滤波辨识(2):有限脉冲响应滑动平均系统的滤波增广迭代参数估计  

Filtering Identification. Part B: Filtering-Based Extended Iterative Parameter Estimation for Finite Impulse Response Moving Average Systems

作　　者：丁锋[1,2] 刘喜梅[2] DING Feng;LIU Ximei(School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China;College of Automation and Electronic Engineering,Qingdao University of Science and Technology,Qingdao 266061,China)

机构地区：[1]江南大学物联网工程学院,江苏无锡214122 [2]青岛科技大学自动化与电子工程学院,山东青岛266061

出　　处：《青岛科技大学学报（自然科学版）》2022年第5期1-13,共13页Journal of Qingdao University of Science and Technology:Natural Science Edition

基　　金：国家自然科学基金项目(61873111,61472195)。

摘　　要：基于系统的观测输入输出数据,利用迭代搜索和滤波辨识理念,研究和提出了有限脉冲响应滑动平均系统的滤波增广梯度迭代辨识方法、滤波增广最小二乘迭代辨识方法、滤波多新息增广梯度迭代辨识方法、滤波多新息增广最小二乘迭代辨识方法,以及引入加权因子和遗忘因子的滤波增广迭代辨识方法等。提出的滤波增广迭代辨识方法可以推广到其它有色噪声干扰下的线性和非线性多变量随机系统中。Based on the observation input-output data and using the iterative search and the filtering identification idea, this paper presents a filtered extended gradient-based iterative identification method, a filtered extended least squares-based iterative identification method, a filtered multi-innovation extended gradient-based iterative identification method and a filtered multi-innovation extended least squares-based iterative identification method for finite impulse response moving average systems. The proposed filtered extended iterative identification methods can be extended to other linear and nonlinear multivariable stochastic systems with colored noises.

关 键 词：参数估计 迭代辨识 多新息辨识 递阶辨识 最小二乘 随机系统 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]