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.
作者
丁锋
栾小丽
徐玲
张霄
周怡红
刘喜梅
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)
出处
《青岛科技大学学报（自然科学版）》
CAS
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).
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
parameter estimation
iterative identification
auxiliary model identification
multi-innovation identification
hierarchical identification
least squares
stochastic system
