{"title":"Modeling and Analysis of Concrete Slump Using Hybrid Artificial Neural Networks","authors":"Vinay Chandwani, Vinay Agrawal, Ravindra Nagar","volume":93,"journal":"International Journal of Civil and Environmental Engineering","pagesStart":987,"pagesEnd":995,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/9999439","abstract":"<p>Artificial Neural Networks (ANN) trained using backpropagation<br \/>\r\n(BP) algorithm are commonly used for modeling<br \/>\r\nmaterial behavior associated with non-linear, complex or unknown<br \/>\r\ninteractions among the material constituents. Despite multidisciplinary<br \/>\r\napplications of back-propagation neural networks<br \/>\r\n(BPNN), the BP algorithm possesses the inherent drawback of<br \/>\r\ngetting trapped in local minima and slowly converging to a global<br \/>\r\noptimum. The paper present a hybrid artificial neural networks and<br \/>\r\ngenetic algorithm approach for modeling slump of ready mix<br \/>\r\nconcrete based on its design mix constituents. Genetic algorithms<br \/>\r\n(GA) global search is employed for evolving the initial weights and<br \/>\r\nbiases for training of neural networks, which are further fine tuned<br \/>\r\nusing the BP algorithm. The study showed that, hybrid ANN-GA<br \/>\r\nmodel provided consistent predictions in comparison to commonly<br \/>\r\nused BPNN model. In comparison to BPNN model, the hybrid ANNGA<br \/>\r\nmodel was able to reach the desired performance goal quickly.<br \/>\r\nApart from the modeling slump of ready mix concrete, the synaptic<br \/>\r\nweights of neural networks were harnessed for analyzing the relative<br \/>\r\nimportance of concrete design mix constituents on the slump value.<br \/>\r\nThe sand and water constituents of the concrete design mix were<br \/>\r\nfound to exhibit maximum importance on the concrete slump value.<\/p>\r\n","references":"[1] P.K. Mehta and P.J.M. Monteiro, Concrete: Structure, Properties and\r\nMaterials. 3rd ed. New York: McGraw Hill, 2006.\r\n[2] Z. Li, Advanced Concrete Technology. 1st ed. New Jersey: John Wiley &\r\nSons, Inc, 2011.\r\n[3] W.P.S. Dias and S.P. Pooliyadda, \"Neural Networks for predicting\r\nproperties of concrete with admixtures,\u201d Construction and Building\r\nMaterials, vol. 15, no. 7, pp. 371-379, 2001.\r\n[4] I.-C. Yeh, \"Exploring concrete slump model using artificial neural\r\nnetworks,\u201d Journal of Computing in Civil Engineering, vol. 20, no. 3,\r\npp. 217-221, 2006.\r\n[5] A. Oztas, M. Pala, E. Ozbay, E. Kanca, N. Caglar and M.A. Bhatti,\r\n\"Predicting the compressive strength and slump of high strength\r\nconcrete using neural network,\u201d Construction and Building Materials,\r\nvol. 20, no. 9, pp. 769-775, 2006.\r\n[6] I.-C.Yeh, \"Modeling slump flow of concrete using second-order\r\nregressions and artificial neural networks,\u201d Cement and Concrete\r\nComposites, vol. 29, pp. 474-480, 2007.\r\n[7] A. Jain, S.K. Jha and S. Misra, \"Modeling and analysis of concrete\r\nslump using artificial neural networks,\u201d Journal of Materials in Civil\r\nEngineering, vol. 20, no. 9, pp. 628-633, 2008.\r\n[8] M. Saridemir, \"Prediction of compressive strength of concretes\r\ncontaining metakaolin and silica fumes by artificial neural networks,\u201d\r\nAdvances in Engineering Software, vol. 40, no. 5, pp. 350-355, 2009.\r\n[9] S.J. Kwon and H.W. Song, \"Analysis of carbonation behaviour in\r\nconcrete using neural network algorithm and carbonation modeling,\u201d\r\nCement and Concrete Research, vol. 40, no. 1, pp. 119-127, 2010.\r\n[10] R. Siddique, P. Aggarwal and Y. Aggarwal, \"Prediction of compressive\r\nstrength of self compacting concrete containing bottom ash using\r\nartificial neural networks,\u201d Advances in Engineering Software, vol. 42,\r\nno. 10, pp. 780-786, 2011.\r\n[11] M.I. Khan, \"Predicting properties of high performance concrete\r\ncontaining composite cementitious materials using Artificial Neural\r\nNetworks,\u201d Automation in Construction, vol.22, pp. 516-524, 2012.\r\n[12] O.A. Hodhod and H.I. Ahmed, \"Developing an artificial neural network\r\nmodel to evaluate chloride diffusivity in high performance concrete,\u201d\r\nHBRC Journal, vol.9, no. 1, pp. 15-21, 2013.\r\n[13] A.M. Diab, H.E. Elyamany, A.E.M.A. Elmoaty and A.H. Shalan,\r\n\"Prediction of concrete compressive strength due to long term sulphate\r\nattack using neural networks,\u201d Alexandria Engineering Journal, vol.53,\r\npp. 627-642, 2014.\r\n[14] C.L. Su, S.M. Yang and W.L. Huang, \"A two stage algorithm\r\nintegrating genetic algorithms and modified Newton method for neural\r\nnetwork training in engineering systems,\u201d Expert Systems with\r\nApplications, vol. 38, no. 10, pp. 12189-12194, 2011.