Title :
A new prediction error identification method for multi-input-multi-output processes
Author :
Cheon, YuJin ; Jeon, Chunho ; Lee, Changkyu ; Lee, Jietae ; Sung, Su Whan
Author_Institution :
Dept. of Chem. Eng., Kyungpook Nat. Univ., Daegu, South Korea
Abstract :
A new prediction error identification method is proposed to identify multi-input-multi-output (MIMO) processes and the initial state. It linearizes the model output with respect to the model parameters so that optimal model parameters can be obtained in an analytic way. And, it has potential to provide a faster convergence rate and a better local minimum in solving the nonlinear optimization problem.
Keywords :
MIMO systems; error analysis; optimisation; multi-input-multi-output processes; optimal model parameters; prediction error identification method; Chemical engineering; Chemical industry; Convergence; Least squares methods; Mathematical model; Newton method; Optimization methods; Predictive models; Recursive estimation; System identification; Linearization; Optimization; Prediction error identification;
Conference_Titel :
ICCAS-SICE, 2009
Conference_Location :
Fukuoka
Print_ISBN :
978-4-907764-34-0
Electronic_ISBN :
978-4-907764-33-3
