IJE TRANSACTIONS A: Basics Vol. 23, No. 2 (April 2010) 145-152   

downloaded Downloaded: 302   viewed Viewed: 2479


Amir Kamalloo, Yadolah Ganjkhanlou, Seyed Hamed Aboutalebi and Hossein Nouranian*
Materials and Energy Research Center, P.O. Box 14155-4777, Tehran, Iran
amirkamalloo@yahoo.com, yadolah1@gmail.com, hamed.Aboutalebi@gmail.com, h_nouranian@yahoo.com

*Corresponding Author

( Received: December 19, 2009 – Accepted: July 15, 2010 )

Abstract    In order to study the effect of R2O/Al2O3 (where R=Na or K), SiO2/Al2O3, Na2O/K2O and H2O/R2O molar ratios on the compressive strength (CS) of Metakaolin base geopolymers, more than forty data were gathered from literature. To increase the number of data, some experiments were also designed. The resulted data were utilized to train and test the three layer artificial neural network (ANN). Bayesian regularization method and Early Stopping methods with back propagation algorithm were applied as training algorithm. Good validation for CS was resulted due to the inhibition of overfitting problems with the applied training algorithm. The results showed that optimized condition of SiO2/Al2O3, R2O/Al2O3, Na2O/K2O and H2O/R2O ratios to achieve high CS should be 3.6-3.8, 1.0-1.2, 0.6-1 and 10-11, respectively. These results are in agreement with probable mechanism of geopolymerization.


Keywords    Neural Network, Overfitting, Geopolymer, Compressive Strength, Metakaolin


چکیده    با هدف مطالعه اثر نسبتهاي مولي R2O/Al2O3(کهR=Na يا K) ، SiO2/Al2O3، Na2O/K2O و H2O/R2Oبر روي استحکام فشاري ژئوپليمرهاي پايه متاکائولن بيش از 40 داده جمع آوري شد. همچنين براي افزايش داده­ها تعدادي آزمايشات جديد طراحي گرديد. داده­هاي بدست آمده براي آموزش و آزمايش يک شبکه 3 لايه­اي استفاده شد. روش انتظام بيزي و توقف زودتر با تکنيک پس انتشار به عنوان روش آموزش استفاده گرديد. توافق خوبي بين استحکام فشاري پيش بيني شده و تجربي بخاطر پيش­گيري از بيش برازش توسط روش آموزش بکار برده شده حاصل شد. نتايج نشان داد که شرايط بهينه نسبتهاي مولي SiO2/Al2O3، R2O/Al2O3، Na2O/K2O وH2O/R2O براي دستيابي به استحکام فشاري بهينه برابر با 8/3-6/3، 2/1-0/1، 1-6/0 و 11-10 به ترتيب مي­باشند. اين نتايج با سازوکار محتمل ژئوپليمريزاسيون همخواني دارد.


1. Davidovits, J., "Geopolymers: inorganic polymeric new materials". Journal of Thermal Analysis, Vol. 37 (1991), 1633-1656.

2. Davidovits, J., "Properties of geopolymer cements". First International Conference on Alkaline Cements concretes, Kiev, Ukrain, ; 1994.

3. Komnitsas, K., Zaharaki, D., "Geopolymerisation: A review and prospects for the minerals industry ". Minerals Engineering, Vol. 20, (2007), 1261-1277.

4. Duxson, P., Fernandez-Jimenez, A., Provis, J. L., Luckey, G. C., Palomo, A., Deventer, J. S. J. V., "Geopolymer technology: the current state of the art". Journal of Materials Science, Vol. 42, (2007), 2917-2933.

5. Barbosa, V. F. F., MacKenzie, K. J. D., Thaumaturgo, C., "Synthesis and characterization of materials based on inorganic polymers of alumina and silica: sodium polysialate polymers". International Journal of Inorganic Materials, Vol. 2, (2000), 309-317.

6. Duxson, P., Provis, J., Lukey, G. C., Mallicoat, S. W., Kriven, W. M., Deventer, J. S. J. V., "Understanding the relationship between geopolymer composition, microstructure and mechanical properties". Colloids and Surfaces A: Eng Aspects, Vol. 269, (2005), 47-58.

7. Rowels, M., O’Connor, B., "Chemical optimization of the compressive strength of aluminosilicate geopolymers synthesized by sodium silicate activation of metakaolinite". journal of Materials Chemistry, Vol. 13, (2003), 1161-1165.

8. Silva, P. D., Sagoe-Crenstil, K., Sirivivatnanon, V., "Kinetics of geopolymerization: Role of Al2O3 and SiO2". Cement and Concrete Research, Vol. 37, (2007), 512-518.

