Gauss Süreç Regresyonu ve Destek Vektör Makineleri Kullanılarak Değerlendirilen Kendiliğinden Yerleşen Beton Davranışının Deneysel Veri İle Doğrulanması

Öz

İnşaat Mühendisliği alanında yapı malzemelerinin özellikle betonun karışım tasarımını anlamak ve bazı özelliklerini tahmin edebilmek için makine öğrenmesi metotları sıkça kullanılmaya başlanmıştır. Bu bağlamda oldukça faydalı olan makine öğrenmesi metotları sayısız denilebilecek çeşitliliktedir. Bu çalışmada makine öğrenmesi metotlarından Gauss Süreç Regresyonu (GSR) ve Destek Vektör Makineleri (DVM), Kendiliğinden Yerleşen Beton (KYB)’nin basınç dayanımını tahmin etmek için tercih edilmiştir. Çalışmanın amacı, farklı makine öğrenmesi metotlarının beton performansını tahmin etmekteki başarılarının ispat edilmesi ve böylece bu metotların özellikle beton karışım tasarımı alanında kullanımının arttırılmasıdır. Bu amaçla, KYB bileşimini ve özelliklerini içeren deneysel veri seti ile GSR ve DVM modelleri geliştirilmiştir. Geliştirilen modellerin performansları hem birbirleri ile hem de bu alanda başarısını literatürdeki birçok çalışma ile ispat etmiş olan başka bir makine öğrenmesi metodu, Yapay Sinir Ağı ile karşılaştırılmıştır. Sonuçta, deneysel veri ile eğitilen ve doğrulanan GSR ve DVM modellerinin KYB’nin basınç dayanım performansını tahmin etmekte başarılı oldukları ortaya çıkmıştır. Çalışma sonuçlarına göre GSR bu problemdeki en başarılı metot olmuştur. GSR için deneysel veri ile modelin çıkışı arasındaki korelasyon katsayıları eğitim aşamasında 0.9888 ve test aşamasında 0.8648 olarak hesaplanmıştır.

Anahtar Kelimeler

• Destek Vektör Makineleri
• Gauss Süreç Regresyonu
• Yapay Sinir Ağları
• Kendiliğinden Yerleşen Beton
• Makine Öğrenmesi

Evaluation of Self-Compacting Concrete Behavior by Using Gaussian Process Regression and Support Vector Machines via Experimental Data Validation

Öz

In the field of Civil Engineering, machine learning methods have been used frequently in order to understand the mixture design and to predict some properties of building materials, especially concrete. Machine learning methods, which are very useful in this context, can be said to be innumerable. In this study, Gaussian Process Regression (GPR) and Support Vector Machines (SVM), which are two types of machine learning methods, were preferred to estimate the compressive strength of Self Compacting Concrete (SCC). The aim of the study is to prove the success of different machine learning methods in predicting concrete performance and thus to redound the usage of the methods, especially for concrete mix design. For this purpose, GPR and SVM models were developed with the experimental data set containing the SCC mix composition and properties. The performances of the developed models were compared both with each other and with another machine learning method, Artificial Neural Network, which has proven its success with numerous studies in the literature. As a result, it was revealed that the GPR and SVM models, trained and validated with an experimental dataset, were successful in predicting the compressive strength of SCC. In addition, GSR has been the most successful method in this problem. The correlation coefficients between the experimental data and the output of the GSR model were calculated as 0.9888 in the training state and 0.8648 in the testing state.

