Machine Learning-Based Empirical Formulations for Strength Properties of Steel Fiber Reinforced Concrete

Document Type : Regular Paper

Authors

1 Ph.D. Candidate, Department of Civil Engineering, Faculty of Engineering, University of Qom, Qom, Iran

2 Associate Professor, Department of Civil Engineering, Faculty of Engineering, University of Qom, Qom, Iran

3 Professor, Department of Railway Engineering, Iran University of Science and Technology, Tehran, Iran

Abstract

The accurate approximation is a benefit of the modern machine learning technique, which also disappeared the problems of traditional empirical methods, such as human and technical errors plus environmental pollution. Although there are many good samples on the state-of-the-art regarding the machine learning prediction of strength properties of steel fiber reinforced concrete, fewer articles are dedicated to proposing empirical formulations. This paper brings some novel empirical formulations to identify the strength properties of macro steel fiber-reinforced concrete. A 2650 multi-national data records are used to perform the regression, which is an exclusive dataset. This archive is the largest available dataset used in the state-of-the-art steel fiber-reinforced concrete prediction process, which is beneficial for supervised learning. Since the user must be careful regarding overtraining with such a vast resource, a successful strategy provided by the authors in previous research is utilized in which various machine learning techniques are compared to forecast the considered properties. So the Ridge, Lasso, and linear methods are used as regressors to predict the strength properties and the constants. Symbolic regression, a powerful tool for producing empirical formulations, is used for creating mathematical expressions regarding the strength properties. The performance is also evaluated based on well-known error analysis metrics. The formulations are presented for flat, waved, and hooked end fibers, the most common fibers used in construction engineering. The machine learning-driven formulations are exclusive due to the utilized strategy and the resources, and the precision of the relations are denoted, which presents the superiority to traditional methods.

Highlights

  • This paper brings some novel empirical formulations to identify the strength properties of macro steel fiber-reinforced concrete.
  • A 2650 multi-national data records are used to perform the regression, which is an exclusive dataset.
  • Since the user must be careful regarding overtraining with such a vast resource, a successful strategy provided by the authors in previous research is utilized in which various machine learning techniques are compared to forecast the considered properties.
  • The Ridge, Lasso, and linear methods are used as regressors to predict the strength properties and the constants. Symbolic regression, a powerful tool for producing empirical formulations, is used for creating mathematical expressions regarding the strength properties.
  • The performance is also evaluated based on well-known error analysis metrics.
  • The formulations are presented for flat, waved, and hooked end fibers, the most common fibers used in construction engineering.
  • The machine learning-driven formulations are exclusive due to the utilized strategy and the resources, and the precision of the relations are denoted, which presents the superiority to traditional methods.

