Development of a Data-Driven Predictive Model for GFRP-Concrete Bond Strength Using the XGBoost Algorithm

Abstract:

In harsh and aggressive environments, steel reinforcement corrodes, leading to a loss of rebar strength and spalling of concrete due to internal stresses caused by the swelling of corrosion products. Therefore, in order to increase the lifespan of a structure, noncorrosive reinforcement is recommended, which includes Glass Fibre Reinforcing Polymer (GFRP) bars. These bars also offer several other advantages over steel, which include higher tensile strength, low weight and cost-effectiveness. These bars exhibit a distinct bond with concrete due to linearly elastic behaviour and different surface deformation patterns. Several empirical equations have been established to analytically predict the bond strength of these bars. This study finds out that even though these empirical models provide useful insights, they may have limitations in predicting bond strength with significant accuracy; therefore, it is imperative to come up with more rigorous data-driven prediction models. This study presents the application of an eXtreme Gradient Boosting (XGBoost)-based machine learning model which predicts the bond strength with significant accuracy, exhibiting a 0.876 coefficient of determination and a 2.319 root mean square error on the full set of data, which concludes improved predictive capability compared to traditional empirical equations.

• Periodical: Construction Technologies and Architecture (Volume 23)
• Pages: 85-90
• DOI: https://doi.org/10.4028/p-2lLl6J
• Online since: May 2026
• Authors: Muhammad Saad Ifrahim*, Abdul Jabbar Sangi, Fawwad Masood, Muhammad Umer Bin Abid Bhatti
• Keywords: Bond Strength, Data-Driven Predictive Model, GFRP Bars, Machine Learning, XGBoost Algorithm

References

[1] Nanni Antonio. Fiber-reinforced-plastic (FRP) reinforcement for concrete structures : properties and applications. Amsterdam: Elsevier; 1993.

DOI: 10.1016/b978-0-444-89689-6.50005-7

[2] El-Nemr A, Ahmed EA, Barris C, Joyklad P, Hussain Q, Benmokrane B. Bond performance of fiber reinforced polymer bars in normal-and high-strength concrete. Constr Build Mater 2023;393:131957.

DOI: 10.1016/j.conbuildmat.2023.131957

[3] Pecce M, Manfredi G, Realfonzo R, Cosenza E. Experimental and analytical evaluation of bond properties of GFRP bars. Journal of Materials in Civil Engineering 2001;13:282–90.

DOI: 10.1061/(asce)0899-1561(2001)13:4(282)

[4] ACI 440.1 R-15. Guide for the design and construction of structural concrete reinforced with FRP bars. Farmington Hills, MI: American Concrete Institute; 2015.

[5] Okelo R, Yuan RL. Bond strength of fiber reinforced polymer rebars in normal strength concrete. Journal of Composites for Construction 2005;9:203–13.

DOI: 10.1061/(asce)1090-0268(2005)9:3(203)

[6] Lee J-Y, Kim T-Y, Kim T-J, Yi C-K, Park J-S, You Y-C, et al. Interfacial bond strength of glass fiber reinforced polymer bars in high-strength concrete. Compos B Eng 2008;39:258–70.

DOI: 10.1016/j.compositesb.2007.03.008

[7] Farahi Shahri S, Mousavi SR. Predicting the bond strength between concrete and glass fiber-reinforced polymer bars using soft computing models. Iranian Journal of Science and Technology, Transactions of Civil Engineering 2023;47:3507–22.

DOI: 10.1007/s40996-023-01125-7

[8] Saad S, Polak MA. Bond behavior of glass fiber-reinforced polymer (GFRP) bars embedded in concrete: a review. Materials 2025;18:3367.

DOI: 10.3390/ma18143367

[9] Yue Z, Ouyang K, Yao X, Hu K, Li L. A critical review of fiber reinforced polymer bars: a scientometric and visualization analysis. Cleaner Materials 2025:100325.

DOI: 10.1016/j.clema.2025.100325

[10] Ifrahim MS, Sangi AJ, Hamza SM. Experimental Study on Bond Strength of Locally Manufactured GFRP Bar. Engineering Proceedings 2022;22:4.

DOI: 10.3390/engproc2022022004

[11] Basaran B, Kalkan I. Investigation on variables affecting bond strength between FRP reinforcing bar and concrete by modified hinged beam tests. Compos Struct 2020;242:112185.

DOI: 10.1016/j.compstruct.2020.112185

[12] Guo Y-C, Cai Y-J, Xie Z-H, Xiao S-H, Zhuo K-X, Cai P-D, et al. Experimental investigation of GFRP bar bonding in geopolymer concrete using hinged beam tests. Eng Struct 2025;322:119036.

DOI: 10.1016/j.engstruct.2024.119036

[13] Hossain KMA, Ametrano D, Lachemi M. Bond strength of GFRP bars in ultra-high strength concrete using RILEM beam tests. Journal of Building Engineering 2017;10:69–79.

DOI: 10.1016/j.jobe.2017.02.005

[14] Cosenza E, Manfredi G, Pecce M, Realfonzo R. Bond between glass fiber reinforced plastic reinforcing bars and concrete—Experimental analysis. Special Publication 1999;188:347–58.

DOI: 10.14359/5636

[15] Kachlakev DI. Experimental and analytical study on unidirectional and off-axis GFRP rebars in concrete. Compos B Eng 2000;31:569–75.

DOI: 10.1016/s1359-8368(99)00062-1

[16] Szczech D, Kotynia R. Beam bond tests of GFRP and steel reinforcement to concrete. Archives of Civil Engineering 2018;64:243–56.

DOI: 10.2478/ace-2018-0072

[17] Sólyom S, Balázs G. GFRP reinforcement for concrete structures -study of the effect of surface profile on bond behavior. 2018.

[18] Qader ZM, Kakshar FSM. Experimental Investigation on Bond Stress Behavior of Sand-Coated GFRP Bars with Concrete. Zanco J Pure Appl Sci 2023;35:30–8.

DOI: 10.21271/zjpas.35.3.3

[19] Rather AI, Banerjee S, Laskar A. Effect of bar surface geometry on bond behavior in GFRP-reinforced concrete beams: Experiments and design implications. Journal of Composites for Construction 2024;28:04024072.

DOI: 10.1061/jccof2.cceng-4710

[20] Tighiouart B, Benmokrane B, Gao D. Investigation of bond in concrete member with fibre reinforced polymer (FRP) bars. Constr Build Mater 1998;12:453–62.

DOI: 10.1016/s0950-0618(98)00027-0

[21] Köroğlu MA. Artificial neural network for predicting the flexural bond strength of FRP bars in concrete. Science and Engineering of Composite Materials 2019;26:12–29.

DOI: 10.1515/secm-2017-0155

[22] Öztornacı B, Ata B, Kartal S. Analysing household food consumption in Turkey using machine learning techniques. Agris On-Line Papers in Economics and Informatics 2024;16.

DOI: 10.7160/aol.2024.160207