On-line soft sensor for predicting rubber properties in a mixture process based on regression models with feature selection

1. Sodupe Ortega, E. ¹
2. Urraca Valle, R. ¹
3. Antoñanzas Torres, J.
4. Alía Martínez, M. J. ¹
5. Sanz García, A. ¹
6. Martínez de Pisón Ascacíbar, F. J.

Export

Export

×

MLA

modern-language-association

APA

apa

Chicago

chicago-fullnote-bibliography

Harvard

harvard-cite-them-right

Vancouver

vancouver-author-date

---

RIS BibTex

Export

×

This document cannot be exported because it belongs to another portal.

Full text

lock_openFull text externo

DIALNET GOOGLE SCHOLAR lock_openOpen access editor

Abstract

This communication deals with the complex behavior of rubber mixture processes andthe more accurate estimation of some properties of resulting rubber bands. The mainissue is to develop an on-line soft sensor for estimating significant parameters relatedto rubber properties. The sensor would be able to avoid the continual discard ofdefective material, reducing its high costs associated. This can be achieved bydetecting the unexpected process variations or even bad operating set points.The system is based on a “wrapper” scheme. First, a feature selection routine(backwards selection) is use to find the optimum feature subset from mixture processattributes, which will be utilized as inputs of linear regression model.Those attributes that better explain the dependent variables are determined in aniterative process and the most accurate solution will be finally selected. Our proposedsensor has several advantages, i.e. the use of a linear model provides wider anddeeper knowledge of the industrial process and the backwards selection techniquesallow us to obtain better parsimony models. Eventually, we demonstrate that the softsensor is also able to establish the clear relations between the independent variablesand rheometric parameters of rubber.

Data source: Dialnet