滤波辨识(6):输出误差自回归滑动平均系统的滤波辅助模型广义增广迭代参数估计  

Identification.Part F:Filtering-Based Auxiliary Model Generalized Extended Iterative Parameter Estimation for Output-Error Autoregressive Moving Average Systems

作　　者：丁锋[1,2] 栾小丽[1] 徐玲[1] 张霄 周怡红 刘喜梅[2] DING Feng;LUAN Xiaoli;XU Ling;ZHANG Xiao;ZHOU Yihong;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）》2023年第3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(62273167).

摘　　要：输出误差自回归滑动平均模型也称为Box-Jenkins模型。针对Box-Jenkins系统,基于滤波辨识理念,研究和提出了滤波辅助模型广义增广梯度迭代辨识方法、滤波辅助模型多新息广义增广梯度迭代辨识方法、滤波辅助模型多新息广义增广投影迭代辨识方法、滤波辅助模型广义增广最小二乘迭代辨识方法、滤波辅助模型多新息广义增广最小二乘迭代辨识方法。这些滤波辅助模型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。The output-error autoregressive moving average model is also called the Box-Jenkins model.Based on the filtering identification idea,the paper studies and proposes the filtered auxiliary model generalized extended gradient-based iterative identification method,the filtered auxiliary model multi-innovation generalized extended gradient-based iterative identification method,the filtered auxiliary model multi-innovation generalized extended projection-based iterative identification method,the filtered auxiliary model generalized extended least squares-based iterative identification method,and the filtered auxiliary model multi-innovation generalized extended least squares-based iterative identification method for Box-Jenkins systems from available input-output data.These filtered auxiliary model 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 辅助模型辨识 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]