DOI QR코드

DOI QR Code

Utilising artificial neural networks for prediction of properties of geopolymer concrete

  • Omar A. Shamayleh (School of Civil and Environmental Engineering Faculty of Engineering and Information Technology, University of Technology Sydney (UTS)) ;
  • Harry Far (School of Civil and Environmental Engineering Faculty of Engineering and Information Technology, University of Technology Sydney (UTS))
  • Received : 2022.11.07
  • Accepted : 2023.01.27
  • Published : 2023.04.25

Abstract

The most popular building material, concrete, is intrinsically linked to the advancement of humanity. Due to the ever-increasing complexity of cementitious systems, concrete formulation for desired qualities remains a difficult undertaking despite conceptual and methodological advancement in the field of concrete science. Recognising the significant pollution caused by the traditional cement industry, construction of civil engineering structures has been carried out successfully using Geopolymer Concrete (GPC), also known as High Performance Concrete (HPC). These are concretes formed by the reaction of inorganic materials with a high content of Silicon and Aluminium (Pozzolans) with alkalis to achieve cementitious properties. These supplementary cementitious materials include Ground Granulated Blast Furnace Slag (GGBFS), a waste material generated in the steel manufacturing industry; Fly Ash, which is a fine waste product produced by coal-fired power stations and Silica Fume, a by-product of producing silicon metal or ferrosilicon alloys. This result demonstrated that GPC/HPC can be utilised as a substitute for traditional Portland cement-based concrete, resulting in improvements in concrete properties in addition to environmental and economic benefits. This study explores utilising experimental data to train artificial neural networks, which are then used to determine the effect of supplementary cementitious material replacement, namely fly ash, Ground Granulated Blast Furnace Slag (GGBFS) and silica fume, on the compressive strength, tensile strength, and modulus of elasticity of concrete and to predict these values accordingly.

Keywords

Acknowledgement

This research is supported by an Australian Government Research Training Program (RTP) Scholarship.

