Abstract
The paper deals with the complexity of rubber mixture process. The main issue is to develop well performing on-line soft sensors to monitoring rheological rubber properties. When mixing all raw materials, continual discards of defective materials with high costs associated can be caused by unexpected process variations and incorrect operating set points. Therefore, accurate on-line rubber properties predictions are crucial to obtain higher quality rubber bands. An on-line soft sensor based on a wrapper scheme is proposed to this end. The wrapper is mainly composed of a regression model and a feature selection routine. This routine is designed to find those optimal process variable subsets (input variables) that explain better the rubber properties (output variables). A backwards selection strategy is the basis of the feature selection routine. After an iterative process, the subset finally selected as inputs for the regression model was the one that predicted better the rubber properties. The proposed approach showed several advantages. First, wider and deeper knowledge of the industrial process was clearly achieved. In addition, the final on-line soft sensor was able to establish clear relations between the independent process variables and some rheological parameters of the rubber. A parsimony model was achieved thanks to a combination of a linear model and a selection feature routine that provided these good results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gao YC, Ji J et al (2010) Adaptive least contribution elimination kernel learning approach for rubber mixing soft-sensing modeling . In Intelligent Computing and Intelligent Systems (ICIS), 2010 IEEE International Conference (3):470-474
Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction. 2nd ed. Springer Verlag
Kadlec P, Gabrys B et al (2009) Data-driven soft sensors in the process industry. Comput Chem Eng 33(4):795–814
Küüksille EU, Selba R et al (2011) Prediction of thermodynamic properties of refrigerants using data mining. Energy Convers Manage 52(2):836–848
Marcos AG, Espinoza AVP et al (2007) A neural network-based approach for optimising rubber extrusion lines. Int J Comput Integr Manuf 20(8):828–837
Martínez-de-Pisón FJ, Barreto C et al (2008) Modelling of an elastomer profile extrusion process using support vector machines (SVM). J Mater Process Technol 197(1–3):161–169
Quinlan RJ (1992) Learning with continuous classes. In Proceedings of the Australian joint conference on artificial intelligence. Singapore. pp 343–348. Hobart, Tasmania. World Scientific.
Therneau TM, Atkinson EJ (1997) An introduction to recursive partitioning using the RPART routines
Yang D, Liu Y et al (2009) Online prediction of Mooney viscosity in industrial rubber mixing process via adaptive kernel learning method. In Porceeding of the 48th IEE conference on decision and control 404–409
Zhang Z, Song K et al (2012) A novel nonlinear adaptive Mooney-viscosity model based on DRPLS-GP algorithm for rubber mixing process. Chemom Intell Lab Syst 112(0):17–23
Acknowledgements
The authors are grateful for financial support provided by the University of La Rioja via grant FPI-2012 and for support provided by the Autonomous Government of La Rioja under its 3er Plan Riojano de I + D + I via project FOMENTA 2010/13. Andres Sanz-Garcia is financed by Academy of Finland projects as follows: No. 266486 (FINSKIN) and No. 276371 (VATURP, mobility grant).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Sodupe-Ortega, E., Urraca, R., Antonanzas, J., Alia-Martinez, M., Sanz-Garcia, A., Martínez-de-Pisón, F. (2015). On-line Soft Sensor Based on Regression Models and Feature Selection Techniques for Predicting Rubber Properties in Mixture Processes. In: Ayuso Muñoz, J., Yagüe Blanco, J., Capuz-Rizo, S. (eds) Project Management and Engineering. Lecture Notes in Management and Industrial Engineering. Springer, Cham. https://doi.org/10.1007/978-3-319-12754-5_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-12754-5_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12753-8
Online ISBN: 978-3-319-12754-5
eBook Packages: EngineeringEngineering (R0)