Support vector machine model for regression applied to the estimation of the creep rupture stress in ferritic steels

Authors

  • Carlos Alberto Donís-Díaz Universidad Central de Las Villas
  • Eduardo Valencia Morales Universidad Central de Las Villas
  • Carlos Morell Pérez Universidad Central de Las Villas

DOI:

https://doi.org/10.17533/udea.redin.16683

Keywords:

Creep, ferritic steels, support vector machine, artificial neural network

Abstract

Having as antecedent the use of artificial neural networks (ANN) in the estimation of the creep rupture stress in ferritic steels, new experiments have been developed using Support Vector Machine for Regression (SVMR), a recently method developed into the machine learning field. A comparative analysis between both methods established that SVMR have a better behavior in the problematic of creep. The results are explained theoretically and finally, the use of a model of SVMR that uses a polynomial kernel of third grade and a control capacity constant of 100, is proposed.

|Abstract
= 273 veces | PDF (ESPAÑOL (ESPAÑA))
= 58 veces|

Downloads

Download data is not yet available.

Author Biographies

Carlos Alberto Donís-Díaz, Universidad Central de Las Villas

Centro de Estudios de Informática (CEI).

Eduardo Valencia Morales, Universidad Central de Las Villas

Centro de Estudios de Informática (CEI).

Carlos Morell Pérez, Universidad Central de Las Villas

Centro de Estudios de Informática (CEI).

References

D. J. C. MacKay. “Bayesian Methods for Neural Networks: Theory and Applications”. Neural Networks Summer School. Cambridge University. U.K. 1995. pp. 15-24.

H. K. D. H. Bhadeshia, T. Sourmail. Japan Society for the Promotion of Science, Committee on Heat– Resisting Materials and Alloys. Vol. 44. 2003. pp. 299–314.

F. Masuyama, H. K. Bhadeshia. “Creep strength of high CR Ferritic Steels designed using neural networks and phase stability calculations”. Fifth International Conference on Advances in Materials Technology for Fossil Power Plants October 3-5 (2007). 4B-01. EPRI. Palo Alto. California. 2007.

http://www.msm.ac.uk./map/map.html Consultada el 20 de enero de 2008.

F. Brun, T. Yoshida, J. D. Robson, V. Narayan, H. K. D. H. Bhadeshia, D. J. C. MacKay. “Theoretical design of ferritic creep resistant steels using neural network, kinetic, and thermodynamic models”. Materials Science and Technology. Vol. 15. 1999. pp. 547-554. DOI: https://doi.org/10.1179/026708399101506085

D. Cole, C. Martin-Moran, A.G. Sheard, H. K. Bhadeshia, D. J. C MacKay. “Modelling creep rupture strength of ferritic steel welds”. Science and Technology of Welding and Joining. Vol. 5. 2000. pp. 81-89. DOI: https://doi.org/10.1179/136217100101538065

A. J. Smola, B. Schölkopf. “A tutorial on Support Vector Regression”. Neuro COLT2 Technical Report Series. NC2-TR-1998-030. 1998. pp. 4-18.

B. M. del Brío, A. S. Molina. Redes Neuronales y Sistemas Difusos. Ed. Alfaomega. Zaragoza. 2001. pp. 76-78.

S. Haykin. Neural Networks. A Comprehensive Foundation. 2a ed. Ed. Prentice-Hall. New York. 1994. 1999. pp. 156-255.

Published

2013-09-18

How to Cite

Donís-Díaz, C. A., Valencia Morales, E. ., & Morell Pérez, C. . (2013). Support vector machine model for regression applied to the estimation of the creep rupture stress in ferritic steels. Revista Facultad De Ingeniería Universidad De Antioquia, (47), 53–58. https://doi.org/10.17533/udea.redin.16683