References

  1. Abellan-Garcia, J. (2022), "Study of nonlinear relationships between dosage mixture design and the compressive strength of UHPC", Case Stud. Constr. Mater., 17, 01228. https://doi.org/10.1016/j.cscm.2022.e01228.
  2. Atchley, B.L. (1959), "The effects of fly-ash on dynamic modulus of elasticity of aconcrete mortar", Masters These, Missouri University of Science and Technology, Rolla, MO, USA.
  3. Bafitlhile, T., Li, Z. and Li, Q. (2018), "Comparison of levenberg marquardt and conjugate gradient descent optimization methods for simulation of streamflow using artificial neural network", Adv. Ecol. Environ. Res., 3(2517-9454), 217-237.
  4. Bendapudi, S. and Saha, P. (2011), "Contribution of fly ash to the properties of mortar and concrete", Int. J. Earth Sci. Eng., 4, 974-5904.
  5. Berry, M.J.A. and Linoff, G.S. (2011), Data Mining Techniques: For Marketing, Sales, and Customer Relationship Management, 3 rd Edition, John Wiley & Sons, Hoboken, NJ, USA.
  6. Boga, A.R., Ozturk, M. and Topcu, I.B. (2013), "Using ANN and ANFIS to predict the mechanical and chloride permeability properties of concrete containing GGBFS and CNI", Compos. Part B: Eng., 45(1), 688-696. https://doi.org/10.1016/j.compositesb.2012.05.054.
  7. Boger, Z. and Guterman, H. (1997), "Knowledge extraction from artificial neural network models", 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, Orlando, FL, USA, August.
  8. Chai, T. and Draxler, R.R. (2014), "Root mean square error (RMSE) or mean absolute error (MAE)? - Arguments against avoiding RMSE in the literature", Geosci. Model Dev., 7(3), 1247-1250. https://doi.org/10.5194/gmd-7-1247-2014.
  9. Chi, J., Liu, Y., Wang, V. and Yan, J. (2022), "Performance analysis of three kinds of neural networks in the classification of mask images", J. Phys. Conf. Ser., 2181(1), 012032. https://doi.org/10.1088/1742-6596/2181/1/012032.
  10. Chou, J.S., Tsai, C.F., Pham, A.D. and Lu, Y.H. (2014), "Machine learning in concrete strength simulations: Multi-nation data analytics", Constr. Build. Mater., 73, 771-780. https://doi.org/10.1016/j.conbuildmat.2014.09.054.
  11. Dao, D.V., Ly, H.B., Trinh, S.H., Le, T.T. and Pham, B.T. (2019), "Artificial intelligence approaches for prediction of compressive strength of geopolymer concrete", Mater., 12(6), 983. https://doi.org/10.3390/ma12060983.
  12. Davidovits, J. (1991), "Geopolymers - Inorganic polymeric new materials", J. Therm. Anal., 37(8), 1633-1656. https://doi.org/10.1007/BF01912193.
  13. Deb, P., Nath, P. and Sarker, P. (2015), "Drying shrinkage of slag blended fly ash geopolymer concrete cured at room temperature", 125, 594-600. https://doi.org/10.1016/j.proeng.2015.11.066.
  14. Duval, R. and Kadri, E.H. (1998), "Influence of silica fume on the workability and the compressive strength of high-performance concretes", Cement Concrete Res., 28(4), 533-547. https://doi.org/10.1016/S0008-8846(98)00010-6.
  15. Duxson, P., Provis, J.L., Lukey, G.C. and van Deventer, J.S.J. (2007), "The role of inorganic polymer technology in the development of "green concrete"", Cement Concrete Res., 37(12), 1590-1597. https://doi.org/10.1016/j.cemconres.2007.08.018.
  16. Far, C. and Far, H. (2018), "Improving energy efficiency of existing residential buildings using effective thermal retrofit of building envelope", Indoor Built Environ., 28(6), 744-760. https://doi.org/10.1177/1420326X18794010.
  17. Far, H. and Flint, D. (2017), "Significance of using isolated footing technique for residential construction on expansive soils", Front. Struct. Civil Eng., 11(1), 123-129. https://doi.org/10.1007/s11709-016-0372-8.
  18. Gavin, H.P. (2020), The Levenberg-Marquardt Algorithm for Nonlinear Least Squares Curve-Fitting Problems, Department of Civil and Environmental Engineering, Duke University, Durham, NC, USA.
  19. Getahun, M.A., Shitote, S.M. and Abiero Gariy, Z.C. (2018), "Artificial neural network based modelling approach for strength prediction of concrete incorporating agricultural and construction wastes", Constr. Build. Mater., 190, 517-525. https://doi.org/10.1016/j.conbuildmat.2018.09.097.
  20. Ghaboussi, J., Garrett, J.H. and Wu, X. (1991), "Knowledge-based modeling of material behavior with neural networks", J. Eng. Mech., 117(1), 132-153. https://doi.org/10.1061/(ASCE)0733-9399(1991)117:1(132).
  21. Golchubian, A., Marques, O. and Nojoumian, M. (2021), "Photo quality classification using deep learning", Multimed. Tools. Appl., 80(14), 22193-22208. https://doi.org/10.1007/s11042-021-10766-7.