Anahtar Kelimeler

• Support Vector Machines, Gaussian Process Regression, Artificial Neural Network, Self-Compacting Concrete, Machine Learning

Kaynakça

1. O. Altay, M. Ulas, and K. E. Alyamac, “Prediction of the Fresh Performance of Steel Fiber Reinforced Self-Compacting Concrete Using Quadratic SVM and Weighted KNN Models,” IEEE Access, vol. 8, pp. 92647–92658, 2020, doi: 10.1109/ACCESS.2020.2994562.
2. O. Altay, T. Gurgenc, M. Ulas, and C. Özel, “Prediction of wear loss quantities of ferro-alloy coating using different machine learning algorithms,” Friction, vol. 8, no. 1, pp. 107–114, 2020, doi: 10.1007/s40544-018-0249-z.
3. T. Gurgenc, O. Altay, M. Ulas, and C. Ozel, “Extreme learning machine and support vector regression wear loss predictions for magnesium alloys coated using various spray coating methods,” J. Appl. Phys., vol. 127, no. 18, p. 185103, May 2020, doi: 10.1063/5.0004562.
4. O. Altay, M. Ulas, and K. E. Alyamac, “DCS-ELM: a novel method for extreme learning machine for regression problems and a new approach for the SFRSCC.,” PeerJ. Comput. Sci., vol. 7, p. e411, 2021, doi: 10.7717/peerj-cs.411.
5. M. Açıkgenç, M. Ulaş, and K. E. Alyamaç, “Using an Artificial Neural Network to Predict Mix Compositions of Steel Fiber-Reinforced Concrete,” Arab. J. Sci. Eng., vol. 40, no. 2, pp. 407–419, 2015, doi: 10.1007/s13369-014-1549-x.
6. M. Acikgenc Ulas, “Development of an artificial neural network model to predict waste marble powder demand in eco‐efficient self‐compacting concrete,” Struct. Concr., no. January, pp. 1–14, May 2022, doi: 10.1002/suco.202200043.
7. T. Standard, “TS 802 Beton karışım tasarımı hesap esasları.” Turkish Standards Institutions, Ankara, 2016.
8. V. Chandwani, V. Agrawal, and R. Nagar, “Modeling slump of ready mix concrete using genetic algorithms assisted training of Artificial Neural Networks,” Expert Syst. Appl., vol. 42, no. 2, pp. 885–893, 2015, doi: 10.1016/j.eswa.2014.08.048.

