全文下载:
202001001.pdf
文章编号: 1672-6987(2020)01-0001-17; DOI: 10.16351/j.1672-6987.2020.01.001
丁锋1,2, 徐玲1, 刘喜梅2
(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)
摘要: 针对不同环节串联而成的系统,根据系统的幅频特性数据和相频特性数据,利用梯度搜索、牛顿搜索,以及多新息辨识理论和耦合辨识概念,分别研究了幅频特性、幅频相频联合、幅频相频耦合的最小均方算法、随机梯度算法、多新息随机梯度算法、递推梯度算法、多新息递推梯度算法、牛顿递推算法等。文中的方法可以推广用于其他传递函数描述的动态系统参数辨识,如具有共轭零点极点、重零点极点传递函数的参数辨识以及任意非线性函数的参数估计。
关键词: 传递函数; 参数估计; 递推辨识; 迭代辨识; 频率特性; 梯度搜索; 牛顿搜索
中图分类号: TP 273文献标志码: A
引用格式: 丁锋, 徐玲, 刘喜梅. 传递函数辨识(12): 频率响应递推参数估计(串联情形)\[J\]. 青岛科技大学学报(自然科学版), 2020, 41(1): 1-17.
DING Feng, XU Ling, LIU Ximei. Transfer function identification. Part L: Recursive parameter estimation based on the frequency characteristics (cascade case)\[J\]. Journal of Qingdao University of Science and Technology(Natural Science Edition), 2020, 41(1): 1-17.
Transfer Function Identification. Part L: Recursive Parameter Estimation
Based on the Frequency Characteristics (Cascade Case)
DING Feng1,2, XU Ling1, LIU Ximei2
(1.School of Internet of Things Engineering, Jiangnan University, Wuxi 214122, China;
2.College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266061, China)
Abstract: According to the amplitude-frequency characteristic data and phase-frequency characteristic data of the cascade systems with distinct zeros and poles, using the gradient search and the Newton search, and the multi-innovation identification theory and the coupling identification concept, this paper presents the least mean square algorithms, the stochastic gradient (SG) algorithms, the multi-innovation SG algorithms, the recursive gradient (RG) algorithms, the multi-innovation RG algorithms, the Newton recursive algorithms based on the amplitude-frequency characteristics and the combined amplitude-frequency phase-frequency characteristics. Although the methods in this paper are proposed for transfer functions with distinct zeros and poles, they can be extended to the parameter estimation of transfer functions with conjugate zeros and poles and duplicated zeros and poles and nonlinear systems.
Key words: transfer function; parameter estimation; recursive identification; iterative identification; frequency response; gradient search; Newton search
收稿日期: 2020-01-01
基金项目: 国家自然科学基金项目(61873111).
作者简介: 丁锋(1963—),男,博士,“泰山学者”特聘教授,博士生导师.