  22. Golewski, G.L. (2018), "Green concrete composite incorporating fly ash with high strength and fracture toughness", J. Clean. Prod., 172, 218-226. https://doi.org/10.1016/j.jclepro.2017.10.065.
  23. Hyndman, R.J. and Koehler, A.B. (2006), "Another look at measures of forecast accuracy", Int. J. Forecast., 22(4), 679-688. https://doi.org/10.1016/j.ijforecast.2006.03.001.
  24. Jager, S., Allhorn, A. and Biessmann, F. (2021), "A benchmark for data imputation methods", Front Big Data, 4, 693-674. https://doi.org/10.3389/fdata.2021.693674.
  25. Langkamp, D.L., Lehman, A. and Lemeshow, S. (2010), "Techniques for handling missing data in secondary analyses of large surveys", Acad. Pediatr., 10(3), 205-210, https://doi.org/10.1016/j.acap.2010.01.005.
  26. Marquardt, D.W. (1963), "An algorithm for least-squares estimation of nonlinear parameters", J. Soc. Indust. Appl. Math., 11(2), 431-441. https://doi.org/10.1137/0111030.
  27. McClelland, J.L., Rumelhart, D.E. and Group, P.R. (1987), Parallel Distributed Processing, Volume 2: Explorations in the Microstructure of Cognition: Psychological and Biological Models (vol. 2), MIT press, Cambridge, MA, USA.
  28. Mohammed Ali, A., Zidan, R. and Al-Eliwi, B. (2020), "Evaluation of mechanical properties of high-strength concrete with sustainable materials", IOP Conf. Ser.: Mater. Sci. Eng., 745, 012147. https://doi.org/10.1088/1757-899X/745/1/012147.
  29. Naser, M.Z. and Alavi, A.H. (2021), "Error metrics and performance fitness indicators for artificial intelligence and machine learning in engineering and sciences", Arch. Struct. Constr., 2021, 1-25. https://doi.org/10.1007/s44150-021-00015-8.
  30. Omran, B.A., Chen, Q. and Jin, R. (2014), "Prediction of compressive strength of 'green' concrete using artificial neural networks", 50th Annual International Conference of the Associated Schools of Construction, Washington, D.C.,USA, April.
  31. Sairamya, N.J., Susmitha, L., Thomas George, S. and Subathra, M.S.P. (2019), "Chapter 12 - Hybrid approach for classification of electroencephalographic signals using time-frequency images with wavelets and texture features", Intelligent Data Analysis for Biomedical Applications, Academic Press, Cambridge, MA, USA.
  32. Saleh, A., Far, H. and Mok, L. (2018), "Effects of different support conditions on experimental bending strength of thin walled cold formed steel storage upright frames", J. Constr. Steel Res., 150, 1-6. https://doi.org/10.1016/j.jcsr.2018.07.031.
  33. Seiffert, U. (2002), "Artificial neural networks on massively parallel computer hardware", Neurocomput., 57, 135-150. https://doi.org/10.1016/j.neucom.2004.01.011.
  34. Sharma, A. and Puvvadi, S. (2012), "Improvement of strength of expansive soil with waste granulated blast furnace slag", GeoCongress 2012: State of the Art and Practice in Geotechnical Engineering, Oakland, CA, USA, March.
  35. Sheskin, D.J. (2004), Handbook of Parametric and Nonparametric Statistical Procedures, 3rd Edition, Taylor and Francis, Hoboken, NJ, USA.
  36. Smarzewski, P. (2019), "Influence of silica fume on mechanical and fracture properties of high performance concrete", Procedia Struct. Integr., 17, 5-12. https://doi.org/10.1016/j.prostr.2019.08.002.
  37. Smith, G.N. (1986), Probability and Statistics in Civil Engineering, Collins Professional and Technical Books, London, UK.
  38. Tabatabaiefar, H.R. (2016), "Detail design and construction procedure of laminar soil containers for experimental shaking table tests", Int. J. Geotech. Eng., 10(4), 328-336. https://doi.org/10.1080/19386362.2016.1145419.
  39. Tomosawa, F. and Noguchi, T. (1995), "Relationship between compressive strength and modulus of elasticity of high-strength concrete", J. Struct. Constr. Eng., 60, 1-10. https://doi.org/10.3130/aijs.60.1_8.
  40. Wilamowski, B.M. and Hao, Y. (2010), "Improved computation for levenberg-marquardt training", IEEE Trans. Neural Netw., 21(6), 930-937. https://doi.org/10.1109/TNN.2010.2045657.
  41. Yeh, I.C. (1998), "Modeling of strength of high-performance concrete using artificial neural networks", Cement Concrete Res., 28(12), 1797-1808. https://doi.org/10.1016/S0008-8846(98)00165-3.
  42. Ziolkowski, P. and Niedostatkiewicz, M. (2019), "Machine learning techniques in concrete mix design", Mater., 12(8), 1256. https://doi.org/10.3390/ma12081256.
  43. Zupan, J. (1994), "Introduction to artificial neural network (ANN) methods: What they are and how to use them", Acta Chim. Slov., 41, 327-352.