Computers and Concrete

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Non-destructive assessment of the three-point-bending strength of mortar beams using radial basis function neural networks

  • Alexandridis, Alex (Department of Electronic Engineering, Technological Educational Institute of Athens) ;
  • Stavrakas, Ilias (Department of Electronic Engineering, Technological Educational Institute of Athens) ;
  • Stergiopoulos, Charalampos (Department of Electronic Engineering, Technological Educational Institute of Athens) ;
  • Hloupis, George (Department of Electronic Engineering, Technological Educational Institute of Athens) ;
  • Ninos, Konstantinos (Department of Electronic Engineering, Technological Educational Institute of Athens) ;
  • Triantis, Dimos (Department of Electronic Engineering, Technological Educational Institute of Athens)
  • Received : 2015.05.06
  • Accepted : 2015.12.14
  • Published : 2015.12.25
⟨ Previous Next ⟩

Abstract

This paper presents a new method for assessing the three-point-bending (3PB) strength of mortar beams in a non-destructive manner, based on neural network (NN) models. The models are based on the radial basis function (RBF) architecture and the fuzzy means algorithm is employed for training, in order to boost the prediction accuracy. Data for training the models were collected based on a series of experiments, where the cement mortar beams were subjected to various bending mechanical loads and the resulting pressure stimulated currents (PSCs) were recorded. The input variables to the NN models were then calculated by describing the PSC relaxation process through a generalization of Boltzmannn-Gibbs statistical physics, known as non-extensive statistical physics (NESP). The NN predictions were evaluated using k-fold cross-validation and new data that were kept independent from training; it can be seen that the proposed method can successfully form the basis of a non-destructive tool for assessing the bending strength. A comparison with a different NN architecture confirms the superiority of the proposed approach.

