Computers and Concrete

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Using generalized regression neural network (GRNN) for mechanical strength prediction of lightweight mortar

  • Razavi, S.V. (Jundi-Shapur University of Technology) ;
  • Jumaat, M.Z. (Civil Engineering Department, University Malaya(UM)) ;
  • Ahmed H., E.S. (Civil Engineering Department, Universiti Kebangsaan Malaysia(UKM)) ;
  • Mohammadi, P. (Islamic Azad University)
  • Received : 2011.06.17
  • Accepted : 2012.04.20
  • Published : 2012.10.25
⟨ Previous Next ⟩

Abstract

In this paper, the mechanical strength of different lightweight mortars made with 0, 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95 and 100 percentage of scoria instead of sand and 0.55 water-cement ratio and 350 $kg/m^3$ cement content is investigated. The experimental result showed 7.9%, 16.7% and 49% decrease in compressive strength, tensile strength and mortar density, respectively, by using 100% scoria instead of sand in the mortar. The normalized compressive and tensile strength data are applied for artificial neural network (ANN) generation using generalized regression neural network (GRNN). Totally, 90 experimental data were selected randomly and applied to find the best network with minimum mean square error (MSE) and maximum correlation of determination. The created GRNN with 2 input layers, 2 output layers and a network spread of 0.1 had minimum MSE close to 0 and maximum correlation of determination close to 1.

Keywords

References

  1. Aydin, A.C., Karakoç, M.B., Düzgün, O.A. and Bayraktutan, M.S. (2010), "Effect of low quality aggregates on the mechanical properties of lightweight concrete", Sci. Res. Essays, 5(10), 1133-1140.
  2. BS EN 992 (1996), Determination of the dry density of lightweight aggregate concrete with open structure, British Standards Institution.
  3. Donald F. Specht (1990), "Probabilistic neural networks", Neural Networks, 3(1), 109-118. https://doi.org/10.1016/0893-6080(90)90049-Q
  4. Famili, H. (1997), "A project about lightweight concrete", Published by University of Elmo sanat, Iran, Tehran.
  5. Gadea, J., Rodríguez, A., Campos, P., Garabito, J. and Calderón, V. (2010), "Lightweight mortar made with recycled polyurethane foam", Cement Concrete Comp., 32(9), 672-677. https://doi.org/10.1016/j.cemconcomp.2010.07.017
  6. Kendrick, R., Acton, D. and Duncan, A. (1994), "Phase-diversity wave-front sensor for imaging systems", Appl. Optics, 33(27), 6533-6547. https://doi.org/10.1364/AO.33.006533
  7. Lanzona, M. and Garcia-Ruiz, P.A. (2008), "Lightweight cement mortars: Advantages and inconveniences of expanded perlite and its influence on fresh and hardened state and durability", Constr. Build. Mater., 22(8), 1798-1806. https://doi.org/10.1016/j.conbuildmat.2007.05.006
  8. Lo, T.Y. and Cui, H.Z. (2004), "Effect of porous lightweight aggregate on strength of concrete", Mater. Lett., 58(6), 916-919. https://doi.org/10.1016/j.matlet.2003.07.036
  9. Mahesh, P. and Surinder, D. (2008), "Modeling pile capacity using support vector machines and generalized regression neural network", J. Geotech. Geoenviron., 134(7), 1021. https://doi.org/10.1061/(ASCE)1090-0241(2008)134:7(1021)
  10. Mahmut, F. and Gungor, M. (2007), "Generalized regression neural networks and feed forward neural networks for prediction of scour depth around bridge piers", Adv. Eng. Softw., 40(8), 731-737.
  11. Mannan, M.A., Alexander, J., Ganapathy, C. and Teo, D. (2006), "Quality improvement of oil palm shell (OPS) as coarse aggregate in lightweight concrete", Build. Environ., 41(9), 1239-1242. https://doi.org/10.1016/j.buildenv.2005.05.018
  12. Merikallio, T. and Mannonen, R. (1996), "Drying of lightweight concrete produced from crushed expended clay aggregates", Comput. Concrete Res., 26(9), 1423-1433. https://doi.org/10.1016/0008-8846(96)00116-0
  13. Mukesh, D. (1996), "Introduction to neural networks: Application of neural computing for process chemists, part 1", J. Chem. Educ., 73(5), 431-434. https://doi.org/10.1021/ed073p431
  14. Rajamane, N.P., Peter, J.A. and Ambily, P.S. (2007), "Prediction of compressive strength of concrete with fly ash as sand replacement material", Cement Concrete Comp., 29(3), 218-223. https://doi.org/10.1016/j.cemconcomp.2006.10.001
  15. Razavi, S.V., Jumaat, M.Z., EI-Shafie, A.H. and Mohammadi, P. (2011), "Artificial neural network for mechanical strength prediction of lightweight mortar", Sci. Res. Essays, 6(16), 3406-3417. https://doi.org/10.5897/SRE11.311
  16. Sanahi, G. (1998), Application of perlit in construction process, University of Tabriz, Iran.
  17. Sari, D. and Pasamehmetoglu, A. (2004), The effect of grading and admixture on the pumice lightweight aggregate concrete, Depart. Civil Eng., Atilim University. Ankara. Turkey.
  18. Shideler, J. (1975), "Lightweight aggregate concrete for structural use", ACI J., 54(4), 299-328.
  19. Shorabi, M. and Rigi, A. (2005), "Application of lightweight concrete properties with lightweight grain of taftan in construction method", 2nd International Conferences on Concrete & Development, Tehran, Iran, 109.
  20. Short, M. and Kinniburgh, W. (1978), Lightweight concrete, Galliard, 464.
  21. Topcu, I.B. and Odler, I. (1996), "Semi lightweight concretes produced by volcanic slags", Cement Concrete Res., 27(1), 15-21.
  22. Unal, O., Uygunog, T. and Yildiz, A. (2007), "Investigation of properties of low strength lightweight concrete for thermal insulation", Build. Environ., 42(2), 584-590. https://doi.org/10.1016/j.buildenv.2005.09.024
  23. Wehenkel, L. (1996), "Contingency severity assessment for voltage security using non-parametric regression techniques", IEEE T. Power Syst., 11(1), 101-111. https://doi.org/10.1109/59.485991
  24. Wei, Y., Yang, J., Lin, Y., Chuang, S. and Wang, H. (2008), "Recycling of harbor sediment as lightweight aggregate", Mar. Pollut. Bull., 57(6-12), 867-872. https://doi.org/10.1016/j.marpolbul.2008.03.033
  25. Williams, T. and Gucunski, N. (1995), "Neural networks for backcalculation of modula from SASW test", J. Comput. Civil Eng., 9(1), 1-9. https://doi.org/10.1061/(ASCE)0887-3801(1995)9:1(1)

Cited by

  1. Inverse identification of impact locations using multilayer perceptron with effective time-domain feature vol.26, pp.3, 2018, https://doi.org/10.1080/17415977.2017.1316496
  2. Comparison of machine learning techniques to predict compressive strength of concrete vol.21, pp.4, 2012, https://doi.org/10.12989/cac.2018.21.4.463