Yeni Geliştirilmiş Hafif Betonun Yapay Sinir Ağlarıyla Isıl İletkenliğinin Tahmini

Artan nüfus ve hızla gelişen küresel dünyada enerjiye olan bağımlılık giderek artmaktadır. Harcanan enerjinin yaklaşık %40’ı yapılarda tüketilmektedir. Yapıların ısıtılması ve soğutulması ile enerji tüketimi ve maliyeti oldukça artmıştır. Bu nedenle yapılarda enerji verimliliğini arttırmak için ısıl yalıtım özelliğine sahip yeni yapı malzemeleri üretmek kaçınılmaz olmuştur. Bu amaçla vermikülit, atık bazalt tozu, eriyik kitre ve çimento katkılı numuneler üretilmiştir. 48 adet farklı oranlarda üretilen numunelere mekanik deneyler ve ısıl iletkenlik deneyi yapılmıştır. Deneysel olarak ölçülen ısıl iletkenlik sonuçları geliştirilen yapay sinir ağı çıkışlarıyla modellenerek karşılaştırılmıştır. Modelleme için Matlab paket programı kullanılmıştır. Yapay Sinir Ağı (YSA) yaklaşımı ile deneysel olarak elde edilmiş mekanik özellikler giriş olarak kullanılmış ve numunelerin ısıl iletkenlik ile ilişkisi incelenmiştir. Bulunan sonuçların birbirleriyle uyumlu olduğu ve ısıl iletkenlik değerlerinin % 7,6701 ile % 0,0091 arasında bir hata ile tahmin edildiği ve YSA’nın % 99 oranın da başarılı sonuçlar verdiği görülmüştür.

Anahtar Kelimeler:

Genleştirilmiş vermikülit, atık bazalt tozu, ısıl iletkenlik, yapay sinir ağları

Prediction Thermal Conductivity of The Novel Developed Light Weight Concrete with Artificial Neural Networks

The dependence on energy is increasing in a growing population and a rapidly developing global world. Around 40% of the energy consumed is consumed in buildings. Building heating and cooling have boosted energy consumption and costs dramatically. As a consequence, in order to boost energy efficiency in buildings, it becomes inevitable to develop new construction materials with thermal insulation properties. Vermiculite, waste basalt powder, molten tragacanth, and cement-reinforced samples were produced for this purpose. Mechanical and thermal conductivity tests were performed on 48 samples produced at various rates. The findings of the experimentally measured thermal conductivity were modelled and compared with the outputs of the created artificial neural network. The Matlab software was used for modelling. The mechanical properties acquired experimentally using the Artificial Neural Networks (ANN) approach were used as an input, and the correlation of the samples with thermal conductivity was investigated. The findings obtained were consistent with one another, and the thermal conductivity values were predicted with an error ranging between 7.6701% and 0.0091%, and the ANN yielded successful results at a rate of 99%.

Keywords:

Expanded vermiculite, waste basalt powder, thermal conductivity, artificial neural networks,

PDF

___

[1]Duaij, J. A. A., El-Laithy K. and Payappilly R. J., “A value engineering approach to determine quality lightweight concrete aggregate,” Cost Engineering, c.39, ss. 21-26, 1997.
[2]V. Khonsari, E. Eslami, and A. Anvari, “Effects of expanded perlite aggregate (EPA) on the mechanical behavior of lightweight concrete,” in Proceedings of the 7th international conference on fracture and mechanics of concrete & concrete structure (FraMCoS-7), Jeju, Korea, ss. 1354–1361, 2010.
[3]S. Chandra and L. Berntsson, “Applications of lightweight aggregate concrete,” Science, Technology, 2002.
[4]Ö. Hasgül, A. S. Anagün “The use of artificial neural networks in the analysis of experimental Results and An Application for Concrete Strength Testing,” V. National Production Research Symposium, Istanbul, ss. 133-139, 2005.
[5]Ç. Elmas, “Artificial intelligence applications,” 5th edition, Ankara, Turkey: Seçkin Publishing, ss.1-480, 2007.
[6]M. Sarıdemir, “Prediction of compressive strength of concretes containing metakaolin and silica fume by artificial neural networks,” Advances in Engineering Software, c. 40, ss. 350-355, 2009.
[7]S.C. Lee, “Prediction of concrete strength using artificial neural networks,” Engineering Structures, 25, ss. 849–857, 2003.
[8]J. Hertz, A. Krogh, and R. Palmer, “An introduction to the theory of neural networks,” Lecture Notes, vol. 1. Studies in the Sciences of Complexity. Addison-Wesley, Redwood City,1991.
[9]A. Öztas, “Predicting the compressive strength and slump of high strength concrete using neural network,” Construction and Building Materials, c. 20, ss.769–775, 2006.
[10]Işık, E., Inallı, M., “Artificial neural networks and adaptive neuro-fuzzy inference systems approaches to forecast the meteorological data for HVAC: The case of cities for Turkey,” Energy, 154, ss. 7-16, 2018.
[11]Işık, E., İnallı, M., Celik, E., “ANN and ANFIS approaches to calculate the heating and cooling degree day values: The case of provinces in Turkey,” Arabian Journal for Science and Engineering, 44(9), ss. 7581-7597, 2019.
[12]E. Öztemel, “Artificial neural networks,” 3rd edition, Istanbul, Turkey: Papatya Publishing, ss. 1-44, 2012.
[13]M. Khandelwal, “Prediction of thermal conductivity of rocks by soft computing,” International Journal of Earth Sciences, c.100, s. 6, ss.1383-1389, 2011.
[14]F. Koçyiğit, F. Ünal, Ş. Koçyiğit,”Experimental analysis and modeling of the thermal conductivities for a novel building material providing environmental transformation,” Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, c. 42, s.24, ss.3063-3079, 2020.