Düşük, Orta ve Yüksek Dayanım için Karar Ağacı Algoritmasıyla Beton Karışım Tasarımı

Öz

Bu makale çalışmasında, mineral katkılı (silis dumanı) ve katkısız betonların karışım tasarımı için karar ağacı algoritmasıyla karışım tasarımı parametreleri 470 adet betona ait 3760 veri derlenerek belirlenmiştir. Elde edilen sonuçlar üzerinde yorumlar ve irdelemeler yapılmıştır. Karar ağacı algoritması sonuçları incelendiğinde, beton karışımları üzerinde en etkili parametreler belirlenmiştir. Elde edilen sonuçlar göstermektedir ki, her bir basınç dayanımı aralığı için en önemli parametre çimento dozajıdır ve diğer parametreler önem derecesine bağlı olarak daha sonra gelmektedir. Diğer yönden, yüksek basınç dayanımları arzulanması durumunda, ince madde içeriğinin belirtilen değerlere yakın olarak seçilmesi gerekli olup ince agreganın boşluk doldurucu etkisi ve sonucu olarak kompakt beton oluşumu/yüksek basınç dayanımı elde edilmesi ilişkisini göstermektedir denilebilir. Ayrıca elde edilen analiz sonucu farklı dayanım aralıkları için hangi karışım içeriğinden hangi miktarlarda seçilmesi gerektiğine %75 doğrulukla bir çözüm getirilmektedir. Böylelikle, beton karışım tasarımı için geliştirilmiş ilgili standartlardaki (örneğin, TS 802) detaylardan bağımsız olarak hangi dayanım için hangi beton içeriğinin seçilebileceği önerisi literatür verisi ile desteklenerek sağlanmıştır.

Anahtar Kelimeler

• Beton karışım tasarımı
• Karar ağacı algoritması
• Mineral katkı
• Silis dumanı

Concrete Mixture Design with Decision Tree Algorithm for Low, Medium and High Strengths

Öz

In this paper, the mixture design parameters for the mixture design of concretes with and without mineral additive (silica fume) were determined by compiling 3760 concrete data for 470 concrete series with the decision tree algorithm. Comments and analyzes were made on the results obtained. When the results of the decision tree algorithm were examined, the most effective parameters on the concrete mixtures were determined. Obtained results show that the most important parameter for each compressive strength range is cement dosage and other parameters come later depending on their importance. On the other hand, if high compressive strengths are desired, the fine matter content should be chosen close to the specified values, and it can be said that the gap-filling effect of the fine aggregate and the resultant compact concrete formation/high compressive strength relationship are shown. In addition, the result of the analysis obtained provides a solution with 75% accuracy to choose which mixture content and which amounts for different strength ranges. Thus, the suggestion that which concrete content can be selected for which strength, regardless of the details in the relevant standards developed for concrete mix design (for example, TS 802), is supported by the literature data.

Anahtar Kelimeler

• : Concrete mix design
• Decision tree algorithm
• Mineral admixture
• Silica füme

Kaynakça

1. ⦁ TS 802, 2016. Turkish Standards Institution, Design of Concrete Mixes, Ankara.
2. ⦁ TS EN 206-1, 2019. Concrete- Specification, Performance, Production and Conformity, Ankara.
3. ⦁ ACI, ACI-318M-05, 2004. Building Code Requirements for Structural Concrete and Commentary, Farmington Hills, MI, USA.
4. ⦁ SEAONC, 2013. Construction Quality Assurance Committee, Guidelines for Reviewing Concrete Mix Designs in Accordance with the 2010 CBC.
5. ⦁ Li, N., Shi, C., Zhang, Z., Wang, H., Liu, Y., 2019. A Review on Mixture Design Methods for Geopolymer Concrete, Composites Part B: Engineering. 178, 107490.
6. ⦁ Dave, S., Bhogayata, A., 2020. The Strength Oriented Mix Design for Geopolymer Concrete Using Taguchi Method and Indian Concrete Mix Design Code. Construction and Building Materials Mat. 262, 120853.
7. ⦁ Omary, S., Ghorbel, E., Wardeh, G., Nguyen, MD., 2018. Mix Design and Recycled Aggregates Effects on the Concrete’s Properties. International Journal of Civil Engineering, 16, 973–992.
8. ⦁ Kupaei, RH., Alengaram, UJ., Bin Jumaat, MZ., Nikraz, H., 2013. Mix Design for Fly Ash Based Oil Palm Shell Geopolymer Lightweight Concrete. Construction and Building Materials, 43 490–496.

