Computers and Concrete

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Predicting concrete properties using neural networks (NN) with principal component analysis (PCA) technique

  • Boukhatem, B. (Geometrical Laboratory, Civil Engineering Department, University of Blida) ;
  • Kenai, S. (Geometrical Laboratory, Civil Engineering Department, University of Blida) ;
  • Hamou, A.T. (Civil Engineering Department, University of Sherbrooke) ;
  • Ziou, Dj. (Department of Informatics, University of Sherbrooke) ;
  • Ghrici, M. (Civil Engineering Departments, University of Chlef)
  • Received : 2011.03.23
  • Accepted : 2012.02.29
  • Published : 2012.12.25
⟨ Previous Next ⟩

Abstract

This paper discusses the combined application of two different techniques, Neural Networks (NN) and Principal Component Analysis (PCA), for improved prediction of concrete properties. The combination of these approaches allowed the development of six neural networks models for predicting slump and compressive strength of concrete with mineral additives such as blast furnace slag, fly ash and silica fume. The Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian regularization was used in all these models. They are produced to implement the complex nonlinear relationship between the inputs and the output of the network. They are also established through the incorporation of a huge experimental database on concrete organized in the form Mix-Property. Thus, the data comprising the concrete mixtures are much correlated to each others. The PCA is proposed for the compression and the elimination of the correlation between these data. After applying the PCA, the uncorrelated data were used to train the six models. The predictive results of these models were compared with the actual experimental trials. The results showed that the elimination of the correlation between the input parameters using PCA improved the predictive generalisation performance models with smaller architectures and dimensionality reduction. This study showed also that using the developed models for numerical investigations on the parameters affecting the properties of concrete is promising.

