滤波辨识(12):多变量OEARMA系统的滤波辅助模型递阶广义增广迭代参数辨识  

Filtering Identification.Part L:Filtering-Based Auxiliary Model Hierarchical Generalized Extended Iterative Parameter Identification for Multivariable OEARMA Systems

作　　者：丁锋[1,2] 万立娟 栾小丽[1] 徐玲[1] 刘喜梅[2] DING Feng;WAN Lijuan;LUAN Xiaoli;XU Ling;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）》2024年第3期1-16,共16页Journal of Qingdao University of Science and Technology:Natural Science Edition

基　　金：国家自然科学基金项目(62273167)。

摘　　要：针对多变量输出误差自回归滑动平均(M-OEARMA)系统,即多变量Box-Jenkins系统,利用滤波辨识理念和辅助模型辨识思想,研究和提出了滤波辅助模型递阶广义增广梯度迭代辨识方法、滤波辅助模型递阶多新息广义增广梯度迭代辨识方法、滤波辅助模型递阶递推广义增广最小二乘迭代辨识方法、滤波辅助模型递阶多新息广义增广最小二乘迭代辨识方法等。这些滤波辅助模型递阶广义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。For multivariable output-error autoregressive moving average(M-OEARMA)models,which are also called multivariable Box-Jenkins(M-BJ)models,this paper investigates and proposes filtered auxiliary-model hierarchical generalized extended gradient-based iterative identification methods,filtered auxiliary-model hierarchical multi-innovation generalized extended gradient-based iterative identification methods,filtered auxiliary-model hierarchical generalized extended least squares-based iterative identification methods,and filtered auxiliary-model hierarchical multi-innovation generalized extended least squares-based iterative identification methods by using the filtering identification idea and the auxiliary-model identification idea from available input-output data.These filtered auxiliary-model hierarchical generalized 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 滤波辨识 最小二乘 多变量系统 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]