9. M. T. Uddin, A. H. Mahmood, M. R. I. Kamal, S. M. Yashin, and Z. U. A. Zihan, “Effects of maximum size of brick aggregate on properties of concrete,” Constr. Build. Mater., vol. 134, pp. 713–726, Mar. 2017, doi: 10.1016/J.CONBUILDMAT.2016.12.164.
10. U. Atici, “Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network,” Expert Syst. Appl., vol. 38, no. 8, pp. 9609–9618, Aug. 2011, doi: 10.1016/J.ESWA.2011.01.156.
11. A. Behnood and E. M. Golafshani, “Predicting the compressive strength of silica fume concrete using hybrid artificial neural network with multi-objective grey wolves,” J. Clean. Prod., vol. 202, pp. 54–64, 2018, doi: 10.1016/j.jclepro.2018.08.065.
12. C. Bilim, C. D. Atiş, H. Tanyildizi, and O. Karahan, “Predicting the compressive strength of ground granulated blast furnace slag concrete using artificial neural network,” Adv. Eng. Softw., vol. 40, no. 5, pp. 334–340, May 2009, doi: 10.1016/J.ADVENGSOFT.2008.05.005.
13. H. Naderpour, A. H. Rafiean, and P. Fakharian, “Compressive strength prediction of environmentally friendly concrete using artificial neural networks,” J. Build. Eng., vol. 16, pp. 213–219, Mar. 2018, doi: 10.1016/J.JOBE.2018.01.007.
14. B. K. R. Prasad, H. Eskandari, and B. V. V. Reddy, “Prediction of compressive strength of SCC and HPC with high volume fly ash using ANN,” Constr. Build. Mater., vol. 23, no. 1, pp. 117–128, Jan. 2009, doi: 10.1016/J.CONBUILDMAT.2008.01.014.
15. İ. B. Topçu and M. Sarıdemir, “Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic,” Comput. Mater. Sci., vol. 41, no. 3, pp. 305–311, Jan. 2008, doi: 10.1016/J.COMMATSCI.2007.04.009.
16. G. Pazouki, E. M. Golafshani, and A. Behnood, “Predicting the compressive strength of self-compacting concrete containing Class F fly ash using metaheuristic radial basis function neural network,” Struct. Concr., no. January, pp. 1–23, 2021, doi: 10.1002/suco.202000047.
17. R. N. Sağlam, M. Açıkgenç Ulaş, and K. E. Alyamaç, “Hafif Beton Üretimi İçin Gerekli Olan Hafif Agrega Miktarının Yapay Sinir Ağı ile Tahmin Edilmesi,” Fırat Üniversitesi Mühendislik Bilim. Derg., vol. 34, no. 2, pp. 889–898, 2022, doi: 10.35234/fumbd.1133877.
18. A. M. Abd and S. M. Abd, “Modelling the strength of lightweight foamed concrete using support vector machine (SVM),” Case Stud. Constr. Mater., vol. 6, pp. 8–15, 2017, doi: https://doi.org/10.1016/j.cscm.2016.11.002.
19. H. Ling, C. Qian, W. Kang, C. Liang, and H. Chen, “Combination of Support Vector Machine and K-Fold cross validation to predict compressive strength of concrete in marine environment,” Constr. Build. Mater., vol. 206, pp. 355–363, 2019, doi: https://doi.org/10.1016/j.conbuildmat.2019.02.071.
20. Z. Fan, R. Chiong, Z. Hu, and Y. Lin, “A fuzzy weighted relative error support vector machine for reverse prediction of concrete components,” Comput. Struct., vol. 230, p. 106171, 2020, doi: https://doi.org/10.1016/j.compstruc.2019.106171.
21. J. Dhanpat, A. Higginson, and K. Brooks, “Estimation of the Effect of Bio-Admixtures on Concrete Workability Using Linear Regression and Support Vector Machines,” IFAC-PapersOnLine, vol. 54, no. 21, pp. 133–138, 2021, doi: https://doi.org/10.1016/j.ifacol.2021.12.023.
22. N. Harish and P. Janardhan, “Support vector machine in predicting epoxy glass powder mixed cement concrete,” Mater. Today Proc., vol. 46, pp. 9042–9046, 2021, doi: https://doi.org/10.1016/j.matpr.2021.05.385.
23. K. Zhang, K. Zhang, R. Bao, and X. Liu, “A framework for predicting the carbonation depth of concrete incorporating fly ash based on a least squares support vector machine and metaheuristic algorithms,” J. Build. Eng., vol. 65, p. 105772, 2023, doi: https://doi.org/10.1016/j.jobe.2022.105772.