Keywords

References

  1. Bellamine, F.H. and Elkamel, A. (2008), "Model order reduction using neural network principal component analysis and generalized dimensional analysis", Eng. Comp. Int. J. Comp.-Aid Eng. Soft., 25(5), 443-463.
  2. Bentz, D.P. (2008), "A review of early-age properties of cement-based materials", Cement. Concrete Res., 38(2), 196-204. https://doi.org/10.1016/j.cemconres.2007.09.005
  3. Bilim, C., Atis, C.D., Tanyildizi, H. and Karahan, O. (2009), "Predicting the compressive strength of ground granulated blast furnace slag concrete using artificial neural network", Adv. Eng. Softw., 40(5), 334-340. https://doi.org/10.1016/j.advengsoft.2008.05.005
  4. Bishop, C.M. (1994), "Neural networks and their applications", Rev. Sci. Instrum., 65(6), 1803-1832. https://doi.org/10.1063/1.1144830
  5. Bolomey, J. (1995), "Granulation and prediction of probable strength of concrete (in French)", Trav., 19(30), 228-232.
  6. Boukhatem, B. (2011), Design of a computer integrated system for the knowledge of concrete with cement additions (SAICBA), PhD Thesis, University of Blida, Algeria, 150.
  7. Building Research Establishment (BRE) (1988), Design of normal concrete mixes, Department of the Environment, Watford, UK.
  8. Chanvillard, G. and D'Aloia, L. (1994), "Prediction of early age concrete compressive strength: Application of the equivalent time method", Bull. LPC, 193, 39-51.
  9. De Larrard, F., Naproux, P. and Waller, V. (1997), "Contribution of silica fume and silico-aluminates fume to concrete compressive strength: quantification", Bull. LPC, 208, 53-65.
  10. Dreyfus, G., Martinez, J.M., Samuelides, M., Gordon, M.B., Badran, F., Thiria, S. and Herault, L. (2002), Neural networks : methodologie and application, Ed. Eyrolles, 386.
  11. Gupta, R., Kewalramani, M.A. and Goel, A. (2006), Prediction of concrete strength using neural-expert system, J. Mater. Civil Eng., 18(3), 462-466. https://doi.org/10.1061/(ASCE)0899-1561(2006)18:3(462)
  12. Harkat, M.F. (2003), Détection et localisation de défauts par analyse en composantes principales, Doctorate thesis, Lorraine Polytechnique, Nancy, 172.
  13. Jayaram, M.A., Nataraja, M.C. and Ravikumar, C.N. (2009), "Elitist genetic algorithm models: optimization of high performance concrete mixes", Mater. Manuf. Process, 24(2), 225-229. https://doi.org/10.1080/10426910802612387
  14. Joe, D. and Eng, P. (1995), Predicting the compressive strength of high performance silica fume concrete by Bayesian methods, Prepared for Department of Works, Services and Transportation, Government of Newfoundland and Labrador, St. John's, Canada.
  15. Jolliffe, I.T. (2002), Principal component analysis, 2nd ed., New York: Springer-Verlag, 486.
  16. Junita, M.S. and Brian, S.H. (2008), "Improved neural network performance using principal component analysis on Matlab", Comput. Integ. M., 16(2), 1-8.
  17. Kresta, J.V., MacGregor, J.F. and Marlin, T.E. (1991), "Multivariate statistical monitoring of process operating performance", Can. J. Chem. Eng., 69(1), 35-47. https://doi.org/10.1002/cjce.5450690105
  18. Kuniar, K. and Waszczyszyn, Z. (2006), "Neural networks and principal component analysis for identification of building natural periods", J. Comput. Civil Eng., 20(6), 431-436. https://doi.org/10.1061/(ASCE)0887-3801(2006)20:6(431)
  19. Lecomte, A. and De Larrard, F. (2001), Mechling J.M., Concrete compressive strength with unoptimised granular skeleton, Bull. LPC, 234, 89-105.
  20. Lee, J.J., Kim, D., Chang, S.K. and Nocete, C.F.M. (2009), "An improved application technique of the adaptive probabilistic neural network for predicting concrete strength", Comp. Mater. Sci., 44(3), 988-998. https://doi.org/10.1016/j.commatsci.2008.07.012
  21. MacGregor, J.F. and Kourti, T. (1995), "Statistical process control of multivariate process", Control Eng. Pract., 3(3), 403-414. https://doi.org/10.1016/0967-0661(95)00014-L
  22. MacKay, D.J.C. (1992), "Bayesian interpolation", Neural. Comput., 4(3), 415-447. https://doi.org/10.1162/neco.1992.4.3.415
  23. Neural Network for user with MATLAB 7.5 (2007), The math works, Inc, Prentice Hall.
  24. Shin, S.W., Yun, C.B., Futura, H. and Popovics, J.S. (2008), "Non-destructive evaluation of crack depth in concrete using PCA-compressed wave transmission function and neural networks", Exp. Mech., 48(2), 225-231. https://doi.org/10.1007/s11340-007-9083-3
  25. Slonski, M. (2007), "HPC strength prediction using bayesian neural networks", Mech. Eng. Sci., 14(2), 345-52.
  26. Snell, L.M. and Wallace, J.V. (1989), "Predicting early concrete strength", Concrete Int., 11(12), 43-47.
  27. Topc, I.B. and Sardemir, M. (2008), "Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic", Comput. Mater. Sci., 41(3), 305-311. https://doi.org/10.1016/j.commatsci.2007.04.009
  28. Uygunoglu, T. and Unal, O. (2006), "A new approach to determination of compressive strength of fly ash concrete using fuzzy logic", J. Sci. Ind. Res., 65(11), 894-899.
  29. Valle, S., Weihua, L. and Qin, S.J. (1999), "Selection of the number of principal components: The variance of the reconstruction error criterion with a comparison to other methods", Ind. Eng. Chem. Res., 38(11), 4389-4401. https://doi.org/10.1021/ie990110i
  30. Xiaodong, C., Bin, C. and Guohua, L. (2007), "Optimization of concrete mixture based on BP ANN and genetic algorithms", J. Hydraul Eng.-ASCE, 26(5), 9-63.
  31. Yeh, I.C. (2006), "Exploring concrete slump model using artificial neural networks", J. Comput. Civil Eng., 20(3), 217-221. https://doi.org/10.1061/(ASCE)0887-3801(2006)20:3(217)
  32. Zain, M.F.M., Nazrul Islam, Md. and Ir. Hassan Basri. (2005), "An expert system for mix design of high performance concrete", Adv. Eng. Softw., 36(5), 325-337. https://doi.org/10.1016/j.advengsoft.2004.10.008

