Farklı Puzolanlarla Üretilmiş Çimentoların Dayanım Gelişiminin Yapay Sinir Ağlarıyla Tahmini
Bu çalışma, çimento üretiminde kullanılan mineral katkılarda en uygun kullanım oranının belirlenmesi için yapılmıştır. Laboratuvarda farklı kaynaklardan sağlanan doğal zeolit, tras, volkanik tüf, uçucu kül ve yüksek fırın cürufu katkıları, çimento üretiminde klinker yerine %10, 20, 30, 35, 40 ve 45 oranlarında kullanılmıştır. Çimentolar üzerinde yapılan 2, 7, 28 ve 180 günlük basınç dayanımı deneyleriyle dayanım gelişimi belirlenmiştir. Daha sonra deneysel çalışmadan elde edilen veriler kullanılarak yapay sinir ağı (YSA) yönteminde model geliştirilmiştir.
Predicting The Strength Development Of Different Pozzolan Cements By Artificial Neural Networks
This study is based on the determination of optimum usage of mineral additives as
supplementary cementing material for blended cement production. For this purpose, blended
cements were produced under laboratory conditions with natural zeolite, trass, volcanic tuff, fly
ash and ground granulated blast furnace slag at 10, 20, 30, 40 and 45% clinker replacement
ratios. Strength development of the cements was determined with compressive strength tests
performed at 2, 7, 28 and 180 days. Experimental results were also obtained by building models
according to artificial neural network (ANN) system.
___
- [1] C. Shi, “An overview on the activation of reactivity of natural pozzolans,” Canadian
Journal of Civil Engineering, Vol. 28, pp. 778-786, 2001.
- [2] M. Khandaker, A. Hossain, “Blended cement using volcanic ash and pumice,” Cement and
Concrete Research, Vol. 33, pp. 1601-1605, 2003.
- [3] F. Massazza, “Pozzolans and Durability of Concrete”, 1st International Symposium on
Mineral Admixtures in Cement, 1997, İstanbul, pp. 1-22.
- [4] C. Gervais, S.K. Ouki, “Performance study of cementitious systems containing zeolite and
silica fume: effects of four metal nitrates on the setting time,” Strength and Leaching
Characteristics, Journal of Hazardous Materials, Vol. B93, pp. 187-200, 2002.
- [5] M. Canbaz, “Alkalilerle aktive edilmiş yüksek fırın cüruflu harçların özelikleri”, Eskişehir
Osmangazi Üniversitesi, Fen Bilimleri Enstitüsü, Doktora Tezi, 206 s., 2007.
- [6] B.B. Adhikary, H. Mutsuyoshi, “Prediction of shear strength of steel fiber RC beams using
neural networks,” Construction and Building Materials, Vol. 20, pp. 801-811, 2006.
- [7] A. Öztaş, M. Pala, E. Özbay, E. Kanca, N. Çağlar, M. Asghar Bhatti, “Predicting the
compressive strength and slump of high strength concrete using neural network,”
Construction and Building Materials, Vol. 20, pp. 769-775, 2005.
- [8] İ.B. Topçu, M. Sarıdemir, “Prediction of rubberized concrete properties using artificial
neural networks and fuzzy logic,” Construction and Building Materials, Vol. 22, pp. 532-
540, 2008.
- [9] A.M. Kewalramani, R. Gupta, “Concrete compressive strength prediction using ultrasonic
pulse velocity through artificial neural networks,” Automation in Construction, Vol. 15, pp.
374-379, 2006.
- [10] J.A. Anderson, “Cognitive and psychological computation with neural models,” IEEE
Transactions on Systems, Man and Cybernetics, Vol. 5, pp. 799-814, 1983.
- [11] S.W. Liu, J.H. Huang, J.C. Sung, C.C. Lee, “Detection of cracks using neural networks and
computational mechanics,” Computer Methods in Applied Mechanics Engineering, Vol.
191, pp. 2831-2845, 2002.
- [12] İ.B. Topçu, M. Sarıdemir, “Prediction of properties of waste AAC aggregate concrete using
ANN,” Computational Materials Science, Vol. 41, pp. 117-125, 2007.
- [13] A. Turatsinze S. Bonnet, J.L. Granju, “Potential of rubber aggregates to modify properties
of cement based-mortars: improvement in cracking shrinkage resistance,” Construction and
Building Materials, Vol. 21, pp. 176-181, 2007.
- [14] İ.B. Topçu, C. Karakurt, M. Sarıdemir, “Predicting the strength development of cements
with different pozzolans by neural network and fuzzy logic,” Journal of Materials Design,
Vol. 29, pp. 1986-1991, 2008.