24. B. Basaran, I. Kalkan, E. Bergil, and E. Erdal, “Estimation of the FRP-concrete bond strength with code formulations and machine learning algorithms,” Compos. Struct., vol. 268, p. 113972, 2021, doi: https://doi.org/10.1016/j.compstruct.2021.113972.
25. K. Liu, Z. Dai, R. Zhang, J. Zheng, J. Zhu, and X. Yang, “Prediction of the sulfate resistance for recycled aggregate concrete based on ensemble learning algorithms,” Constr. Build. Mater., vol. 317, p. 125917, 2022, doi: https://doi.org/10.1016/j.conbuildmat.2021.125917.
26. K. Ozawa, K. Maekawa, M. Kunishima, and H. Okamura, “High-performance concrete based on the durability of concrete structures,” 1989.
27. H. Okamura, K. Ozawa, K. Maekawa, and S. Tangtermsinikul, “High-performance concrete mechanism of super-fluidized concrete,” in EIT-JSCE-AIT joint seminar on solution to urban infrastructure problems through civil engineering technology, 1992, p. 16.
28. X. Wang, K. Wang, P. Taylor, and G. Morcous, “Assessing particle packing based self-consolidating concrete mix design method,” Constr. Build. Mater., vol. 70, pp. 439–452, 2014, doi: 10.1016/j.conbuildmat.2014.08.002.
29. H. Yazici, “The effect of silica fume and high-volume Class C fly ash on mechanical properties, chloride penetration and freeze-thaw resistance of self-compacting concrete,” Constr. Build. Mater., vol. 22, no. 4, pp. 456–462, 2008, doi: 10.1016/j.conbuildmat.2007.01.002.
30. B. Felekoǧlu, S. Türkel, and B. Baradan, “Effect of water/cement ratio on the fresh and hardened properties of self-compacting concrete,” Build. Environ., vol. 42, no. 4, pp. 1795–1802, 2007, doi: 10.1016/j.buildenv.2006.01.012.
31. K. E. Alyamaç and R. Ince, “A preliminary concrete mix design for SCC with marble powders,” Constr. Build. Mater., vol. 23, no. 3, pp. 1201–1210, Mar. 2009, doi: 10.1016/j.conbuildmat.2008.08.012.
32. M. C. S. Nepomuceno, L. A. Pereira-de-Oliveira, and S. M. R. Lopes, “Methodology for the mix design of self-compacting concrete using different mineral additions in binary blends of powders,” Constr. Build. Mater., vol. 64, pp. 82–94, 2014, doi: 10.1016/j.conbuildmat.2014.04.021.
33. H. J. H. Brouwers and H. J. Radix, “Self-compacting concrete: Theoretical and experimental study,” Cem. Concr. Res., vol. 35, no. 11, pp. 2116–2136, 2005, doi: 10.1016/j.cemconres.2005.06.002.
34. H. W. Reinhardt and M. Stegmaier, “Influence of heat curing on the pore structure and compressive strength of self-compacting concrete (SCC),” Cem. Concr. Res., vol. 36, no. 5, pp. 879–885, 2006, doi: 10.1016/j.cemconres.2005.12.004.
35. R. Siddique, P. Aggarwal, and Y. Aggarwal, “Influence of water/powder ratio on strength properties of self-compacting concrete containing coal fly ash and bottom ash,” Constr. Build. Mater., vol. 29, pp. 73–81, 2012, doi: 10.1016/j.conbuildmat.2011.10.035.
36. S. Nunes, H. Figueiras, P. Milheiro Oliveira, J. S. Coutinho, and J. Figueiras, “A methodology to assess robustness of SCC mixtures,” Cem. Concr. Res., vol. 36, no. 12, pp. 2115–2122, 2006, doi: 10.1016/j.cemconres.2006.10.003.
37. V. B. Bosiljkov, “SCC mixes with poorly graded aggregate and high volume of limestone filler,” Cem. Concr. Res., vol. 33, no. 9, pp. 1279–1286, 2003, doi: 10.1016/S0008-8846(03)00013-9.
38. E. Güneyisi, M. Gesoǧlu, Z. Algin, and H. Yazici, “Effect of surface treatment methods on the properties of self-compacting concrete with recycled aggregates,” Constr. Build. Mater., vol. 64, pp. 172–183, 2014, doi: 10.1016/j.conbuildmat.2014.04.090.
