ANN KULLANARAK ÇELİK FİBERLİ GEOPOLİMER BETONLARIN EĞİLME DAYANIMININ TAHMİNİ

Yıl 2024, Cilt: 11 Sayı: 24, 489 - 501, 31.12.2024

Necip Altay Eren

https://doi.org/10.54365/adyumbd.1473171

Öz

Geopolimer mekanik özellikler, işlenebilirlik ve uzun süreli kullanımdan sonra dayanıklılıktaki iyi performansları nedeniyle birçok inşaat alanında incelenmiş ve uygulanmıştır. Geopolimer betonun eğilme dayanımının belirlenmesi için genellikle pahalı laboratuvar testleri gerekmektedir. Bu çalışmanın amacı eğilme dayanımını daha hızlı, doğru, ucuz ve zahmetsiz tahmin edilmesidir. Yapay zekanın geliştirilmesi, deneysel veriler aracılığıyla beton yapıların performansını verimli bir şekilde tahmin edebilen ve belirleyebilen bazı yöntemler önermektedir. Bu araştırmada, makine öğrenimi ile çelik fiber takviyeli geopolimer betonların eğilme dayanım performansının tahmini ve doğrulanması değerlendirilmiştir. Literatürdeki geopolimer betonun eğilme dayanımına ilişkin çalışmalardaki deneysel veriler kullanılarak toplamda 104 deney verisi içeren bir veri seti oluşturulmuş ve modellemeye hazır hale getirilmiştir. Bu veri seti, Yapay Sinir Ağı yöntemi kullanılarak Python programlama diliyle modellenmiş ve analiz edilmiştir. Yapılan çalışma sonucunda R2 değeri 0,994183 olarak elde edilmiştir. Bu sonuçlar, Yapay Sinir Ağı modelinin çelik fiberli geopolimer betonun eğilme dayanımını tahmin etmede oldukça başarılı olduğunu göstermektedir. Sonuç olarak, yapay zekâ teknikleri eğilme dayanım sonuçlarının daha hızlı tahmin edebilecek ve maliyetleri önemli ölçüde azaltacak imkânlar sunmaktadır. Bu çalışmanın bulguları, inşaat sektöründe gelecekteki araştırma ve uygulamalar için umut verici bir yöntem sunmaktadır.

Anahtar Kelimeler

Geopolimer, Eğilme Dayanımı, Yapay Sinir Ağı, Çelik Fiber

ESTIMATION OF FLEXURAL STRENGTH OF STEEL FIBER GEOPOLYMER CONCRETE USING ANN

Öz

Geopolymer has been studied and applied in many construction areas due to its good performances in mechanical properties, workability and durability after long-term use. Expensive laboratory tests are usually required to determine the flexural strength of geopolymer concrete. The aim of this study is to estimate the flexural strength more quickly, accurately, cheaply and effortlessly. The development of artificial intelligence suggests some methods that can efficiently predict and determine the performance of concrete structures through experimental data. In this research, the flexural strength performance prediction and verification of steel fiber reinforced geopolymer concretes were evaluated with machine learning. A data set containing a total of 104 experimental data was created using experimental data from studies on the flexural strength of geopolymer concrete in the literature and made ready for modeling. This data set was modeled and analyzed with the Python programming language using the Artificial Neural Network method. As a result of the study, the R2 value was obtained as 0.994183. These results show that the Artificial Neural Network model is quite successful in predicting the flexural strength of steel fiber geopolymer concrete. In conclusion, artificial intelligence techniques offer the opportunity to predict flexural strength results faster and significantly reduce costs. The findings of this study provide a promising method for future research and applications in the construction industry.

Anahtar Kelimeler

Geopolymer, Flexural Strength, ANN, Steel Fiber

Kaynakça

• Niveditha M, Koniki S. Effect of Durability properties on Geopolymer concrete–A Review. E3S Web of Conferences EDP Sciences 2020; Vol. 184. https://doi.org/10.1051/e3sconf/202018401092
• Eren NA. Punching shear behavior of geopolymer concrete two-way flat slabs incorporating a combination of nano silica and steel fibers. Construction and Building Materials 2022; Volume 346, 128351. https://doi.org/10.1016/j.conbuildmat.2022.128351
• Bernal SA, Rodrı´guez ED, Mejı´a de Gutie´rrez R, Marisol Gordillo M, Provis JL. Mechanical and thermal characterisation of geopolymers based on silicate-activated metakaolin/slag blends. Journal of Materials Science 2011; volume 46, pages 5477–5486.
• Davidovits J. Geopolymers and geopolymeric materials. Journal of thermal analysis, 1989; volume 35, pages 429–441.
• Duxson P, Provis JL, Lukey GC, Deventer JSJ. The role of inorganic polymer technology in the development of ‘green concrete’. Cement and Concrete Research 2007; 37 1590–1597.
• Davidovits J. Properties of Geopolymer Cements. In First International Conference on Alkaline Cements and Concretes 1994; 131–149.
• Deng F, He Y, Zhou S, Yu Y, Cheng H, Wu X. Compressive strength prediction of recycled concrete based on deep learning. Construction and Building Materials 2018; Vol. 175, pp. 562-569. https://doi.org/10.1016/j.conbuildmat.2018.04.169
• Şimşek O. Beton ve Beton Teknolojisi, Seçkin Yayınevi, 2016; ISBN: 9789750261930, Türkiye.
• Arunkumar K, Muthukannan M, Sureshkumar A. Experimental Behaviour of Fiber Reinforced Reactive Powder Concrete International Journal of Engineering and Advanced Technology (IJEAT) 2019; 9 (1S4) (2019) 454-459.
• Aggarwal P, Aggarwal Y, Siddique R, Gupta S and Garg H. Fuzzy logic modeling of compressive strength of high-strength concrete (HSC) with supplementary cementitious material. Journal of Sustainable Cement-Based Materials, 2013; pp.1-16
• Razavi SU, Jumaat MZ and El-Shafie AH. Load-deflection Analysis of CFRF strengthened RC slab using focused feedforward time delay neural network. Concrete Research Letters, 5(3), 2014; pp.858-872.
• Moghaddam MG and Khajeh M. Comparison of Response Surface Methodology and Artificial Network in predicting microwave-assisted extraction procedure to determine zinc in fish muscles. Food and Nutrition Sciences, 2, 2011; pp.803- 808.
• Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Duchesnay É. Scikit-learn: Machine learning in Python. The Journal of Machine Learning Research, 2011; 12, 2825-2830.
• Gomes RF, Dias DP, Silva FA. Determination of the fracture parameters of steel fiber-reinforced geopolymer concrete, Theoretical and Applied Fracture Mechanics, 2020; Volume 107, https://doi.org/10.1016/j.tafmec.2020.102568
• Ding Y, Bai YL. Fracture properties and softening curves of steel fiber-reinforced slag-based geopolymer mortar and concrete. Materials 2018; 11(8), 1445.
• Pham KV, Nguyen TK, Le TA, Han SW, Lee G, Lee K. Assessment of performance of fiber reinforced geopolymer composites by experiment and simulation analysis. Applied Sciences 2019; 9(16), 3424.
• Aisheh YIA, Atrushi DS, Akeed MH, Qaidi S, Tayeh BA. Influence of polypropylene and steel fibers on the mechanical properties of ultra-high-performance fiber-reinforced geopolymer concrete. Case Studies in Construction Materials 2022; 17, e01234.
• Zhang P, Wang J, Li Q, Wan J, Ling Y. Mechanical and fracture properties of steel fiber-reinforced geopolymer concrete. Science and Engineering of Composite Materials 2021; 28(1), 299-313.
• Sukontasukkul P, Pongsopha P, Chindaprasirt P, Songpiriyakij S. Flexural performance and toughness of hybrid steel and polypropylene fibre reinforced geopolymer. Construction and Building Materials 2018; 161, 37-44.
• Liu Y, Shi C, Zhang Z, Li N, Shi D. Mechanical and fracture properties of ultra-high performance geopolymer concrete: Effects of steel fiber and silica fume. Cement and Concrete Composites 2020; 112, 103665.
• Khan MZN, Hao Y, Hao H, Shaikh FUA. Mechanical properties of ambient cured high strength hybrid steel and synthetic fibers reinforced geopolymer composites. Cement and Concrete Composites 2018; 85, 133-152.
• Liu Y, Zhang Z, Shi C, Zhu D, Li N, Deng Y. Development of ultra-high performance geopolymer concrete (UHPGC): Influence of steel fiber on mechanical properties. Cement and Concrete Composites 2020; 112:103670. https://doi.org/10.1016/j.cemconcomp.2020.103670
• Vijai K, Kumutha R, Vishnuram BG. Effect of Inclusion of Steel Fibres on The Properties of Geopolymer Concrete Composites. Asian Journal of Civil Engineering (Building and Housing) 2012; 13(3), 381-389. https://sid.ir/paper/298940/en
• Zaid O, Martínez-García R, Abadel AA, Fraile-Fernández FJ, Alshaikh IM, Palencia-Coto C. To determine the performance of metakaolin-based fiber-reinforced geopolymer concrete with recycled aggregates. Archives of Civil and Mechanical Engineering 2022; 22(3), 114.
• Sanjayan JG, Nazari A, Pouraliakbar H. FEA modelling of fracture toughness of steel fibre-reinforced geopolymer composites. Materials & Design 2015; 76, 215-222.
• Rabiaa E, Mohamed RAS, Sofi WH, Tawfik TA. Developing geopolymer concrete properties by using nanomaterials and steel fibers. Advances in Materials Science and Engineering 2020; 2020, 1-12.
• Bellum RR. Influence of steel and PP fibers on mechanical and microstructural properties of fly ash-GGBFS based geopolymer composites. Ceramics International 2022; 48(5), 6808-6818.
• Faris MA, Abdullah MMAB, Muniandy R, Abu Hashim MF, Błoch K, Jeż B, Garus S, Palutkiewicz P, Mohd Mortar NA, Ghazali MF. Comparison of Hook and Straight Steel Fibers Addition on Malaysian Fly Ash-Based Geopolymer Concrete on the Slump, Density, Water Absorption and Mechanical Properties. Materials. 2021; 14(5):1310. https://doi.org/10.3390/ma14051310
• Wang Y, Aslani F, Valizadeh A. An investigation into the mechanical behaviour of fibre-reinforced geopolymer concrete incorporating NiTi shape memory alloy, steel and polypropylene fibres. Construction and Building Materials 2020; Volume 259, 119765 https://doi.org/10.1016/j.conbuildmat.2020.119765
• Bernal S, De Gutierrez R, Delvasto S, Rodriguez E. Performance of an alkali-activated slag concrete reinforced with steel fibers. Construction and building Materials 2010; 24(2), 208-214.
• Eren NA, Alzeebaree R, Çevik A, Niş A, Mohammedameen A, Gülşan ME. Fresh and hardened state performance of self-compacting slag based alkali activated concrete using nanosilica and steel fiber. Journal of Composite Materials 2021; 55(28):4125-4139. doi:10.1177/00219983211032390
• Shah SFA, Chen B, Oderji SY, Haque MA, Ahmad MR. Comparative study on the effect of fiber type and content on the performance of one-part alkali-activated mortar. Construction and Building Materials 2020; 243:118221. https://doi.org/10.1016/j.conbuildmat.2020.118221
• Ganesh AC, Sowmiya K, Muthukannan M. Investigation on the effect of steel fibers in geopolymer concrete. In IOP Conference Series: Materials Science and Engineering 2020; Vol. 872, No. 1, p. 012156. IOP Publishing. doi:10.1088/1757-899X/872/1/012156
• Bhutta A, Borges PH, Zanotti C, Farooq M, Banthia N. Flexural behavior of geopolymer composites reinforced with steel and polypropylene macro fibers. Cement and Concrete Composites 2017; 80, 31-40. http://dx.doi.org/10.1016/j.cemconcomp.2016.11.014
• Simon H. Neural networks: a comprehensive foundation. Prentice Hall PTR, 1998.
• Mohammad R, Toufigh V. Evaluation of geopolymer concrete at high temperatures: An experimental study using machine learning. Journal of Cleaner Production 2022; 372: 133608. https://doi.org/10.1016/j.jclepro.2022.133608
• Al-Jabery, K.K., Obafemi-Ajayi, T., Olbricht, G.R. and Wunsch Ii, D.C. (2020), “9 – Data analysis and machine learning tools in MATLAB and python”, in Al-Jabery, K.K., Obafemi-Ajayi, T.,Olbricht, G.R. and Wunsch Ii, D.C., (Eds), Computational Learning Approaches to Data Analytics in Biomedical Applications, Academic Press, pp. 231-290.
• Géron A. Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, O’Reilly Media 2019.
• Kaya M. Geopolimer Betonun Yangın Dayanımının Makine Öğrenmesi Algoritmaları Kullanılarak Modellenmesi. Yüksek Lisans Tezi, Iğdır Üniversitesi İnşaat Mühendisliği Ana Bilim Dalı 2023.