Yüksek performanslı betonun basınç dayanımının farklı makine öğrenimi algoritmaları ile tahmin edilmesi

Abstract

Betonun basınç dayanımı, beton bileşenlerinin miktarları ve özellikleri, yaşı, ortam koşulları, deneysel koşullar gibi birçok faktörden etkilenmektedir. Betonun en önemli özelliği olan basınç dayanımının belirlenmesi amacıyla makine öğrenimi algoritmaları alternatif bir yöntem olarak kullanılmaktadır. Bu çalışmada, yüksek performanslı betonun basınç dayanımını tahmin etmek amacıyla 1030 satırlık açık veri seti üzerinde altı farklı makine öğrenimi modeli kullanılmıştır. Ayrıca mevcut veri setine türetilen yeni öznitelikler ilave edilerek betonun basınç dayanımını tahmin etme süreçlerindeki etkileri incelenmiştir. Bu bağlamda yeni özniteliklerin algoritmaların performansına olan katkısı değerlendirilmiş ve hangi algoritmaların en iyi sonuçları verdiği analiz edilmiştir. Elde edilen sonuçlara göre doğru tahmin etme yeteneği ve süre açısından en iyi sonucu XGBoost ve LightGBM algoritmaları göstermiştir. Buna ilaveten, veri setine iki yeni öznitelik daha eklenmesi kullanılan makine öğrenimi algoritmalarının doğru tahmin etme yeteneğini arttırmıştır.

Keywords

• Beton
• Basınç Dayanımı
• Makine Öğrenimi

Prediction of high performance concrete compressive strength with different machine learning algorithms

Abstract

Compressive strength of concrete is influenced by various factors including the amount and properties of concrete components, age, environmental conditions and experimental conditions. Machine learning algorithms are emerging as an alternative method for determining the compressive strength of concrete which is one of its most critical properties. In this study six different machine learning models were employed to predict the compressive strength of high-performance concrete using an open dataset of 1030 samples. Additionally the impact of incorporating newly derived features into the existing dataset on the prediction process was examined. The contribution of these new features to the performance of the algorithms was evaluated and the algorithms yielding the best results were analyzed. According to the results XGBoost and LightGBM demonstrated the best performance in terms of prediction accuracy and computational efficiency. Moreover, adding two new features to the dataset improved the predictive accuracy of the employed machine learning algorithms.

Keywords

• Concrete
• Compressive Strength
• Machine Learning

References

1. Kandiri A, Golafshani EM, Behnood A (2020) 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 248:118676. https://doi.org/10.1016/ j.conbuildmat.2020.118676
2. Nguyen H, Vu T, Vo TP, Thai HT (2021) Efficient machine learning models for prediction of concrete strengths. Construction and Building Materials 266:120950. https://doi.org/10.1016/j.conbuildmat.2020.120950
3. AlShareedah O, Nassiri S (2021) Pervious concrete mixture optimization, physical, and mechanical properties and pavement design: A review. Journal of Cleaner Production 288:125095. https://doi.org/ 10.1016/j.jclepro.2020.125095.
4. Mardani-Aghabaglou A, Bayqra SH, Özen S, Altun MG, Faqiri ZA, Ramyar K (2020) Silindirle sıkıştırılmış beton karışımlarının tasarım yöntemleri ve yapılan çalışmalar. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi 26(3):419-431. https://doi.org/10.5505/pajes.2019.93530.
5. Han Q, Gui C, Xu J, Lacidogna G (2019) A generalized method to predict the compressive strength of high-performance concrete by improved random forest algorithm. Construction and Building Materials 226:734-742. https://doi.org/10.1016/j.conbuildmat.2019.07.315.
6. Elemam WE, Abdelraheem AH, Mahdy MG, Tahwia AM (2020) Optimizing fresh properties and compressive strength of self-consolidating concrete. Construction and Building Materials 249:118781. https://doi.org/10.1016/j.conbuildmat.2020.11878.
7. Mardani-Aghabaglou A, Tuyan M, Yılmaz G, Arıöz Ö, Ramyar K (2013) Effect of different types of superplasticizer on fresh, rheological and strength properties of self-consolidating concrete. Construction and Building Materials 47:1020-1025. https://doi.org/10.1016/j.conbuildmat.2013.05.105
8. Mardani-Aghabaglou A, Sezer Gİ, Ramyar K (2014) Comparison of fly ash, silica fume and metakaolin from mechanical properties and durability performance of mortar mixtures view point. Construction and Building Materials 70:17-25. https://doi.org/10.1016/j.conbuildmat.2014.07.089

