Title :
Application of the PLS-PH algorithm for identification of closed-loop systems
Author :
Quachio, Raphael ; Garcia, Claudio
Author_Institution :
Chemtech - a Siemens Bus., São Paulo, Brazil
Abstract :
In previous papers, the PLS-PH algorithm has presented good results in identifying ill-conditioned systems, where a high collinearity in the collected data is found. All published papers up to now have dealt with open-loop data. One possible source of collinearity in data is the presence of feedback loops. In this paper, models are identified through different MRI methods (PLS-PH and MPEM) and then are compared. The data are collected from a simulated shell-tube heat exchanger controlled by a PI controller.
Keywords :
PI control; closed loop systems; feedback; identification; MPEM; MRI methods; PI controller; PLS-PH algorithm; closed-loop systems; feedback loops; ill-conditioned system identification; partial least squares-prediction horizon; simulated shell-tube heat exchanger; Analytical models; Autoregressive processes; Delay effects; Fluids; Mathematical model; Predictive models; Vectors;
Conference_Titel :
Control and Automation (ICCA), 2011 9th IEEE International Conference on
Conference_Location :
Santiago
Print_ISBN :
978-1-4577-1475-7
DOI :
10.1109/ICCA.2011.6137944
