Title :
Gradient-based iterative parameter identification for multi-input multi-output OEMA-like models
Author :
Zhening Zhang ; Feng Ding ; Dongqing Wang
Author_Institution :
Key Lab. oratory of Adv. Process Control for Light Ind. (Minist. of Educ.), Jiangnan Univ., Wuxi, China
fDate :
June 29 2011-July 1 2011
Abstract :
This paper develops a hierarchical gradient-based iterative estimation algorithm for multi-input multi-output output error moving average (OEMA-like) models. In order to solve the difficulties that the noise-free outputs and the noise terms in the information vector/matrix of the corresponding identification model are unmeasurable, we replace the unknown variables in the information vector/matrix with their estimates. The simulation results show the effectiveness of the proposed algorithm.
Keywords :
MIMO systems; gradient methods; matrix algebra; parameter estimation; vectors; gradient-based iterative parameter identification; hierarchical gradient-based iterative estimation algorithm; information vector; matrix; multiinput multioutput OEMA-like models; noise-free outputs; output error moving average like models; Computers; Equations; Iterative methods; Mathematical model; Parameter estimation; Stochastic processes; Hierarchical identification; Iterative estimation; Multivariable CARMA-like model; Multivariable OEMA-like model; Parameter identification;
Conference_Titel :
American Control Conference (ACC), 2011
Conference_Location :
San Francisco, CA
Print_ISBN :
978-1-4577-0080-4
DOI :
10.1109/ACC.2011.5991261
