Comparing regressors selection methods for the Soft Sensor design of a Sulfur Recovery Unit

Author

Fortuna, L. ; Graziani, S. ; Xibilia, M.G. ; Napoli, G.

Author_Institution

DIEES, Catania Univ.

fYear

2006

fDate

28-30 June 2006

Firstpage

1

Lastpage

6

Abstract

The paper proposes a comparison of different strategies of regressors selection for the design of a soft sensor for a sulfur recovery unit of a refinery. The soft sensor is designed to replace the on line analyzer during maintenance and it is designed by using nonlinear MA models implemented by a MLP neural network. A number of strategies for the automatic choice of influent input variables and regressors selection, on the basis of available experimental data, are compared with a strategy based on a trial and error approach, guided by the knowledge of the experts, both in terms of their performance and their computational complexity

Keywords

air pollution control; moving average processes; multilayer perceptrons; neurocontrollers; nonlinear systems; oil refining; MLP neural network; computational complexity; nonlinear MA model; refinery; regressor selection; soft sensor design; sulfur recovery unit; trial-error approach; Algorithm design and analysis; Computational complexity; Gases; Input variables; Least squares methods; Neural networks; Nonlinear dynamical systems; Nonlinear systems; Pollution; Tail;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Automation, 2006. MED '06. 14th Mediterranean Conference on

Conference_Location

Ancona

Print_ISBN

0-9786720-1-1

Electronic_ISBN

0-9786720-0-3

Type

conf

DOI

10.1109/MED.2006.328855

Filename

4124961