Keywords

Acknowledgement

Supported by : European Union

References

  1. Alexandridis, A., Sarimveis, H. and Bafas, G. (2003), "A new algorithm for online structure and parameter adaptation of RBF networks", Neural Networks, 16(7), 1003-1017. https://doi.org/10.1016/S0893-6080(03)00052-2
  2. Alexandridis, A., Triantis, D., Stavrakas, I. and Stergiopoulos, C. (2012a), "A neural network approach for compressive strength prediction in cement-based materials through the study of pressure stimulated electrical signals", Constr. Build. Mater., 30, 294-300. https://doi.org/10.1016/j.conbuildmat.2011.11.036
  3. Alexandridis, A., Chondrodima, E. and Sarimveis, H. (2012b), "Radial basis function network training using a nonsymmetric partition of the input space and particle swarm optimization", IEEE Trans. Neural Network. Learn. Syst., 24(2), 219-230. https://doi.org/10.1109/TNNLS.2012.2227794
  4. Alexandridis, A., Stogiannos, M. Kyriou, A. and Sarimveis, H. (2013), "An offset-free neural controller based on approximating the inverse process dynamics", J. Process Cont., 23(7), 968-979. https://doi.org/10.1016/j.jprocont.2013.04.008
  5. Alexandridis, A. (2013), "Evolving RBF neural networks for adaptive soft-sensor design", Int. J. Neur. Syst., 23(6), 1350029. https://doi.org/10.1142/S0129065713500299
  6. Alexandridis, A. and Chondrodima, E. (2014), "A medical diagnostic tool based on radial basis function classifiers and evolutionary simulated annealing", J. Biomed. Inform., 49, 61-72. https://doi.org/10.1016/j.jbi.2014.03.008
  7. Balayssac, J.P., Laurens, S., Breysse, D. and Garnier, V. (2013), Evaluation of concrete properties by combining NDT methods. Nondestructive Testing of Materials and Structures, Springer, Netherlands.
  8. Beycioglu, A., Emiroglu, M., Kocak, Y. and Subas, S. (2015), "Analyzing the compressive strength of clinker mortars using approximate reasoning approaches-ANN vs MLR", Comput. Concrete, 15(1), 89-102. https://doi.org/10.12989/cac.2015.15.1.089
  9. Christopoulos, S.R.G. and Sarlis, N.V. (2014), "q-exponential relaxation of the expected avalanche size in the coherent noise model", Physica A: Stat. Mech. Appl., 407, 216-225. https://doi.org/10.1016/j.physa.2014.03.090
  10. Demir, A. (2015), "Prediction of hybrid fibre-added concrete strength using artificial neural networks", Comput. Concrete, 15(4), 503-514. https://doi.org/10.12989/cac.2015.15.4.503
  11. Enomoto, J. and Hashimoto, H. (1990), "Emission of charged particles from indentation fracture of rocks", Nature, 346(6285), 641-643. https://doi.org/10.1038/346641a0
  12. Hadjicontis, V. and Mavromatou, C. (1994), "Transient electric signals prior to rock failure under uniaxial compression", Geophys. Res. Lett., 21(16), 1687-1690. https://doi.org/10.1029/94GL00694
  13. Hagan, M.T. and Menhaj, M. (1994), "Training feedforward networks with the Marquardt algorithm", IEEE Trans. Neural Netw., 5, 989-993. https://doi.org/10.1109/72.329697
  14. Hagan, M.T. and Menhaj, M.B. (1994), "Training feedforward networks with the Marquardt algorithm,", Neural Networks, IEEE Tran., 5(6), 989-993. https://doi.org/10.1109/72.329697
  15. Haykin, S. (1999), Neural Networks: A Comprehensive Foundation, 2nd Edition, Prentice Hall, Upper Saddle River, NJ.
  16. Kosmatka, S., Kerkhoff, B. and Panarese, W. (2002), Design and control of concrete mixtures, 14th Edition, Portland Cement Association, Skokie Illinois USA.
  17. Kyriazis, P., Anastasiadis, C., Triantis, D. and Vallianatos, F. (2006), "Wavelet analysis on pressure stimulated currents emitted by marble samples", Nat. Hazard. Earth Syst. Sci., 6(6), 889-894. https://doi.org/10.5194/nhess-6-889-2006
  18. Kyriazis, P., Anastasiadis, C., Stavrakas, I., Triantis, D. and Stonham, J. (2009), "Modelling of electric signals stimulated by bending of rock beams", Int. J. Microstruct. Mater. Prop., 4(1), 5-18. https://doi.org/10.1504/IJMMP.2009.028429
  19. Kyriazopoulos, A., Anastasiadis, C., Triantis, D. and Brown, C.J. (2011a), "Non-destructive evaluation of cement-based materials from pressure-stimulated electrical emission-Preliminary results", Constr. Build. Mater., 25, 1980-1990. https://doi.org/10.1016/j.conbuildmat.2010.11.053
  20. Kyriazopoulos, A., Stavrakas, I., Anastasiadis, C. and Triantis, D. (2011b), "Study of weak electric current emission on cement mortar under uniaxial compressional mechanical stress up to the vicinity of fracture", J. Mech. Eng., 57, 237-244.
  21. Nie, J. (1997), "Fuzzy control of multivariable nonlinear servomechanisms with explicit decoupling Scheme", IEEE Tran. Fuzzy Syst., 5(2), 304-311. https://doi.org/10.1109/91.580803
  22. O'Keefee, S.G. and Thiel, D.V. (1995), "A mechanism for the production of electromagnetic radiation during fracture of brittle materials", Phys. Earth Planet. Inter., 89(1), 127-135. https://doi.org/10.1016/0031-9201(94)02994-M
  23. Park, J.W., Harley, R.G. and Venayagamoorthy, G.K. (2002), "Comparison of MLP and RBF neural networks using deviation signals for on-line identification of a synchronous generator", Power Engineering Society Winter Meeting, 2002. IEEE, 1, 274-279.
  24. Rao, B., Fung, G. and Rosales, R. (2008), "On the dangers of cross-validation. An experimental evaluation", Proceedings of the SIAM International Conference on Data Mining, Atlanta, GA, USA.