Keywords

Main Subjects

References

[1]     Boursier Niutta C, Wehrle EJ, Duddeck F, Belingardi G. Surrogate modeling in design optimization of structures with discontinuous responses. Struct Multidiscip Optim 2018;57:1857–69. https://doi.org/10.1007/s00158-018-1958-7.
[2]     Faisal FW, Ashour SA. Mechanical properties of high-strength fiber reinforced concrete. ACI Mater J 1992;89:449–55.
[3]     Khaloo A, Kim N. Mechanical Properties of Normal to High-Strength Steel Fiber-Reinforced Concrete. Cem Concr Aggregates 1996;18:92–7. https://doi.org/10.1520/CCA10156J.
[4]     Nataraja MC, Dhang N, Gupta AP. Stress–strain curves for steel-fiber reinforced concrete under compression. Cem Concr Compos 1999;21:383–90. https://doi.org/10.1016/S0958-9465(99)00021-9.
[5]     Song P., Hwang S. Mechanical properties of high-strength steel fiber-reinforced concrete. Constr Build Mater 2004;18:669–73. https://doi.org/10.1016/j.conbuildmat.2004.04.027.
[6]     Yazıcı Ş, İnan G, Tabak V. Effect of aspect ratio and volume fraction of steel fiber on the mechanical properties of SFRC. Constr Build Mater 2007;21:1250–3. https://doi.org/10.1016/j.conbuildmat.2006.05.025.
[7]     Ou Y-C, Tsai M-S, Liu K-Y, Chang K-C. Compressive Behavior of Steel-Fiber-Reinforced Concrete with a High Reinforcing Index. J Mater Civ Eng 2012;24:207–15. https://doi.org/10.1061/(ASCE)MT.1943-5533.0000372.
[8]     Adhikary BB, Mutsuyoshi H. Prediction of shear strength of steel fiber RC beams using neural networks. Constr Build Mater 2006;20:801–11. https://doi.org/10.1016/j.conbuildmat.2005.01.047.
[9]     Thomas J, Ramaswamy A. Mechanical Properties of Steel Fiber-Reinforced Concrete. J Mater Civ Eng 2007;19:385–92. https://doi.org/10.1061/(ASCE)0899-1561(2007)19:5(385).
[10]   Wang HT, Wang LC. Experimental study on static and dynamic mechanical properties of steel fiber reinforced lightweight aggregate concrete. Constr Build Mater 2013;38:1146–51. https://doi.org/10.1016/j.conbuildmat.2012.09.016.
[11]   Ghanizadeh AR, Ghanizadeh A, Asteris PG, Fakharian P, Armaghani DJ. Developing bearing capacity model for geogrid-reinforced stone columns improved soft clay utilizing MARS-EBS hybrid method. Transp Geotech 2023;38:100906. https://doi.org/10.1016/j.trgeo.2022.100906.
[12]   Fakharian P, Rezazadeh Eidgahee D, Akbari M, Jahangir H, Ali Taeb A. Compressive strength prediction of hollow concrete masonry blocks using artificial intelligence algorithms. Structures 2023;47:1790–802. https://doi.org/10.1016/j.istruc.2022.12.007.
[13]   Alilou VK, Teshnehlab M. Prediction of 28-day compressive strength of concrete on the third day using artificial neural networks. Int J Eng 2010;3:565–76.
[14]   Chopra P, Sharma RK, Kumar M. Prediction of Compressive Strength of Concrete Using Artificial Neural Network and Genetic Programming. Adv Mater Sci Eng 2016;2016:1–10. https://doi.org/10.1155/2016/7648467.
[15]   Khademi A, Behfarnia K, Kalman Šipoš T, Miličević I. The use of machine learning models in estimating the compressive strength of recycled brick aggregate concrete. Comput Eng Phys Model 2021;4:1–25.
[16]   Hossain KMA, Gladson LR, Anwar MS. Modeling shear strength of medium- to ultra-high-strength steel fiber-reinforced concrete beams using artificial neural network. Neural Comput Appl 2017;28:1119–30. https://doi.org/10.1007/s00521-016-2417-2.
[17]   Ahn N, Jang H, Park DK. Presumption of shear strength of steel fiber reinforced concrete beam using artificial neural network model. J Appl Polym Sci 2007;103:2351–8. https://doi.org/10.1002/app.25121.
[18]   Abbas YM, Iqbal Khan M. Influence of Fiber Properties on Shear Failure of Steel Fiber Reinforced Beams Without Web Reinforcement: ANN Modeling. Lat Am J Solids Struct 2016;13:1483–98. https://doi.org/10.1590/1679-78252851.
[19]   Açikgenç M, Ulaş M, Alyamaç KE. Using an Artificial Neural Network to Predict Mix Compositions of Steel Fiber-Reinforced Concrete. Arab J Sci Eng 2015;40:407–19. https://doi.org/10.1007/s13369-014-1549-x.
[20]   Shende AM, Pande AM, Manchalwar S. Prediction of flexural Strength of SFRC form Concrete Strength without fibres. IOP Conf Ser Mater Sci Eng 2018;410:012023. https://doi.org/10.1088/1757-899X/410/1/012023.
[21]   Kabir A, Hasan M, Miah K. Predicting 28 days compressive strength of concrete from 7 days test result. Proc. Int. Conf. Adv. Des. Constr. Struct., 2012, p. 18–22.