\r\n[15] A. Johari, A.A. Javadi and G. Habibagahi, \"Modelling the mechanical\r\nbahaviour of unsaturated soils using a genetic algorithm based neural\r\nnetwork,\u201d Computers and Geotechnics, vol. 38, no. 1, pp. 2-13, 2011.\r\n[16] H. Karimi and F. Yousefi, \" Application of artificial neural networkgenetic\r\nalgorithm (ANN-GA) to correlation of density in nanofluids,\u201d\r\nFluid Phase Equilibria, vol. 336, pp. 79-83, 2012.\r\n[17] R. Wang,C. Zhou, Z. Deng, B. Ni and Z. Zhao, \"Predicting foF2 in China\r\nregion using the artificial neural networks improved by the genetic\r\nalgorithms,\u201d Journal of Atmospheric and Solar-Terrestrial Physics, vol.\r\n92, pp. 7-17, 2013.\r\n[18] Y. Xue, L. Cheng, J. Mou and W. Zhao, \"A new fracture prediction\r\nmethod by combining genetic algorithm with neural network in lowpermeability\r\nreservoirs,\u201d Journal of Petroleum Science and Engineering,\r\nvol. 121, pp. 159-166, 2014.\r\n[19] M.M. Alshihri, A.M. Azmy and M.S. El-Bisy, \"Neural Networks for\r\npredicting compressive strength of structural light weight concrete,\u201d\r\nConstruction and Building Materials, vol. 23, no. 6, pp. 2214-2219,\r\n2009.\r\n[20] K. Hornik, M. Stinchcombe and H. White, \"Multilayer feed forward\r\nnetworks are universal approximators,\u201d Neural Networks, vol. 2, no. 5,\r\npp. 359-366, 1989.\r\n[21] S. Tamura and M. Tateishi, \"Capabilities of four layered feedforward\r\nneural network: four layer versus three,\u201d IEEE Trasactions on Neural\r\nNetworks, vol. 8, no. 2, pp. 251-255, 1997.\r\n[22] P.C. Pendharkar and J.A.Rodger, \"Technical efficiency based selection\r\nof learning cases to improve the forecasting efficiency of neural\r\nnetworks under monotonicity assumption,\u201d, Decision Support Systems,\r\nvol. 36, no. 1, pp. 117-136, 2003.\r\n[23] K. Jinchuan and L. Xinzhe, \"Empirical analysis of optimal hidden layer\r\nneurons in neural network modeling for stock prediction,\u201d in\r\nProceedings of Pacific-Asia Workshop on Computational Intelligence\r\nand Industrial Applications, vol. 2, pp. 828-832, Dec. 2008.\r\n[24] D. Hunter, Y. Hao, M.S. Pukish, J. Kolbusz and B.M Wilamowski,\r\n\"Selection of proper Neural Network sizes and architectures-A\r\ncomparative study,\u201d IEEE Transaction on Industrial Informatics, vol. 8,\r\nno. 2, pp. 228-240, 2012.\r\n[25] S. Rajasekaran and G.A.V. Pai, \"Neural Networks, Fuzzy Logic and\r\nGenetic Algorithms: Synthesis & Applications,\u201d New Delhi: Prentice-\r\nHall of India Private Limited, 2003..\r\n[26] B.M. Wilamowski, Y. Chen, A. Malinowski, \"Efficient Algorithm for\r\nTraining Neural Networks with One Hidden Layer,\u201d in Proceedings of\r\nInternational Joint Conference on Neural Networks IEEE, pp. 1725-\r\n1728, 1999.\r\n[27] K. Wang, Computational Intelligence in Agile Manufacturing\r\nEngineering, in: Gunasekaran A, editor. Agile Manufacturing The 21st\r\nCentury Competitive Strategy, Oxford, UK: Elsevier Science Ltd, 2001,\r\npp. 297-315.\r\n[28] J.E. Nash and J.V. Sutcliffe, \"River flow forecasting through conceptual\r\nmodels Part I \u2013 a discussion of principles,\u201d Journal of Hydrology, vol.\r\n10, no. 3, pp. 282\u2013290, 1970.\r\n[29] S. Srinivasulu and A. Jain, \"A comparative analysis of training methods\r\nfor artificial neural network rainfall-runoff models,\u201d Applied Soft\r\nComputing, vol. 6, pp. 295-306, 2006.\r\n[30] J.D. Olden and D.A. Jackson, \"Illuminating the \"Black Box\u201d: a\r\nrandomization approach for understanding variable contributions in\r\nartificial neural networks.\u201d Ecological Modeling ,vol. 154, pp. 135-150,\r\n2002.\r\n[31] G. Acciani, E. Chiarantoni and G. Fornarelli, A neural network\r\napproach to study O3 and PM10 concentration, in: Kollias S, Staflopatis\r\nA, Duch W, Oja E, editors. ICANN'06 Proceedings of the 16th\r\ninternational conference on Artificial Neural Networks - Volume Part II,\r\nBerlin, Germany: Springer Verlag, 2006, pp. 913-922.\r\n[32] G.D. Garson, \"Interpreting neural network connection\r\nweights,\u201dArtificial Intelligence Expert , vol. 6, pp. 47-51, 1991.\r\n[33] M. Gevrey, I. Dimopoulos and S. Lek, \"Review and comparison of\r\nmethods to study the contribution of variables in artificial neural\r\nnetwork models,\u201d Ecological Modeling , vol. 160, pp. 249-264, 2003.\r\n[34] J.J. Montano and A. Palmer, \"Numeric sensitivity analysis applied to\r\nfeedforward neural networks,\u201d Neural Computing and Applications, vol.\r\n12, pp. 119-125, 2003.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 93, 2014"}