Experimental Investigation on Mechanical Properties of Concrete containing Nano Wollastonite and Modeling with GMDH-type Neural Networks

Document Type : Research Article


1 Assistant professor, Civil Engineering Dept., University of Sistan and Baluchestan, Zahedan, Iran

2 Ph.D. Student, Civil Engineering Dept., University of Sistan and Baluchestan, Zahedan, Iran

3 M.Sc. Student, Civil Eng. Dept., Birjand Branch, Islamic Azad University, Birjand, Iran


Wollastonite is a natural and low cost material, which can be replaced by cement in concrete. In the present paper, the influence of Nano Wollastonite on mechanical and durability of concrete was investigated using the measurement of compressive and flexural strength and water penetration on concrete specimens after 3, 7, 28 and 60 days. The results show that flexural strength increase of 63%, compressive strength of 9% and water penetration resistance with around 50% by substitute of 10% Nano Wollastonite. GMDH-type neural networks were used for modeling of these concrete properties. The aim of such modeling is to make a model for predicting of compressive and flexural strength of concrete with the different percentage of Nano Wollastonite. The age and percent of Nano Wollastonite were used as an input variables. The results show that the outputs of neural network model have a good agreement with experimental data.


[1] ASTM C78, “Standard Test Method for Flexural Strength of Concrete (Using Simple Beam with Third-Point Loading) ”, American Society for Testing and Materials, 2002.
[2] A.A. Basma, S. Barakat, S.A1-Orimi, “Prediction of Cement Degree of Hydration
Using Artificial Neural Networks”, ACI Material Journal, Vol. 96, No. 2, pp. 42- 48, 1999.
[3] Y. Benachour, C. A. Davy, F. Skoczylas, H. Houari, “Effect of high calcite filler addition upon micro structural, mechanical, Shrinkage and transport properties of a mortar ”, Cement and Concrete Research, Vol. 38, pp. 727- 736, 2008.
[4] M. H. Fazel Zarandi, I. B. Turksen, J. Sobhani, A.A. Ramezanianpour, “Fuzzy polynomial neural networks for approximation of the compressive strength of concrete”, Applied Soft Computing Vol. 8, pp. 488- 498, 2008.
[5] Jian Ping Jiang, “Prediction of Concrete Strength Based on BP Neural Network”, Advanced Materials Research, Vol. 341– 342, pp. 58- 62, 2011.
[6] A. G. Ivakhnenko, “Polynomial Theory of Complex System”, IEEE Trans. Syst. Man & Cybern, S.M.C. 1, pp. 364- 378, 1971.
[7] A.G. Ivakhnenko, “The group method of data handling- a rival of the method of stochastic approximation”, Soviet Automatic Control, Vol.13, No. 3, pp. 43- 55, 1966.
[8] YH. Lin, YY. Tyan, TP. Chang, CY. Chang, “An assessment of optimal mixture for concrete made with recycled concrete aggregates”, Cement and Concrete Research, Vol. 34, No. 8, pp. 1373– 1380, 2004.
[9] M. M. Alshihri, M. A. Azmy, M. S. El-Bisy, “ Neural networks for predicting compressive strength of structural lightweight concrete”, Construction and Building Materials, Vol. 23, pp. 2214– 2219, 2009.
[10] M. Barbuta1, R.M. Diaconescu, M. Harja, “Using Neural Networks for Prediction of Properties of Polymer Concrete with Fly Ash”, Materials in Civil Engineering, Vol. 24, No. 5, pp. 523– 528, 2012.
[11] M. Dumont, Canadian Minerals Yearbook, 2005.
[12] N. Nariman-Zadeh, A. Darvizeh, R. Ahmad-Zadeh, “Hybrid Genetic Design of GMDH-Type Neural Networks Using Singular Value Decomposition for Modeling and Prediction of the Explosive Cutting Process”, Engineering Manufacture, Vol. 217, pp. 779– 790, 2003.
[13] N. Nariman-zadeh, A. Darvizeh, M. Darvizeh, H. Gharababaei, “Modelling of explosive cutting process of plates using GMDH-type neural network and singular value decomposition”, Materials Processing Technology, Vol. 128, No. 1- 3, pp. 80- 87, 2002.
[14] N. Nariman-zadeh, N. Darvizeh, A. Jamali, A. Moeini, “Evolutionary Design of Generalized polynomial Neural Networks for Modeling and Prediction of Explosive forming Process”, Journal of Materials Processing Technology, Vol. 164- 165, pp. 1561- 1571, 2005.
[15] BS 1881, “Method for determination of compressive strength of concrete cubes”, British Standard, Part 116, 1983.
[16] A. A. Ramezanianpour, A. Tarighat , “Neural Network Modeling of Concrete Carbonation”, 7th CANMENT/ACI International conference on fly ash, silica fume, slag and natural pozzolans in concrete, Chennai(Madras), India, July, 2001.
[17] G. D. Ransinchung, Brind Kumar, Veerendra Kumar, “Assessment of Water absorption and Chloride Ion Penetration of Pavement Quality Admixed with Wollastonite and Microsilica”,
Construction and Building, Vol. 23, pp. 1168- 1177, 2009.
[18] G. D. Ransinchung, Brind Kumar, “ Investigations on Pastes and Mortars of Ordinary Portland Cement Admixed with Wollastonite and Microsilica”, Materials in Civil Engineering, Vol. 22, No. 4, pp. 305- 313, 2010.
[19] Renu Mathur, T. Misra, A. K. Pankaj Goel., “Influence of Wollastonite on Mechanical Properties of Concrete”, Scientific and Industrial Research, Vol. 66, pp. 1029- 1034, 2007.
[20] T. Sato, J. J. Beaudoin, “An Ac Impedance Spectroscopy Study of freezing Phenomena in Wollastonite Micro-Fibre Reinforced Cement Paste”, Department of Civil Engineering, NRCC- 46636, pp. 379- 388, 2003.
[21] S. Malasri, E. Thorsteinsdottir, J. Malasri, “ Concrete Strength Prediction Using a Neural
Network”, MAESC 2006 Conference, USA, 2006.
[22] GH. Tattersall, PH. Baker, “An instigation of the effect of vibration on the workability of fresh concrete using a vertical pipe apparatus”, Concrete Research, Vol. 14, pp. 3– 9, 1989.
[23] I. C. Yeh, “Modeling Concrete Strength with Argument– Neuron Network”, Materials in Civil Engineering, Vol. 10, No. 4, pp. 263– 268, 1998.