Comparative estimation of models with different structures for estimation of mechanical properties of light steel profiles

  • Zambrano Ortíz Denis Joaquín Technical University of Manabí, Department of Industrial Engineering, Ecuador
  • Litardo Velásquez Rosa Mariuxi Technical University of Manabí, Department of Industrial Engineering, Ecuador
  • Arzola Ruiz José Study Center of Mathematics for Technical Sciences, Technological University of Havana
Keywords: properties estimation, steel profiles, mathematical modeling, steel production, engineering systems

Abstract

The paper presents linear, quadratic, signomial and radial-based neural networks for the estimation of the mechanical properties of steel profiles for construction obtained from the chemical composition of the batches, the cross-section of the profile to be laminated, for the lamination workshops taken as case studies. As primary information, a database with the batches produced in the Antillana de Acero rolling mills is used for more than ten years. The results obtained show that the radial base neural networks applying Landweber's iterative regularization method to network training provide the highest precision. The signomial, quadratic and linear models reach similar values ​​of precision taking as a criterion of comparison the standard deviation of the estimate with respect to the results of the passive experiments obtained from the quality control of the production. The modeling work is done for the case studies of the laminating workshops 250 and 300 of the steel company Antillana de Acero.

Downloads

Download data is not yet available.

References

Arzola, J., (1989). Selection of Proposals. Editorial Technical Scientific, Havana.

Arzola, J., (2000). Engineering Systems First edition. Editorial Félix Varela, Havana.

Arzola, J., (2009). Monograph Analysis and Synthesis of Engineering Systems. Havana.

Arzola, J., Suárez, L., (1993). Rules of Conduct in the projection and conduction of steel heating processes. Rev. Argus, Saltillo.

Arzola, N., Menéndez, A., De León, M., García, E., & Cabrera, A. (1998). Bases for the use of Fertilizers and Amendments. In: Basic Elements on Soils and Fertilizer Uses in the cultivation of CaBa de Az6car. Editors: M. PCrez and J. Campos. Department of Soils and Agrochemistry. INICA , 37-132.

Arzola, RJ and Valdés, OM (2008): Elaboration of Monomial, Posinomial and Signomial Approximation Functions. In XIV Scientific Convention of Engineering and Architecture, La Habana

Ashby, M. F., & Cebon, D. (1993). Materials selection in mechanical design. Le Journal de Physique IV, 3(C7), C7-1.

Ashby, M. F., Shercliff, H., & Cebon, D. (2010). Materials Engineering, science, processing and design, Second Editions, Editorials Elsevier Ltd.

Bin, W. (1994). CAD “Interaction with CAPP”. Manufacturing Systems Design and Analysis.

del Brío González, JA, & Cimadevilla, BJ (2001). Environment and business: from confrontation to opportunity . Madrid: Civitas.

Demuth, H., & Beale, M. (2002). Neural network toolbox for use with Matlab: User’s Guide, Natick, USA: MathWorks.

Elanayar, S., & Shin, Y. C. (1991). Tool wear estimation in turning operations based on radial basis functions. In Intelligent Engineering Systems Through Artificial Neural Networks (pp. 685-692). ASME Press.

Guerra, V.A. (1994). Behavior of the properties of the bars in the Antillana de Acero 200 laminator. Grade Thesis of the UDM. CUJAE, Havana

Hernández, E. H. O., Moncayo, E. H. O., Sánchez, L. K. M., & Calderero, R. P. de. (2017). Behavior of clayey soil existing in the portoviejo canton and its neutralization characteristics. International Research Journal of Engineering, IT & Scientific Research, 3(6), 1-10.

Karayiannis, N. B. (1999). Reformulated radial basis neural networks trained by gradient descent. IEEE transactions on neural networks, 10(3), 657-671. https://doi.org/10.1109/72.761725

Martín del Brío, B., & Sanz Molina, A. (2001). Redes Neuronales y Sistemas Borrosos, 2da. Edición, Ra-Ma, Madrid, España.

Morozov, V. A., & Stessin, M. (1993). Regularization methods for ill-posed problems (p. 257). Boca Raton, FL:: CRC press.

Neto, F. D. M., & da Silva Neto, A. J. (2012). An introduction to inverse problems with applications. Springer Science & Business Media.

Neto, W. P. F., Silvério, H. A., Dantas, N. O., & Pasquini, D. (2013). Extraction and characterization of cellulose nanocrystals from agro-industrial residue–Soy hulls. Industrial Crops and Products, 42, 480-488.

Parraga, WER, Parraga, MAC, Salazar, MJV, & Albear, JJH (2017). Reusing the coconut clay (brick) as construction material. International Research Journal of Engineering, IT & Scientific Research , 3 (4), 102-109.

Patan, K. (2008). Artificial neural networks for the modelling and fault diagnosis of technical processes. Springer.

Sánchez, L. K. M., Hernández, E. H. O., Fernández, L. S. Q., & Párraga, W. E. R. (2018). Determination of Physical and Mechanical Properties of Quarries Dos Bocas Mouths and Mine Copeto for High Resistance Concretes. International Research Journal of Engineering, IT & Scientific Research, 4(2), 33-40.

Silva Neto, A. J. (2012). An inverse analysis of the radiative transfer in a two-layer heterogeneous medium. Inverse Problems in Science and Engineering, 20(7), 917-939.

Silva Neto, A. J., & Moura Neto, F. D. (2005). Inverse Problems–Fundamental Concepts and Applications. EdUERJ, Rio de Janeiro.(In Portuguese).

Silva-Neto, A. J., & Becceneri, J. C. (2009). Bioinspired computational intelligence techniques–application in inverse radiative transfer problems. Notes in Applied Mathematics, SBMAC, So Carlos.

Simpen, I. N., Dewi, N. P. G. B., & Aribudiman, I. N. (2018). Relationship between resistivity and soil strength based on geoelectric data. International Journal of Life Sciences, 2(2), 22-29. https://doi.org/10.29332/ijls.v2n2.126

Snieder, R., & Trampert, J. (1999). Inverse problems in geophysics. In Wavefield inversion (pp. 119-190). Springer, Vienna.

Vt, S. E., & Shin, Y. C. (1994). Radial basis function neural network for approximation and estimation of nonlinear stochastic dynamic systems. IEEE transactions on neural networks, 5(4), 594-603. https://doi.org/10.1109/72.298229

Wesley Hines, J. (1997). Fuzzy and Neural Approaches in Engineering MATLAB Supplement. Fuzzy and Neural Approaches in Engineering, John Wiley & sons, New York.

Published
2019-07-31
How to Cite
Joaquín, Z. O. D., Mariuxi, L. V. R., & José, A. R. (2019). Comparative estimation of models with different structures for estimation of mechanical properties of light steel profiles. International Research Journal of Engineering, IT & Scientific Research, 5(4), 16-27. https://doi.org/10.21744/irjeis.v5n4.687
Section
Articles