[22]   Sharifi Y, Moghbeli A. Stepwise Regression for shear capacity assessment of steel fiber reinforced concrete beams. J Rehabil Civ Eng 2019;7:152–63.
[23]   Kara IF. Empirical modeling of shear strength of steel fiber reinforced concrete beams by gene expression programming. Neural Comput Appl 2013;23:823–34. https://doi.org/10.1007/s00521-012-0999-x.
[24]   Sharifi Y, Moghbeli A. New predictive models via gene expression programming and multiple nonlinear regression for SFRC beams. J Mater Res Technol 2020;9:14294–306. https://doi.org/10.1016/j.jmrt.2020.10.026.
[25]   Al-Musawi AA, Alwanas AAH, Salih SQ, Ali ZH, Tran MT, Yaseen ZM. Shear strength of SFRCB without stirrups simulation: implementation of hybrid artificial intelligence model. Eng Comput 2020;36:1–11. https://doi.org/10.1007/s00366-018-0681-8.
[26]   Kang M-C, Yoo D-Y, Gupta R. Machine learning-based prediction for compressive and flexural strengths of steel fiber-reinforced concrete. Constr Build Mater 2021;266:121117. https://doi.org/10.1016/j.conbuildmat.2020.121117.
[27]   Keshtegar B, Bagheri M, Yaseen ZM. Shear strength of steel fiber-unconfined reinforced concrete beam simulation: Application of novel intelligent model. Compos Struct 2019;212:230–42. https://doi.org/10.1016/j.compstruct.2019.01.004.
[28]   Sarveghadi M, Gandomi AH, Bolandi H, Alavi AH. Development of prediction models for shear strength of SFRCB using a machine learning approach. Neural Comput Appl 2019;31:2085–94. https://doi.org/10.1007/s00521-015-1997-6.
[29]   Ahmadi M, Kheyroddin A, Dalvand A, Kioumarsi M. New empirical approach for determining nominal shear capacity of steel fiber reinforced concrete beams. Constr Build Mater 2020;234:117293. https://doi.org/10.1016/j.conbuildmat.2019.117293.
[30]   Taghavi Parsa MH, Adlparvar MR, Esmaeili M. Machine Learning and Feature Selection Techniques for Predicting the Strength Properties of Steel Fiber Reinforced Concrete. J Struct Des Constr Pract 2022.
[31]   Adlparvar MR, Esmaeili M, Taghavi Parsa MH. Strength properties of fiber reinforced concrete including steel fibers. World J Eng 2024;21:194–202. https://doi.org/10.1108/WJE-12-2021-0680.
[32]   Adlparvar MR, Taghavi Parsa MH. The Improvement of the Tensile Behavior of CFRP and GFRP Laminates at Elevated Temperatures Using Fire Protection Mortar. J Rehabil Civ Eng 2021;9:41–54.
[33]   Nematzadeh Z, Ibrahim R, Selamat A. Comparative studies on breast cancer classifications with k-fold cross validations using machine learning techniques. 2015 10th Asian Control Conf., IEEE; 2015, p. 1–6. https://doi.org/10.1109/ASCC.2015.7244654.
[34]   Li J, Cheng K, Wang S, Morstatter F, Trevino RP, Tang J, et al. Feature selection: A data perspective. ACM Comput Surv 2017;50:1–45. https://doi.org/10.1145/3136625.
[35]   Bilbao I, Bilbao J. Overfitting problem and the over-training in the era of data: Particularly for Artificial Neural Networks. 2017 Eighth Int. Conf. Intell. Comput. Inf. Syst., IEEE; 2017, p. 173–7. https://doi.org/10.1109/INTELCIS.2017.8260032.
[36]   Billard L, Diday E. Symbolic Regression Analysis, 2002, p. 281–8. https://doi.org/10.1007/978-3-642-56181-8_31.
[37]   Weisberg S. Applied Linear Regression. Wiley; 2005. https://doi.org/10.1002/0471704091.
[38]   McDonald GC. Ridge regression. WIREs Comput Stat 2009;1:93–100. https://doi.org/10.1002/wics.14.
[39]   Ranstam J, Cook JA. LASSO regression. Br J Surg 2018;105:1348–1348. https://doi.org/10.1002/bjs.10895.
[40]   Kotulski ZA, Szczepinski W. Error Analysis with Applications in Engineering. vol. 169. Dordrecht: Springer Netherlands; 2010. https://doi.org/10.1007/978-90-481-3570-7.
[41]   Zheng D, Wu R, Sufian M, Kahla N Ben, Atig M, Deifalla AF, et al. Flexural Strength Prediction of Steel Fiber-Reinforced Concrete Using Artificial Intelligence. Materials (Basel) 2022;15:5194. https://doi.org/10.3390/ma15155194.
[42]   Li Y, Zhang Q, Kamiński P, Deifalla AF, Sufian M, Dyczko A, et al. Compressive Strength of Steel Fiber-Reinforced Concrete Employing Supervised Machine Learning Techniques. Materials (Basel) 2022;15:4209. https://doi.org/10.3390/ma15124209.

Files

History

  • Receive Date: 27 December 2023
  • Revise Date: 07 March 2024
  • Accept Date: 29 April 2024

Share

How to cite

Statistics