39. M. Gesoǧlu, E. Güneyisi, M. E. Kocabaǧ, V. Bayram, and K. Mermerdaş, “Fresh and hardened characteristics of self compacting concretes made with combined use of marble powder, limestone filler, and fly ash,” Constr. Build. Mater., vol. 37, pp. 160–170, 2012, doi: 10.1016/j.conbuildmat.2012.07.092.
40. E. Güneyisi, M. Gesoğlu, S. Al-Rawi, and K. Mermerdaş, “Effect of volcanic pumice powder on the fresh properties of self-compacting concretes with and without silica fume,” Mater. Struct. Constr., vol. 47, no. 11, pp. 1857–1865, 2014, doi: 10.1617/s11527-013-0155-9.
41. K. E. Alyamaç, E. Ghafari, and R. Ince, “Development of eco-efficient self-compacting concrete with waste marble powder using the response surface method,” J. Clean. Prod., vol. 144, pp. 192–202, 2017, doi: 10.1016/j.jclepro.2016.12.156.
42. P. K. Mehta and P. J. M. Monteiro, Concrete: Microstructure, Propertiesand Materials. New York: McGraw-Hill, 2006.
43. M. A. Ulas, K. E. Alyamac, and Z. C. Ulucan, “Effects of aggregate grading on the properties of steel fibre-reinforced concrete,” IOP Conf. Ser. Mater. Sci. Eng., vol. 246, p. 12015, 2017, doi: 10.1088/1757-899x/246/1/012015.
44. C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995, doi: 10.1007/BF00994018.
45. T. Kavzoğlu and İ. Çölkesen, “Destek vektör makineleri ile uydu görüntülerinin sınıflandırılmasında kernel fonksiyonlarının etkilerinin incelenmesi,” Harit. Derg., vol. 76, no. 144, pp. 73–82, 2010, [Online]. Available: http://search/yayin/detay/102501.
46. M. Korkmaz, A. Dogan, and V. Kirmaci, “Performance Analysis of Counterflow Ranque – Hilsch Vortex Tube with Linear Regression, Support Vector Machines and Gaussian Process Regression Method,” Gazi J. Eng. Sci., vol. 8, no. 2, pp. 361–370, 2022, doi: 10.30855/gmbd.0705015.
47. O. Chapelle, P. Haffner, and V. N. Vapnik, “Support vector machines for histogram-based image classification,” IEEE Trans. Neural Networks, vol. 10, no. 5, pp. 1055–1064, 1999, doi: 10.1109/72.788646.
48. E. Snelson and Z. Ghahramani, “Local and global sparse Gaussian process approximations,” in the Eleventh International Conference on Artificial Intelligence and Statistics, 2007, vol. 2, pp. 524–531, [Online]. Available: http://proceedings.mlr.press/v2/snelson07a/snelson07a.pdf.
49. J. Vanhatalo, V. Pietiläinen, and A. Vehtari, “Approximate inference for disease mapping with sparse Gaussian processes,” Stat. Med., vol. 29, no. 15, pp. 1580–1607, Jul. 2010, doi: https://doi.org/10.1002/sim.3895.
50. M. N. Mohd Aris, H. Daud, S. C. Dass, and K. A. Mohd Noh, “Gaussian Process Methodology for Multi-Frequency Marine Controlled-Source Electromagnetic Profile Estimation in Isotropic Medium,” Processes, vol. 7, no. 10. 2019, doi: 10.3390/pr7100661.
51. J. Liang, Z. Shi, F. Zhu, W. Chen, X. Chen, and Y. Li, “Gaussian Process Autoregression for Joint Angle Prediction Based on sEMG Signals,” Front. Public Heal., vol. 9, 2021, doi: 10.3389/fpubh.2021.685596.
52. Ç. Elmas, Yapay Zeka Uygulamaları. Ankara: Seçkin Yayıncılık, 2007.
53. M. Sarıdemir, “Prediction of compressive strength of concretes containing metakaolin and silica fume by artificial neural networks,” Adv. Eng. Softw., vol. 40, no. 5, pp. 350–355, May 2009, doi: 10.1016/J.ADVENGSOFT.2008.05.002.
54. A. S. Pandya and R. B. Macy, Pattern Recognition with Neural Networks in C++. Boca Raton, Florida: CRC Press, 1996.
55. A. J. Thomas, M. Petridis, S. D. Walters, S. M. Gheytassi, and R. E. Morgan, “On Predicting the Optimal Number of Hidden Nodes,” in 2015 International Conference on Computational Science and Computational Intelligence (CSCI), 2015, pp. 565–570, doi: 10.1109/CSCI.2015.33.