Explainable machine learning-based prediction of plate-end debonding in fiber-reinforced polymer-strengthened reinforced concrete beams
Source abstract
Abstract
This study investigates plate-end (PE) debonding in reinforced concrete beams strengthened with fiber-reinforced polymer (FRP) composites. PE debonding is a critical failure mode that compromises the effectiveness and structural performance of FRP reinforcement systems. Although FRP has been widely adopted in structural rehabilitation for its high strength and corrosion resistance, PE debonding—often initiated by shear or inclined cracks—remains a persistent challenge. Conventional computational models for predicting this failure mechanism exhibit limited accuracy due to the complex nonlinear interactions among influencing parameters. To overcome these limitations, this research applies machine learning techniques, with an emphasis on explainable artificial intelligence methods such as Shapley additive explanations, to build more reliable predictive models. A comprehensive database is developed incorporating key variables governing PE debonding, and various machine learning algorithms are trained, validated, and benchmarked against existing code-based models. Furthermore, parameter importance and sensitivity analyses are conducted to improve interpretability and provide insights for advancing the design and application of FRP-reinforced structures.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Structural Behavior of Reinforced Concrete · Concrete Corrosion and Durability · Innovative concrete reinforcement materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Railway Engineering, Zhengzhou Railway Vocational and Technical College 1 , Zhengzhou 450001,
School of Civil Engineering and Architecture, Anyang Normal University 2 , Anyang 455000,
Henan Province Engineering Technology Research Center of Digital-Intelligent Building and Low-Carbon Building Materials, Anyang Normal University 3 , Anyang 455000,
Henan Jiaoyuan Engineering Technology Group Co., Ltd. 4 , Zhengzhou 450001,
School of Future Transportation, Guangzhou Maritime University 5 , Guangzhou 510725,
Funding
Henan Province Department of Education Service Industry Development Special Plan · China Postdoctoral Science Foundation · Youth Talent Promotion Project of Henan Province · Special Program for Cultivating Outstanding Young Science and Technology Talents in Zhengzhou City in 2024 · Postdoctoral Research Funding Project of Henan Province in 2023 · Henan Province Science and Technology Research Program · Key Scientific Research Project of Higher Education Institutions in Henan Province
References (40)
Show source-provided references
1. Investigation on bond behavior of GFRP bar embedded in ultra-high performance polyoxymethylene fiber reinforced concrete10.1016/j.engstruct.2024.119324 ↗
2. Explainable machine learning: Compressive strength prediction of FRP-confined concrete column10.1016/j.mtcomm.2024.108883 ↗
3. Structural response of beam-column joint made of fiber reinforced concrete (FRC) using ANSYS FEA simulation10.54740/ros.2025.015 ↗
4. Analysis on the behaviour of stiffened and unstiffened steel plate shear walls with enhanced performance10.1088/1757-899x/804/1/012035 ↗
5. A study on reinforced concrete beams strengthened with FRP and FRCM10.1016/j.engstruct.2025.119687 ↗
6. Prediction of the debonding failure of beams strengthened with FRP through machine learning models10.3390/buildings13030608 ↗
7. Data-driven model for predicting intermediate crack induced debonding of FRP-strengthened RC beams in flexure10.1016/j.istruc.2022.05.023 ↗
8. Assessment of plate-end debonding design provisions for RC beams strengthened with FRP10.1590/1679-78255920 ↗
9. End cover separation in RC beams strengthened in flexure with bonded FRP reinforcement: Simplified finite element approach10.1617/s11527-015-0645-z ↗
10. ACI-440.2R · 2017
11. JSCE · 2001
12. 2017
13. National Research Council · 2013
14. Plate end debonding in FRP-plated RC beams—I: Experiments10.1016/j.engstruct.2006.11.022 ↗
15. Empirical shear based model for predicting plate end debonding in FRP strengthened RC beams10.3846/jcem.2021.14304 ↗
16. Explainable machine learning (XML) framework for seismic assessment of structures using extreme gradient boosting (XGBoost)10.1016/j.engstruct.2025.119621 ↗
17. Enhancing FRP-concrete interface bearing capacity prediction with explainable machine learning: A feature engineering approach and SHAP analysis10.1016/j.engstruct.2024.118831 ↗
18. Prediction of load-bearing capacity of FRP-steel composite tubed concrete columns: Using explainable machine learning model with limited data10.1016/j.istruc.2024.107890 ↗
19. Explainable machine learning model for predicting compressive strength of CO2-cured concrete10.1016/j.cscm.2025.e04589 ↗
20. P. A. Ritchie , “External reinforcement of concrete beams using fiber reinforced plastic,” M.S. thesis, Lehigh University, 1988.
21. Experimental and analytical investigation of FRP strengthened beam response: Part I10.1680/macr.1996.48.177.331 ↗
22. Brittle failure in FRP plate and sheet bonded beams10.14359/487 ↗
23. Flexural strengthening of RC beams with CFRP sheets
24. Compressive strength and elastic modulus of RBAC: An analysis of existing data and an artificial intelligence based prediction10.1016/j.cscm.2023.e02184 ↗
25. Ductility of reinforced concrete beams strengthened with CFRP strips and fabric10.1142/9789812704863_0030 ↗
26. Enhancing the debonding strain limit for CFRP-strengthened RC beams using U-clamps: Identification of design parameters10.1061/(asce)cc.1943-5614.0000599 ↗
27. Experimental study on RC beams with FRP strips bonded with rubber modified resins10.1016/j.compscitech.2004.05.016 ↗
28. A hybrid Bayesian model updating and non-dominated sorting genetic algorithm framework for intelligent mix design of steel fiber reinforced concrete10.1016/j.engappai.2025.112071 ↗
29. Mesoscale modeling of flexural fracture behavior in steel fiber reinforced concrete10.1177/13694332241226921 ↗
30. Uniaxial mechanical behaviors of recycled coarse aggregate concretes cast with conventional and equivalent mortar volume methods10.1177/13694332221108439 ↗
31. Cleaner production of the precast concrete industry: Comparative life cycle analysis of concrete using recycled aggregates from crushed precast rejects10.1080/19648189.2023.2240882 ↗
32. Data-driven analysis on compressive behavior of unconfined and confined recycled aggregate concretes10.1016/j.conbuildmat.2022.129282 ↗
33. Ensemble machine learning models for compressive strength and elastic modulus of recycled brick aggregate concrete10.1016/j.mtcomm.2024.110635 ↗
34. An agile, intelligent and scalable framework for mix design optimization of green concrete incorporating recycled aggregates from precast rejects10.1016/j.cscm.2024.e03156 ↗
35. Probabilistic models for characteristic bond stresses of steel-concrete in steel reinforced concrete structures10.1016/j.engstruct.2023.117167 ↗
36. Probabilistic models for shear strength of circular and square concrete-filled steel tubes10.1063/5.0250829 ↗
37. Compressive stress–strain relationship and its variability of basalt fiber reinforced recycled aggregate concrete10.1063/5.0220434 ↗
38. Explainable machine learning models for punching shear capacity of FRP bar reinforced concrete flat slab without shear reinforcement10.1016/j.cscm.2024.e03162 ↗
39. Machine learning-based evaluation of shear capacity of recycled aggregate concrete beams10.3390/ma13204552 ↗
40. Machine learning based compressive strength prediction model for CFRP-confined columns10.1007/s12205-023-0827-0 ↗