varying descrete system is put forward.

关 键 词：自适应辨识 最小二乘法 正交变换 离散系统 

分 类 号：TP271.8[自动化与计算机技术—检测技术与自动化装置] TP11[自动化与计算机技术—控制科学与工程]