Abstract
In carbon black reinforced rubbers, the shape of the carbon black aggregates has a very significant influence on the final properties of the material. Accurately classifying these particles by shape has proven to be difficult, but the results of the classification would allow to model the final mechanical properties of the material. In this work, 21 features are measured from 7714 isolated filler images obtained from TEM images and used for the classification. Support vector machines and artificial neural network techniques are used to classify the aggregates using a methodology to tune the algorithm parameters to improve the performance of the models. Also, genetic algorithms are applied to make a feature selection in order to get most robust and accurate models. It is demonstrated that the combination of genetic algorithms with support vector machines and artificial neural network improves the classification results and minimizes the complexity of the resulting model.
Graphical abstract
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
ASTM Standard D3849–07 (2011) Standard test method for carbon black morphological characterization of carbon black using electron microscopy. ASTM International, West Conshohocken, PA
Bishop C (1995) Neural networks for pattern recognition. Oxford University Press, Oxford
Bishop C (2006) Pattern recognition and machine learning. Springer, New York
Cortes C, Vapnik VN (1995) Support vector networks. Mach Learn 20:273–297
Fernandez Martinez R, Martinez-de-Pison Ascacibar FJ, Pernia Espinoza AV, Lostado Lorza R (2011) Predictive modelling in grape berry weight during maturation process: comparison of data mining, statistical and artificial intelligence techniques. Span J Agric Res 9(4):1156–1167
Fernandez Martinez R, Okariz A, Ibarretxe J, Iturrondobeitia M, Guraya T (2014) Use of decision tree models based on evolutionary algorithms for the morphological classification of reinforcing nano-particle aggregates. Comput Mater Sci 92:102–113
Fernandez Martinez R, Iturrondobeitia M, Ibarretxe J, Guraya T (2017) Methodology to classify the shape of reinforcement fillers: optimization, evaluation, comparison, and selection of models. J Mater Sci 52(1):569–580
Goettler LA, Cole WF (2001) Short fiber-filled rubber composites. In: Bhowmick AK, Stephens HL (eds) Handbook of elastomers, 2nd edn. Marcel Dekker, New York
Hess WM, Ban LL, McDonald GC (1969) Carbon black morphology: I. Particle micro-structure. II. Automated EM analysis of aggregate size and shape. Rubber Chem Technol 42(4):1209–1234
Hess WM, McDonald GC, Urban E (1973) Specific shape characterization of carbon black primary units. Rubber Chem Technol 46(1):204–231
Herd CR, McDonald GC, Hess WM (1992) Morphology of carbon-black aggregates: fractal versus euclidean geometry. Rubber Chem Technol 65(1):107–129
Holland JH (1975) Adaptation in natural and artificial systems. The University of Michigan Press, Ann Arbor
Hsu CW, Lin CJ (2002) A comparison on methods for multi-class support vector machines. IEEE Trans Neural Netw 13:415–425
Kuhn M (2015) Caret: classification and regression training, R package version 6.0-41. http://CRAN.R-project.org/package=caret. Accessed 29 May 2018
Kuhn M, Johnson K (2013) Applied predictive modeling. Springer, New York
Lopez-De-Uralde J, Salazar M, Santamaria A, Zubillaga A, Bringas PG, Guraya T, Okariz A, Gomez E, Saghi Z (2012) Three-dimensional carbon black aggregate reconstruction from two orthogonal TEM images. In: Constitutive models for rubber VII—proceedings of the 7th European conference on constitutive models for rubber, ECCMR, pp 433–438
Lostado R, Fernandez Martinez R, Mac Donald BJ, Villanueva PM (2015) Combining soft computing techniques and the finite element method to design and optimize complex welded products. Integr Comput Aided Eng 22(2):153–170
Lostado R, Escribano Garcia R, Fernandez Martinez R (2016) Optimization of operating conditions for a double-row tapered roller bearing. Int J Mech Mater Des 12(3):353–373
Luengo L, Treuillet S, Gomez E (2015) Automatic grading of carbon blacks from transmission electron microscopy. Proc SPIE Int Soc Opt Eng 9534:95340G
Maas S, Gronski W (1999) Characterization of carbon blacks by transmission electron microscopy and advanced image analysis. Kautsch Gummi Kunstst 52:26–31
Mark JE, Erman B, Eirich FR (2005) Science and technology of rubber, 3rd edn. Elsevier, Amsterdam
Mitchell M (1998) An introduction to genetic algorithms. MIT Press, Cambridge
R Core Team (2016) R: a language and environment for statistical computing. R Foundation for Statistical, Computing, Vienna, Austria. http://www.R-project.org/
Ripley B (1996) Pattern recognition and neural networks. Cambridge University Press, Cambridge
Sanz-Garcia A, Pernia-Espinoza AV, Fernandez-Martinez R, Martinez-De-Pison-Ascacibar FJ (2012) Combining genetic algorithms and the finite element method to improve steel industrial processes. J Appl Logic 10(4):298–308
Scrucca L (2012) GA: a package for genetic algorithms in R. J Stat Softw 53(4):1–37
Vapnik VN (1995) The nature of statistical learning theory. Springer, New York
Vapnik VN (1998) Statistical learning theory. Wiley, New York
Wan Y, Wang M, Ye Z, Lai X (2016) A feature selection method based on modified binary coded ant colony optimization algorithm. Appl Soft Comput J 49:248–258
Weston J, Watkins C (1999) Multi-class support vector machines. In: Verlysen M (ed) Proc ESANN’99. D-Facto Publications, Brussels
Acknowledgements
The authors would like to thank the Basque Government for financial support through the KK-2015/00076-MESALIQ and KK-2016/00032-MESALIQ2, and the University of the Basque Country through the project US15/18 OMETESA.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Communicated by V. Loia.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Fernandez Martinez, R., Jimbert, P., Ibarretxe, J. et al. Use of support vector machines, neural networks and genetic algorithms to characterize rubber blends by means of the classification of the carbon black particles used as reinforcing agent. Soft Comput 23, 6115–6124 (2019). https://doi.org/10.1007/s00500-018-3262-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-018-3262-2