Polipropilen Lifli Betonların Yüksek Sıcaklık Sonrası Basınç Dayanımlarının Yapay Sinir Ağları ile Tahmini

Year 2009, Volume: 1 Issue: 2, 23 - 28, 15.06.2009

Hasbi Yaprak , Abdulkadir Karacı

Abstract

Beton yüksek sıcaklık etkisinde kaldığında önemli ölçüde hasara uğrar. Bu durum istenilmeyen yapısal kusurlara neden olabilir. Polipropilen liflerin ilavesi bu hasarın azaltılmasında kullanılan yöntemlerden biridir. Bu çalısmada lif katkısız, 0.9, 1.35 ve 1.8 kg/m3 polipropilen lif katkılı beton numuneler üretilmis, numuneler laboratuar ortamında olgunlastırılmıs, 28. günün sonunda tüm numuneler 20, 400, 600 ve 800 ºC sıcaklık etkisinde bırakılmıstır. Yüksek sıcaklık etkisinde kalan numunelerin basınç dayanımları test edilmistir. Deneysel olarak bulunan test sonuçlarının yapay sinir ağları (YSA) kullanılarak bulunması amaçlanmıstır. YSA yaklasımı ile deneysel olarak elde edilmis veriler karsılastırıldığında değerlerin birbirine en çok % 3.5 en az % 0.0 hata ile yakın olduğu görülmüstür.

Keywords

Yüksek Sıcaklık, Polipropilen Lif, Basınç Dayanımı, Yapay Sinir Ağları

Polipropilen Lifli Betonların Yüksek Sıcaklık Sonrası Basınç Dayanımlarının Yapay Sinir Ağları ile Tahmini

Abstract

Concrete, when under the impact of high temperatures, is considerably damaged. This may result in undesirable structural failures. One of the ways to reduce this damage is to incorporate polypropylene fibers. In this study, first, concrete samples- both without fibers, and with polypropylene fibers in three different amounts - 0.9, 1.35, 1.8 kg/m3- were produced, and then, these samples were matured in laboratory conditions, and all samples were exposed to high temperatures of 20, 400, 600, and 800 ºC respectively at the end of the 28th day. The compressive strengths of the samples exposed to higher temperatures were tested. It was aimed to obtain the same laboratory test results by using Neural Network. When the data from the laboratory testing and from the Neural Network applications were compared, it was found that the values were very identical. When the data obtained empirically through the ANN approach were compared, it was noted that the values were close to each other with a margin of error of 3.5 % (maximum) and 0 % 0.0 (minimum).

Keywords

High Temperature, Polypropylene Fiber, Compressive Strength, Artificial Neural Network

References

• [1] F.Ali, A.Nadjai, G.Silcock, A.Abu-Tair, “Outcomes of a Major Research on Fire Resistance of Concrete Columns”, Fire Saf. J., 39, pp. 433–445, 2004. [2] KD. Hertz, “Concrete Strength for Fire Safety Design”, Mag Concrete. Res., 57(8), pp. 445–453, 2005. [3] Y Ichikawa, GL England, “Prediction of Moisture Migration and Pore Pressure Build-up in Concrete at High Temperatures”, Nucl. Eng. Des., 59, pp. 228-245, 2004. [4] KD Hertz, LS Sorensen, “Test Method for Spalling of Fire Exposed Concrete”, Fire Saf. J., 40, pp. 466–476, 2005. [5] P. Kalifa, F.D. Menneteau, D. Quenard, “Spalling and Pore Pressure in HPC at High Temperatures”, Cement and Concrete Research, 30 (12), pp. 1915–1927, 2000. [6] K Sakr, E EL-Hakim, “Effect of High Temperature or Fire on Heavy Weight Concrete Properties”, Cement Concrete Res., 35(3), pp. 590– 596, 2005. [7] P. Kalifa, G. Chene, Ch. Galle, “High-temperature Behaviour of HPC with Polypropylene Fibers from Spalling to Microstructure”, Cem. Concr. Res., 31, pp. 1487–1499,2001. [8] M.S. Cülfik, T.Özturan, “Effect of Elevated Temperatures on The Residual Mechanical Properties of High-performance Mortar”, Cement Concrete Res.,32(5), pp. 809–816, 2002. [9] Ç. Elmas, “Yapay Zeka Uygulamaları”, Seçkin Yayıncılık, Ankara, 2007. [10] M. Sarıdemir, “Prediction of Compressive Strength of Concretes Containing Metakaolin and Silica Fume by Artificial Neural Networks”, Advances in Engineering Software, 40, pp. 350-355, 2009. [11] S.C. Lee, “Prediction of Concrete Strength Using Artificial Neural Networks”, Engineering Structures, 25, pp. 849–857, 2003. [12] J. Hertz, A. Krogh, and R. Palmer, “Introduction to the Theory of Neural Networks”, Addison-Wesley, Redwood City, CA., 1991. [13] A. Öztas, “Predicting the Compressive Strength and Slump of High Strength Concrete Using Neural Network”, Construction and Building Materials, 20, pp.769–775, 2006. [14] R. Begg, (Editor), “Computational Intelligence for Movement Sciences : Neural Networks and Other Emerging Techniques.” Hershey, PA, USA: Idea Group Publishing, pp. 220, 2006. [15] F. Demir, “Prediction of Elastic Modulus of Normal and High Strength Concrete by Artificial Neural Networks”, Construction and Building Materials, 22, pp. 1428–1435, 2008. [16] Ö. Kelesoğlu, “Silis Dumanı Katkılı Betonların Çarpma Dayanımının Yapay Sinir Ağı Đle Belirlenmesi”, e-Journal of New World Sciences Academy, 3, p.1, 2008. [17] K. Smith, (Editor), “Neural Networks in Business: Techniques and Applications”, Hershey, PA, USA: Idea Group Publishing, p.2, 2002. [18] A. Tortum, N. Yayla, C. Çelik, M. Gökdağ, “The Investigation of Model Selection Criteria in Artificial Neural Networks by The Taguchi Method”, Physica A, 386, pp. 446–468, 2007