Cited by

  1. Predicting the strength properties of slurry infiltrated fibrous concrete using artificial neural network 2018, https://doi.org/10.1007/s11709-017-0445-3
  2. An optimized classification algorithm by BP neural network based on PLS and HCA vol.43, pp.1, 2015, https://doi.org/10.1007/s10489-014-0618-x
  3. Simulation of Experimental Parameters of RC Beams by Employing the Polynomial Regression Method vol.52, pp.3, 2016, https://doi.org/10.1007/s11029-016-9590-3
  4. Exploring the major factors affecting fly-ash concrete carbonation using artificial neural network 2017, https://doi.org/10.1007/s00521-017-3052-2
  5. The use of artificial neural networks in predicting ASR of concrete containing nano-silica vol.13, pp.6, 2014, https://doi.org/10.12989/cac.2014.13.6.739
  6. Repetitive model refinement for structural health monitoring using efficient Akaike information criterion vol.15, pp.5, 2015, https://doi.org/10.12989/sss.2015.15.5.1329
  7. Sound absorbing materials made by embedding crumb rubber waste in a concrete matrix vol.124, 2016, https://doi.org/10.1016/j.conbuildmat.2016.07.145
  8. Prediction of axial capacity of piles driven in non-cohesive soils based on neural networks approach vol.23, pp.3, 2017, https://doi.org/10.3846/13923730.2016.1144643
  9. A practical hybrid NNGA system for predicting the compressive strength of concrete containing natural pozzolan using an evolutionary structure vol.149, 2017, https://doi.org/10.1016/j.conbuildmat.2017.05.165
  10. Analog Circuit Soft Fault Diagnosis based on PCA and PSO-SVM vol.8, pp.12, 2013, https://doi.org/10.4304/jnw.8.12.2791-2796
  11. Radial Basis Function Network-Based Approach for Determining Interaction Behavior of Reinforced Concrete Rectangular Columns vol.39, pp.11, 2014, https://doi.org/10.1007/s13369-014-1401-3
  12. Neural networks and principle component analysis approaches to predict pile capacity in sand vol.149, pp.2261-236X, 2018, https://doi.org/10.1051/matecconf/201714902025
  13. Neural networks and principle component analysis approaches to predict pile capacity in sand vol.149, pp.2261-236X, 2018, https://doi.org/10.1051/matecconf/201814902025
  14. Predicting the mechanical properties of ordinary concrete and nano-silica concrete using micromechanical methods vol.43, pp.12, 2018, https://doi.org/10.1007/s12046-018-0965-0
  15. Compressive strength prediction of limestone filler concrete using artificial neural networks vol.3, pp.3, 2018, https://doi.org/10.12989/acd.2018.3.3.289
  16. Application of artificial neural networks for the prediction of the compressive strength of cement-based mortars vol.24, pp.4, 2012, https://doi.org/10.12989/cac.2019.24.4.329
  17. Connecting concrete technology and machine learning: proposal for application of ANNs and CNT/concrete composites in structural health monitoring vol.10, pp.39, 2012, https://doi.org/10.1039/d0ra03450a
  18. Estimating the compressive strength of HPFRC containing metallic fibers using statistical methods and ANNs vol.10, pp.6, 2012, https://doi.org/10.12989/acc.2020.10.6.479
  19. Principal Component Analysis as a Statistical Tool for Concrete Mix Design vol.14, pp.10, 2012, https://doi.org/10.3390/ma14102668
  20. Application of Principal Component Analysis Approach to Predict Shear Strength of Reinforced Concrete Beams with Stirrups vol.14, pp.13, 2021, https://doi.org/10.3390/ma14133471
  21. The utility of proper orthogonal decomposition for dimensionality reduction in understanding behavior of concrete vol.28, pp.2, 2012, https://doi.org/10.12989/cac.2021.28.2.129