9. Aydogmus HY, Erdal HI, Karakurt O, Namli E, Turkan YS, Erdal H (2015) A comparative assessment of bagging ensemble models for modeling concrete slump flow. Computers and Concrete. 16(5):741-757. https://doi.org/10.12989/cac.2015.16.5.741.
10. Banthia N, Sheng J (1996) Fracture toughness of micro-fiber reinforced cement composites. Cement and Concrete Composites 18:251-269. https://doi.org/10.1016/0958-9465(95)00030-5.
11. Altun MG, Oltulu M (2020) Effect of different types of fiber utilization on mechanical properties of recycled aggregate concrete containing silica füme. Journal of Green Building 15(1):119-136. https://doi.org/10.3992/1943-4618.15.1.119.
12. Güneyisi E, Gesoglu M, Özbay E (2009) Evaluating and forecasting the initial and final setting times of self-compacting concretes containing mineral admixtures by neural network. Materials and Structures 42:469-484. https://doi.org/10.1617/s11527-008-9395-5.
13. Avci E, Altun MG, (2023) Betonun çökme ve basınç dayanımının makine öğrenmesi modelleri kullanılarak tahmin edilmesi. ICSHSR 4th International Conference on Health, Engineering and Applied Sciences.
14. Yeh IC (1998) Modeling of strength of high-performance concrete using artificial neural networks. Cement and Concrete Research 28:1797-1808. https://doi.org/10.1016/S0008-8846(98)00165-3.
15. Nguyen-Sy T, Wakim J, To QD, Vu MN, Nguyen TD, Nguyen TT (2020) Predicting the compressive strength of concrete from its compositions and age using the extreme gradient boosting method. Construction and Building Materials 260:119757. https://doi.org/10.1016/j.conbuildmat.2020.119757.
16. Yörübulut S, Dogan O, Erdugan F, Yörübulut S (2019) Tahribatsız Yöntem Verileri Kullanılarak Yapay Sinir Ağı ve Regresyon Yöntemi ile Beton Basınç Dayanımının Tahmin Edilmesi. International Journal of Engineering Research and Development 12(2):769-776. https://doi.org/10.29137/umagd.734655
17. Topçu İB, Boğa AR, Hocaoğlu FO (2009) Modeling corrosion currents of reinforced concrete using ANN. Automation in Construction 18(2):145-152. https://doi.org/10.1016/j.autcon.2008.07.004.
18. Boğa AR, Öztürk M, Topçu İB (2013) Using ANN and ANFIS to predict the mechanical and chloride permeability properties of concrete containing GGBFS and CNI. Composites:Part B 45:688-696. https://doi.org/10.1016/j.compositesb.2012.05.054.
19. Ofuyatan OM, Agbawhe OB, Omole DO, Igwegbe CA, Ighalo JO (2022) RSM and ANN modelling of the mechanical properties of self compacting concrete with silica fume and plastic waste as partial constituent replacement. Cleaner Materials 4:100065. https://doi.org/10.1016/j.clema.2022.100065.
20. Hammoudi A, Moussaceb K, Belebchouche C, Dahmoune F (2019) Comparison of artificial neural network (ANN) and response surface methodology (RSM) prediction in compressive strength of recycled concrete aggregates. Construction and Building Materials 209:425-436. https://doi.org/10.1016/ j.conbuildmat.2019.03.119.
21. Açikgenç M, Ulaş M, Alyamaç KE (2015) Using an artificial neural network to predict mix compositions of steel fiber-reinforced concrete. Arabian Journal for Science and Engineering 40:407-419. https://doi.org/10.1007/s13369-014-1549-x
22. Hossain MM, Uddin MN, Hossain MAS (2023) Prediction of compressive strength ultra-high steel fiber reinforced concrete (UHSFRC) using artificial neural networks (ANNs). Materials Today: Proceedings. https://doi.org/10.1016/j.matpr.2023.02.409
23. Köksal F, Şahin Y, Beycioğlu A, Gencel O, Brostow W (2012) Estimation of fracture energy of high-strength steel fibre-reinforced concrete using rule-based Mamdani-type fuzzy inference system. Science and Engineering of Composite Materials 19(4):373-380. https://doi.org/10.1515/secm-2012-0017
24. Neville AM (1997) Properties of Concrete. London: Wiley
25. Mehta PK, Monteiro P (1997) Concrete: microstructure, properties, and materials. McGraw-Hill Publishing.