  25. Sarimveis, H., Alexandridis, A., Tsekourasm G. and Bafas, G. (2002), "A fast and efficient algorithm for training radial basis function neural networks based on a fuzzy partition of the input space", Ind. Eng. Chem. Res., 41(4), 751-759. https://doi.org/10.1021/ie010263h
  26. Sarlis, N.V., Skordas, E.S. and Varotsos, P.A. (2010), "Nonextensivity and natural time: The case of seismicity", Phys. Rev. E., 82(2), 021110. https://doi.org/10.1103/PhysRevE.82.021110
  27. Stavrakas, I., Anastasiadis, C., Triantis, D. and Vallianatos, F. (2003). "Piezo stimulated currents in marble samples: precursory and concurrent-with-failure signals", Nat. Hazard. Earth Syst.Sci., 3(3-4), 243-247. https://doi.org/10.5194/nhess-3-243-2003
  28. Stavrakas, I., Triantis, D., Agioutantis, Z., Maurigiannakis, S., Saltas, V., Vallianatos, F. and Clarke, M. (2004), Pressure stimulated currents in rocks and their correlation with mechanical properties.
  29. Stergiopoulos, C., Stavrakas, I., Hloupis, G., Triantis, D. and Vallianatos, F. (2013), "Electrical and acoustic emissions in cement mortar beams subjected to mechanical loading up to fracture", Eng. Fail. Anal., 35, 454-461. https://doi.org/10.1016/j.engfailanal.2013.04.015
  30. Stergiopoulos, C., Stavrakas, I., Triantis, D., Vallianatos, F. and Stonham, J. (2015), "Predicting fracture of mortar beams under three-point bending using non-extensive statistical modelling of electric emissions", Physica A, 419, 603-611. https://doi.org/10.1016/j.physa.2014.10.060
  31. Triantis, D., Stavrakas, I., Anastasiadis, C., Kyriazopoulos, A. and Vallianatos, F. (2006), "An analysis of pressure stimulated currents (PSC), in marble samples under mechanical stress", Phys. Chem. Earth, Parts A/B/C, 31(4), 234-239. https://doi.org/10.1016/j.pce.2006.02.018
  32. Triantis, D., Anastasiadis, C., Vallianatos, F., Kyriazis, P. and Nover, G. (2007), "Electric signal emissions during repeated abrupt uniaxial compressional stress steps in amphibolite from KTB drilling", Nat. Hazard. Earth Syst. Sci., 7, 149-154. https://doi.org/10.5194/nhess-7-149-2007
  33. Triantis, D., Stavrakas, I., Kyriazopoulos, A., Hloupis, G. and Agioutantis, Z. (2012), "Pressure stimulated electrical emissions from cement mortar used as failure predictors", Int. J. Fract., 175(1), 53-61. https://doi.org/10.1007/s10704-012-9701-7
  34. Tsai, H.C. (2010), "Predicting strengths of concrete-type specimens using hybrid multilayer perceptrons with center-unified particle swarm optimization", Expert Syst. Appl., 37(2), 1104-1112. https://doi.org/10.1016/j.eswa.2009.06.093
  35. Tsallis, C. (1999), "Nonextensive statistics: theoretical, experimental and computational evidences and connections", Braz. J. Phys., 29(1), 1-35. https://doi.org/10.1590/S0103-97331999000400001
  36. Tsallis, C. (2009), Introduction To Nonextensive Statistical Mechanics: Approaching A Complex World, Springer, Berlin.
  37. Vallianatos, F., Triantis, D., Tzanis, A., Anastasiadis, C. and Stavrakas, I. (2004), "Electric earthquake precursors: from laboratory results to field observations", Phys. Chem. Earth, Parts A/B/C, 29(4), 339-351. https://doi.org/10.1016/j.pce.2003.12.003
  38. Vallianatos, F., Triantis, D. and Sammonds, P. (2011), "Non-extensivity of the isothermal depolarization relaxation currents in uniaxial compressed rocks", Europhys. Lett., 94(6), 68008. https://doi.org/10.1209/0295-5075/94/68008
  39. Vallianatos, F. (2013), "On the statistical physics of rockfalls: A non-extensive view", Europhys. Lett., 101(1), 10007. https://doi.org/10.1209/0295-5075/101/10007
  40. Vallianatos, F. and Triantis, D. (2013), "A non-extensive view of the pressure stimulated current relaxation during repeated abrupt uniaxial load-unload in rock samples", Europhys. Lett., 104(6), 68002. https://doi.org/10.1209/0295-5075/104/68002
  41. Varotsos, P., Alexopoulos, K. and Nomicos, K. (1982), "Comments on the pressure variation of the Gibbs energy for bound and unbound defects", Physica Status Solidi B, 111(2), 581-590. https://doi.org/10.1002/pssb.2221110221
  42. Varotsos, P. and Alexopoulos, K. (1984), "Physical properties of the variations of the electric field of the earth preceding earthquakes, II. Determination of epicenter and magnitude", Tectonophysics, 110(1), 99-125. (see page 122) https://doi.org/10.1016/0040-1951(84)90060-X
  43. Varotsos, P. and Alexopoulos, K. (1986), Thermodynamics of point defects and their relation with the bulk properties, Eds. S. Amelinckx, R. Gevers, and J. Nihoul, North Holland.
  44. Varotsos, P., Sarlis, N., Lazaridou, M. and Kapiris, P. (1998), "Transmission of stress induced electric signals in dielectric media", J. Appl. Phys., 83(1), 60-70. https://doi.org/10.1063/1.366702
  45. 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

Cited by

  1. Investigation on the Sensitivity of Ultrasonic Test Applied to Reinforced Concrete Beams Using Neural Network vol.8, pp.3, 2018, https://doi.org/10.3390/app8030405
  2. Artificial neural network model using ultrasonic test results to predict compressive stress in concrete vol.19, pp.1, 2017, https://doi.org/10.12989/cac.2017.19.1.059
  3. Computation of High-Performance Concrete Compressive Strength Using Standalone and Ensembled Machine Learning Techniques vol.14, pp.22, 2015, https://doi.org/10.3390/ma14227034