传递函数辨识(18):输出误差模型的辅助模型递阶迭代参数估计  

Transfer Function Identification.Part R:Auxiliary Model Hierarchical Iterative Parameter Estimation for Output-Error Models

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）》2021年第1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)。

摘　　要：针对输出误差系统,利用迭代搜索原理,研究了辅助模型梯度迭代算法、辅助模型最小二乘迭代算法、辅助模型多新息梯度迭代算法、辅助模型多新息最小二乘迭代算法;利用递阶辨识原理,研究了辅助模型递阶梯度迭代算法、辅助模型递阶多新息梯度迭代算法、辅助模型递阶最小二乘迭代算法、辅助模型递阶多新息最小二乘迭代算法等。这些辨识方法可以推广到有色噪声的随机系统中。For output-error models,this paper presents the auxiliary model gradient-based iterative algorithm,the auxiliary model least squares-based iterative algorithm,the auxiliary model multi-innovation gradient-based iterative algorithm,and the auxiliary model multi-innovation least squares-based iterative algorithm based on the gradient search principle,and presents the auxiliary model hierarchical gradient-based iterative algorithm,the auxiliary model hierarchical least squares-based iterative algorithm,the auxiliary model hierarchical multi-innovation gradient-based iterative algorithm,and the auxiliary model hierarchical multi-innovation least squares-based iterative algorithm based on the hierarchical identification principle,These methods can be extended to stochastic output-error 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 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]