26. Baradan B, Türkel S, Yazıcı H, Ün H, Yiğiter H, Felekoğlu B, Tosun K, Aydın S, Yardımcı MY, Topal A Öztürk AU (2012) Beton. Dokuz Eylül Üniversitesi Mühendislik Fakültesi No:334, İzmir, Türkiye.
27. Daemen J, Rijmen V, Daemen J, Rijmen V (2020). Correlation matrices. The design of Rijndael: the advanced encryption standard (AES), 91-113.
28. Awad M, Khanna R, Awad M, Khanna R (2015) Support vector regression. Efficient learning machines: Theories, concepts, and applications for engineers and system designers, pp. 67-80.
29. Parbat D, Chakraborty M (2020) A python based support vector regression model for prediction of COVID19 cases in India. Chaos, Solitons & Fractals, 138, 109942.
30. Biau G, Scornet E (2016) A random forest guided tour. Test, 25:197-227.
31. Chen T, Guestrin C (2016) Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
32. Brownlee J (2016) XGBoost With python: Gradient boosted trees with XGBoost and scikit-learn. Machine Learning Mastery.
33. Collins M, Schapire RE, Singer Y (2002) Logistic regression, AdaBoost and Bregman distances. Machine Learning 48:253-285.
34. Gao R, Liu Z (2020) An improved adaboost algorithm for hyperparameter optimization. In Journal of Physics: Conference Series 1631(1), 012048. IOP Publishing.
35. Beskopylny AN, Stel’makh SA, Shcherban EM, Mailyan LR, Meskhi B, Razveeva I, Beskopylny N (2022) Concrete strength prediction using machine learning methods CatBoost, k-nearest neighbors, support vector regression. Applied Sciences 12(21), 10864. https://doi.org/10.3390/app122110864.
36. Xiang W, Xu P, Fang J, Zhao Q, Gu Z, Zhang Q (2022) Multi-dimensional data-based medium-and long-term power-load forecasting using double-layer CatBoost. Energy Reports 8:8511-8522. https://doi.org/10.1016/j.egyr.2022.06.063.
37. Al-Kasassbeh M, Abbadi MA, Al-Bustanji AM (2020) LightGBM algorithm for malware detection. In Intelligent Computing: Proceedings of the 2020 Computing Conference 3:391-403. Springer International Publishing.
38. Ju Y, Sun G, Chen Q, Zhang M, Zhu H, Rehman MU (2019) A model combining convolutional neural network and LightGBM algorithm for ultra-short-term wind power forecasting. Ieee Access 7:28309-28318. https://doi.org/10.1109/ACCESS.2019.2901920
39. Tatachar AV (2021) Comparative assessment of regression models based on model evaluation metrics. International Journal of Innovative Technology and Exploring Engineering 8(9):853-860.
40. Chicco D, Warrens MJ, Jurman G (2021) The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. Peerj Computer Science 7, e623. https://doi.org/10.7717/peerj-cs.623
41. Zhou Z, Hooker G (2021) Unbiased measurement of feature importance in tree-based methods. ACM Transactions on Knowledge Discovery from Data (TKDD) 15(2):1-21.
42. Jeon H, Oh S (2020) Hybrid-recursive feature elimination for efficient feature selection. Applied Sciences 10(9), 3211. https://doi.org/10.3390/app10093211
43. Chen T, Guestrin C (2016) Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp 785-794).
44. Chen C, Zhang Q, Ma Q, Yu B (2019) LightGBM-PPI: Predicting protein-protein interactions through LightGBM with multi-information fusion. Chemometrics and Intelligent Laboratory Systems 191:54-64. https://doi.org/10.1016/j.chemolab.2019.06.003.
45. Solomatine DP. Shrestha DL (2004) AdaBoost. RT: a boosting algorithm for regression problems. In 2004 IEEE international joint conference on neural networks (IEEE Cat. No. 04CH37541) (Vol 2, pp 1163-1168). IEEE.
46. Awad M, Khanna R, Awad M, Khanna R (2015) Support vector regression. Efficient learning machines: Theories, concepts, and applications for engineers and system designers. Springer Nature. pp 67-80.
47. Feng J, Zhang H, Gao K, Liao Y, Gao W, Wu G (2022) Efficient creep prediction of recycled aggregate concrete via machine learning algorithms. Construction and Building Materials 360,129497. https://doi.org/10.1016/j.conbuildmat.2022.129497.