9. Bai, J., Wild, S., Ware, J. A., Sabir, B. B., "Using neural networks to predict workability of concrete incorporating metakaolin and fly ash". Advances in Engineering Software, Vol. 34, (2003), 663-669.

10. Lai, S., Serra, M., "Concrete strength prediction by means of neural network". Construction and Building Materials, Vol. 11, (1997), 93-98.

11. Mandal, A., Roy, P., "Modeling the compressive strength of molasses-cement sand system using design of experiments and back propagation neural network". Journal of Materials Processing Technology, Vol. 180, (2006), 167-173.

12. Sebastia, M., Fernandez Olmo, I., Irabien, A., "Neural network prediction of unconfined compressive strength of coal fly ash-cement mixtures". Cement and Concrete Research, Vol. 33, (2003), 1137-1146.

13. Stegemann, J. A., Buenfeld, N. R., "Prediction of unconfined compressive strength of cement paste with pure metal compound additions". Cement and Concrete Research, Vol. 32, (2002), 903-913.

14. Topcu, I. B., Saridemir, M., "Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic". Computational Materials Science, Vol. 41, (2008), 305-311.

15. MATLAB Release 12, The Math Work Inc., Natick, MA, USA.

16. Yeh, I. C., "Modeling of strength of high-performance concrete using artificial neural networks". Cement and Concrete Research, Vol. 28, (1998), 1797-1808.

17. Topalov, A. V., Kaynak, O., "Neural network modeling and control of cement mills using a variable structure systems theory based on-line learning mechanism". Journal of Process Control, Vol. 14, (2004), 581-589.

18. Arabani, M., "Evalution of rough set theory for decision making of rehabilitation method for concrete pavement". International Journal of Engineering Vol. 18 (2005), 1-10.

19. Goel, A., "ANN based modeling for prediction of evaporation in reservoirs". International Journal of Engineering, Vol. 22, (2009), 351-358.

20. Saghatoleslam, N., Karimi, H., Rahimi, R., Shirazi, H. H. A., "Modeling of texture and color froth characterization for evalution of flotation performance in Sarcheshmeh copper pilot plant using image analysis and Neural Network". International Journal of Engineering Vol. 17, (2004), 121-130.

21. Bayar, S., Demir, I., Engin, G. O., "Modeling leaching behavior of solidified wastes using back-propagation neural networks". Ecotoxicology and Environmental Safety, Vol. In Press, Corrected Proof), 311.

22. "Hagan, M. T., Demuth, H. B., Beale, M. H., “Neural network design”, PWS Publishing, Boston, (1996)." Vol.).

23. Heiermann, K., Riesch-Oppermann, H., Huber, N., " Reliability confidence intervals for ceramic components as obtained from bootstrap methods and neural networks". Computational Materials Science, Vol. 34, (2005), 1-13.

24. Scott, D. J., Coveney, P. V., Kilner, J. A., Rossiny, J. C. H., Alfor, N. M. N., "Prediction of the functional properties of ceramic materials from composition using artificial neural networks". Journal of the European Ceramic Society, Vol. 27, (2007), 4425- 4435.

25. Koker, R., Altinkok, N., Demir, A., "Neural network based prediction of mechanical properties of particulate reinforced metal matrix composites using various training algorithms". Materials and Design, Vol. 26, (2005), 305-311.

26. Yang, Y. Y., Linkens, D. A., Talamantes, S. J., " Roll load prediction—data collection, analysis and neural network modeling". Journal of Materials Processing Technology, Vol. 152, (2004), 304-315.

27. MacKay, D. J. C., “Bayesian methods for adaptive models, California Institute of Technology”, PhD. dissertation, Pasadena, California, (1992).

28. Subaer, Riessen, A. V., "Thermo-mechanical and microstructural characterisation of sodium-poly(sialate-siloxo) (Na-PSS) geopolymers". J Mater Sci, Vol. 42, (2007), 3117-3123.

29. Duxson, P., Mallicoat, S. W., Lukey, G. C., Kriven, W. M., Deventer, J. S. J. v., "The effect of alkali and Si/Al ratio on the development of mechanical properties of metakaolin-based geopolymers". Colloids and Surfaces A: Physicochem Eng Aspects Vol. 292, (2007), 8-20.

30. Wang, H., Li, H., Yan, F., "Synthesis and mechanical properties of metakaolinite-based Geopolymer". Colloids and Surfaces A: Eng Aspects, Vol. 268, (2005), 1-3.

International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir