Agrega türlerinin ve farklı oranlarda kullanımının geri dönüştürülmüş agrega beton basınç dayanımına etkisinin makine öğrenmesi regresyon modellemesi uyarlanarak değerlendirilmesi

Öz

Yapay zekanın makine öğrenimi olarak adlandırılan bir dalı, çeşitli etki faktörlerini ve karmaşık faktörler arası bağlantıları dikkate alabilen bir tahmin yöntemi olarak iyi bir konuma sahiptir. Bu makine öğrenimi modelleri, özel olarak eğitilmeksizin verileri genelleştirme, tahmin etme ve onlardan öğrenme becerisine sahiptir. Regresyon teorisi, istatistiksel modelleme ve makine öğreniminde kilit bir konudur. Bu çalışmanın temel amacı, 24 Ocak 2020'deki Sivrice-Elazığ depreminin ardından yıkılan bir binadan elde edilen geri dönüştürülmüş beton agregalarından üretilen betonların erken yaş basınç dayanımını tahmin etmek için birkaç popüler makine öğrenimi regresyon modelinin performansını karşılaştırmaktır. Deprem sonrasında yeni inşa edilen binlerce yapının olması, bu yapıların hızlı bir şekilde imal edilmesi ve projenin en kısa sürede tamamlanması gibi faktörler nedeniyle erken yaş basınç dayanımı daha da büyük önem taşımaktadır. Erken yaş beton dayanımının yüksek doğrulukla ve kullanışlı bir şekilde belirlenmesi bu nedenle çok önemlidir. Bu çalışmada tüm bu hedeflere ulaşmak için yedi farklı klasik makine öğrenimi algoritması kullanılmıştır. Erken yaş basınç dayanımı değerleri 1 ve 3 gün için dikkate alınmıştır. Deneysel sonuçlar ile kullanılan algoritmaların öngördüğü sonuçlar arasındaki ilişki incelenmiş ve bu akıllı regresyon algoritmalarının kapsamlı bir karşılaştırması yapılmıştır. Sürdürülebilir kalkınma ve döngüsel ekonomi hedefleri kapsamında bu atık malzemelerin değerlendirilmesi ve üretilen betonların erken yaş basınç dayanımlarının yüksek doğrulukla belirlenebilmesi açısından makalenin literatüre önemli katkılar sağlayacağı düşünülmektedir.

Anahtar Kelimeler

• Basınç dayanımı
• İnşaat ve yıkıntı atıkları
• Makine öğrenme
• Geri dönüşüm agregalı beton

Comparing Machine Learning Regression Models for Early-Age Compressive Strength Prediction of Recycled Aggregate Concrete

Öz

A branch of artificial intelligence called machine learning is well-positioned as a prediction method that can take into consideration several influencing factors and complex inter-factor connections. Without being specifically trained to do so, these machine learning models have the ability to generalize, predict, and learn from data. Regression theory is a key topic in statistical modelling and machine learning. The main goal of this study is to compare the performance of several popular machine learning regression models for predicting the early-age compressive strength of concretes made from recycled concrete aggregates from a structure that demolished following the Sivrice-Elazig earthquake on January 24, 2020. Early-age concrete compressive strength is even more crucial due to factors like the fact that there are thousands of newly built structures in the aftermath of the earthquake, the quick manufacturing of these structures, and the completion of the project in the lowest amount of time. Determining the early-age concrete strength with high accuracy and in a useful manner is crucial for this reason. Seven different classical machine learning algorithms were employed in this study to achieve all of these goals. Early-age concrete compressive strength values were considered for 1 and 3 days. The relationship between the experimental results and the predicted outcomes of the employed algorithms was investigated, and a thorough comparison of these intelligent regression algorithms was conducted. Within the scope of sustainable development and circular economy goals, it is thought that this article will make significant contributions to the literature in terms of utilizing these waste materials and determining the early-age compressive strengths of the concretes produced with high accuracy.

Anahtar Kelimeler

• Compressive strength
• Construction and demolition waste
• Machine learning
• Recycled aggregate concrete

Kaynakça

1. Oikonomou ND. Recycled concrete aggregates, Cement and Concrete Composites 2005; 27: 315–318. https://doi.org/10.1016/j.cemconcomp.2004.02.020.
2. Farina I, Colangelo F, Petrillo A, Ferraro A, Moccia I, Cioffi R. LCA of concrete with construction and demolition waste, in: Advances in Construction and Demolition Waste Recycling, Elsevier 2020; 501–513. https://doi.org/10.1016/B978-0-12-819055-5.00024-3.
3. de Andrade Salgado F, de Andrade Silva F. Recycled aggregates from construction and demolition waste towards an application on structural concrete: A review, Journal of Building Engineering 2022; 52: 104452. https://doi.org/10.1016/j.jobe.2022.104452.
4. Abed M, Fořt J, Rashid K. Multicriterial life cycle assessment of eco-efficient self-compacting concrete modified by waste perlite powder and/or recycled concrete aggregate, Construction and Building Materials 2022; 348: 128696. https://doi.org/10.1016/j.conbuildmat.2022.128696.
5. Qin D, Zong Z, Dong C, Guo Z, Tang L, Chen C, Zhang L. Long‐term behavior of sustainable self‐compacting concrete with high volume of recycled concrete aggregates and industrial by‐products, Structural Concrete 2023; 24: 3385–3404. https://doi.org/10.1002/suco.202200464.
6. Yan Y, Gao D, Yang L, Pang Y, Zhang Y. Evaluation method of shear toughness for steel fiber‐reinforced concrete containing recycled coarse aggregate, Structural Concrete 2023; 24: 2879–2893. https://doi.org/10.1002/suco.202200324.
7. Kapoor K, Singh SP, Singh B. Improving the durability properties of self-consolidating concrete made with recycled concrete aggregates using blended cements, International Journal of Civil Engineering 2021; 19: 759–775. https://doi.org/10.1007/s40999-020-00584-7.
8. Marinković S, Radonjanin V, Malešev M, Ignjatović I. Comparative environmental assessment of natural and recycled aggregate concrete, Waste Management 2010; 30: 2255–2264. https://doi.org/10.1016/j.wasman.2010.04.012.

9. Tao X, Zhang J, Zhang Y, Li X, Zhang M. Bond Behavior Between High-Strength Recycled Aggregate Concrete and UHSSB Using Beam Test, International Journal of Civil Engineering 2022; 20: 1129-1144. https://doi.org/10.1007/s40999-022-00719-y.
10. Wang J, Xu Q. The combined effect of load and corrosion on the flexural performance of recycled aggregate concrete beams, Structural Concrete 2023; 24: 359–373. https://doi.org/10.1002/suco.202100819.
11. Yang C, Feng H, Esmaeili‐Falak M. Predicting the compressive strength of modified recycled aggregate concrete, Structural Concrete 2022. https://doi.org/10.1002/suco.202100681.
12. Ulucan M, Alyamac KE. A holistic assessment of the use of emerging recycled concrete aggregates after a destructive earthquake: Mechanical, economic and environmental, Waste Management 2022; 146: 53–65. https://doi.org/10.1016/j.wasman.2022.04.045.
13. Ulucan M, Alyamac KE. An integrative approach of the use of recycled concrete aggregate in high‐rise buildings: example of the Elysium, Structural Concrete 2023; 24: 3329–3350. https://doi.org/10.1002/suco.202200512.
14. Kul A, Ozel BF, Ozcelikci E, Gunal MF, Ulugol H, Yildirim G, Sahmaran M. Characterization and life cycle assessment of geopolymer mortars with masonry units and recycled concrete aggregates assorted from construction and demolition waste, Journal of Building Engineering 2023; 78: 107546. https://doi.org/10.1016/j.jobe.2023.107546.
15. Ilcan H, Sahin O, Unsal Z, Ozcelikci E, Kul A, Demiral NC, Ekinci MO, Sahmaran M. Effect of industrial waste-based precursors on the fresh, hardened and environmental performance of construction and demolition wastes-based geopolymers, Construction and Building Materials 2023; 394: 132265. https://doi.org/10.1016/j.conbuildmat.2023.132265.
16. Özçelikci E, Oskay A, Bayer İR, Şahmaran M. Eco-hybrid cement-based building insulation materials as a circular economy solution to construction and demolition waste, Cement and Concrete Composites 2023; 141: 105149. https://doi.org/10.1016/j.cemconcomp.2023.105149.
17. Ulucan M, Alyamac KE. A comprehensive assessment of mechanical and environmental properties of green concretes produced using recycled concrete aggregates and supplementary cementitious material, Environmental Science and Pollution Research 2023; 30: 97765–97785. https://doi.org/10.1007/s11356-023-29197-y.
18. Ulucan M, Yildirim G, Alatas B, Alyamac KE, A new intelligent sunflower optimization based explainable artificial intelligence approach for early‐age concrete compressive strength classification and mixture design of RAC, Structural Concrete 2023; 24: 7400-7418. https://doi.org/10.1002/suco.202300138.
19. Ulucan M, Tas Y, Alyamac KE, Multi‐objective optimization and assessment of recycled concrete aggregates for sustainable development: Example of the Kömürhan bridge, Structural Concrete 2023; 24: 5750–5768. https://doi.org/10.1002/suco.202201018.
20. Han B, Wu Y, Liu L. Prediction and uncertainty quantification of compressive strength of high‐strength concrete using optimized machine learning algorithms, Structural Concrete 2022; 23: 3772–3785. https://doi.org/10.1002/suco.202100732.
21. Kandiri A, Golafshani EM, Behnood A. Estimation of the compressive strength of concretes containing ground granulated blast furnace slag using hybridized multi-objective ANN and salp swarm algorithm, Construction and Building Materials 2020; 248: 118676. https://doi.org/10.1016/j.conbuildmat.2020.118676.
22. Zhang J, Huang Y, Wang Y, Ma G. Multi-objective optimization of concrete mixture proportions using machine learning and metaheuristic algorithms, Construction and Building Materials 2020; 253: 119208. https://doi.org/10.1016/j.conbuildmat.2020.119208.
23. Golafshani EM, Arashpour M, Behnood A. Predicting the compressive strength of green concretes using Harris hawks optimization-based data-driven methods, Construction and Building Materials 2022; 318: 125944. https://doi.org/10.1016/j.conbuildmat.2021.125944.
24. Tam VWY, Butera A, Le KN, Da Silva LCF, Evangelista ACJ. A prediction model for compressive strength of CO2 concrete using regression analysis and artificial neural networks, Construction and Building Materials 2022; 324: 126689. https://doi.org/10.1016/j.conbuildmat.2022.126689.
25. Amiri M, Hatami F. Prediction of mechanical and durability characteristics of concrete including slag and recycled aggregate concrete with artificial neural networks (ANNs), Construction and Building Materials 2022; 325: 126839. https://doi.org/10.1016/j.conbuildmat.2022.126839.
26. Adam SP, Alexandropoulos SAN, Pardalos PM, Vrahatis MN, No free lunch theorem: A review, Approximation and optimization 2019; 57–82. https://doi.org/10.1007/978-3-030-12767-1_5.
27. Jobson JD. Multiple linear regression, in: Applied Multivariate Data Analysis, Springer 1991: 219–398. https://doi.org/10.1007/978-1-4612-0955-3_4.
28. Jobson JD. Applied multivariate data analysis: volume II: Categorical and Multivariate Methods, Springer Science and Business Media, 2012. https://doi.org/10.1007/0-387-22753-9_8.
29. Awad M, Khanna R. Support vector regression, Efficient Learning Machines 2015: 67-80. https://doi.org/10.1007/978-1-4302-5990-9_4.
30. Ince K, Klawonn F. Decision and regression trees in the context of attributes with different granularity levels, Towards Advanced Data Analysis by Combining Soft Computing and Statistics 2013: 331–342. https://doi.org/10.1007/978-3-642-30278-7_26.
31. Vanneschi L, Castelli M, Manzoni L, Silva S, Trujillo L. Is k Nearest Neighbours Regression Better Than GP?, European Conference on Genetic Programming 2020: 244–261. https://doi.org/10.1007/978-3-030-44094-7_16.
32. Caselli M, Trizio L, De Gennaro G, Ielpo P. A simple feedforward neural network for the PM10 forecasting: comparison with a radial basis function network and a multivariate linear regression model, Water Air and Soil Pollution 2009; 201: 365–377. https://doi.org/10.1007/s11270-008-9950-2.