9. ⦁ Junaid, M., Kayali, O., Khennane, A., Black, J., 2015. A Mix Design Procedure for Low Calcium Alkali Activated Fly Ash-Based Concretes. Construction and Building Materials, 79, 301–310.
10. ⦁ Wardeh, G., Ghorbel, E., Gomart, H., 2015. Mix Design and Properties Of Recycled Aggregate Concretes: Applicability of Eurocode 2. International Journal of Concrete Structures and Materials, 9, 1–20.
11. ⦁ Erdoğan, T., 2007. Beton. METU Press, Ankara, 741.
12. ⦁ Adil, M., Ullah, R., Noor, S., Gohar, N., 2020. Effect of Number of Neurons and Layers in an Artificial Neural Network for Generalized Concrete Mix Design. Neural Computing and Applications, 1-9.
13. ⦁ Nowozin, S., Rother, C., Bagon, S., Sharp, T., Bangpeng Y., Kohli, P., 2011. Decision Tree Fields. 2011 International Conference on Computer Vision, IEEE, 1668–1675.
14. ⦁ Myles, AJ., Feudale, RN., Liu, Y., Woody, NA., Brown, S., 2004. An Introduction to Decision Tree Modeling. Journal of Chemometrics. 18, 275–285.
15. ⦁ Kumar, R., Verma, R., 2021. Classification Algorithms for Data Mining: A Survey. Journal of Innovations in Engineering and Technology, 1, 7–14.
16. ⦁ Güçlüer, K., Özbeyaz, A., Göymen, S., Günaydın, O., 2021. A Comparative Investigation Using Machine Learning Methods for Concrete Compressive Strength Estimation. Materials Today Communications, 27, 102278.
17. ⦁ Friedl, M., Brodley, C., 1997. Decision Tree Classification of Land Cover From Remotely Sensed Data. Remote Sensing of Environment, 61, 399–409.
18. ⦁ Rokach, L., Maimon, O., 2005. Decision Trees, Data Mining and Knowledge Discovery Handbook, Springer-Verlag. New York, 165–192.
19. ⦁ Karbassi, A., Mohebi, B., Rezaee, S., Lestuzzi, P., 2014. Damage Prediction for Regular Reinforced Concrete Buildings Using the Decision Tree Algorithm. Computers and Structures, 130, 46–56.
20. ⦁ Sojobi, A., Aladegboye, O., Awolusi, T., 2018. Green Interlocking Paving Units. Construction and Building Materials, 173, 600–614.
21. ⦁ Milborrow, S., 2017. R Part. Plot: Plot’rpart’Models: An Enhanced Version of’plot. rpart’. R Package Version 2.1.2.
22. ⦁ Joseph, VR., 2022. Optimal Ratio for Data Splitting. Statistical Analysis and Data Mining: The ASA Data Science Journal, 15, 531-538.
23. ⦁ Gholamy, A., Kreinovich, V., Kosheleva, O., 2018. Why 70/30 Or 80/20 Relation between Training and Testing Sets: A Pedagogical Explanation. Technical Report: UTEP-CS-18- 09.
24. ⦁ Al-Haidari, H., Al-Haydari, IS., 2022. Artificial Intelligence-based Compressive Strength Prediction of Medium to High Strength Concrete. Iranian Journal of Science and Technology. Transactions of Civil Engineering, 46(2), 951-964.
25. ⦁ Dilbas, H., Çakır, Ö., 2021. Physical and Mechanical Properties of Treated Recycled Aggregate Concretes: Combination of Mechanical Treatment and Silica Fume. Journal of Materials in Civil Engineering. 33, 04021096.
26. ⦁ Baradan, B., Yazıcı, H., Ün, H., 2010. Beton ve Betonarme Yapılarda Kalıcılık Durabilite. THBB, 318.
27. ⦁ Çakır, Ö., Dilbas, H., 2021. Durability Properties of Treated Recycled Aggregate Concrete: Effect of Optimized Ball Mill Method. Construction and Building Materials, 268, 121776.
28. ⦁ Ren, M., Wen, X., Gao, X., Liu, Y., 2021. Thermal and Mechanical Properties of Ultra- High Performance Concrete Incorporated with Microencapsulated Phase Change Material. Construction and Building Materials, 273, 121714.
29. ⦁ Liu, Y., Zhang, Z., Shi, C., Zhu, C., Li, N., Deng, N., 2020. Development of Ultra-High Performance Geopolymer Concrete (UHPGC): Influence of Steel Fiber on Mechanical Properties. Cement and Concrete Composites, 112, 103670.
30. ⦁ Arunothayan, AR., Nematollahi, B., Ranade, R., Bong, Sh., Sanjayan, J., 2020. Development of 3D-printable Ultra-High Performance Fiber-Reinforced Concrete for Digital Construction. Construction and Building Materials, 257, 119546.
31. ⦁ Jiao, Y., Zhang, Y., Guo, M., Zhang, L., Ning, H., Liu, S., 2020. Mechanical and Fracture Properties of Ultra-High Performance Concrete (UHPC) Containing Waste Glass Sand as Partial Replacement Material. Journal Of Cleaner Production, 277, 123501.
32. ⦁ Atiş, C., Özcan, F., Karahan, O., Bilim, C., Sevim, U., Demir, A., 2004. Silis Dumanı Kullanımının Beton Basınç Dayanımı Üzerindeki Etkisi. Türkiye Mühendislik Haberleri, 426, 54-59.