Vol. 22, No. 4, pp. 418-431 (2026)
MOMENT CAPACITY PREDICTION OF HIGH STRENGTH
STEEL (HSS)-ECC COMPOSITE BEAMS USING
MACHINE LEARNING MODELS
Cong-Luyen Nguyen * and Binh-Nam Nguyen
The University of Danang - University of Science and Technology, Danang, Vietnam
*(Corresponding author: E-mail:This email address is being protected from spambots. You need JavaScript enabled to view it.)
Received: 5 January 2026; Revised: 16 February 2026; Accepted: 13 March 2026
DOI:10.18057/IJASC.2026.22.4.6
 View Article |
Export Citation: Plain Text | RIS | Endnote |
ABSTRACT
The demand for high-performance structures has led to the development of composite beams made of High Strength Steel (HSS) I-section and Engineered Cementitious Composites (ECC) slab connected through headed shear studs, which could enhance both ductility and flexural capacity compared to conventional counterpart. Accurate prediction of flexural strength in HSS-ECC composite beams is crucial for optimal design and safety. This study presents a machine learning approach, including five machine learning (ML) models (i.e., Extreme Gradient Boosting (XGBoost), Artificial Neural Network (ANN), Support Vector Regression (SVR), Categorical Boosting (CatBoost), and Random Forest (RF)) to predict the flexural capacity of HSS-ECC composite beams. A total of 135 composite beam data were compiled and utilized for training and validating the machine learning models. By using performance metrics, it is indicate that all of the employed ML models showed excellent predicted performance, among which the SVR model exhibits superior predictive accuracy by achieving the lowest prediction errors (MAE, MAPE, and RMSE) together with the highest coefficient of determination (R² = 0.99), indicating superior generalization ability. This offers a viable alternative to traditional analytical approaches for predicting structural engineering.
KEYWORDS
HSS-ECC composite beams, Moment capacity, Machine learning, Extreme Gradient Boosting (XGBoost), Artificial Neural Network (ANN), Support Vector Regression (SVR)
REFERENCES
[1] Uy B. and R. Sloane, “Behavior of composite tee beams constructed with high strength steel”, Journal of Constructional Steel Research, 1: 203-204, 1998. https://doi.org/10.1016/S0143-974X(98)00126-6
[2] Zhao H. and Yuan Y., “Experimental studies on composite beams with high-strength steel and concrete”, Steel and Composite Structures, 10(5): 373-383, 2010. https://doi.org/10.12989/scs.2010.10.5.373.
[3] Ban H. and Bradford M.A., “Flexural behaviour of composite beams with high strength steel”, Engineering Structures, 56: 1130-1141, 2013. https://doi.org/10.1016/j.engstruct.2013.06.040.
[4] Shamass R. and Cashell K.A., “Behaviour of Composite Beams Made Using High Strength Steel”, Structures, 12: 88-101, 2017. https://doi.org/10.1016/j.istruc.2017.08.005.
[5] Ban H., Bradford M. A., Uy B., and Liu X., “Available rotation capacity of composite beams with high strength materials under sagging moment”, Journal of Constructional Steel Research, 118: 156-168, 2016. https://doi.org/10.1016/j.jcsr.2015.11.008.
[6] Ban H. and Bradford M.A., “Elastoplastic cross-sectional behavior of composite beams with high-strength steel: analytical modeling”, Journal of Structural Engineering, 141(10): 04014236, 2015. https://doi.org/10.1061/(ASCE)ST.1943-541X.0001208.
[7] Nguyen C.-L. and Lee C.-K., “Experimental study of flexural behaviour of high strength steel (HSS) - Engineered Cementitious Composites (ECC) composite beam with profiled steel sheeting”, ce/papers, 4: 781-786, 2021. https://doi.org/10.1002/cepa.1361.
[8] Li V. C., Mishra D. K., Naaman A. E., Wight J. K., LaFave J. M., Wu H. C., and Inada Y., “On the shear behavior of engineered cementitious composites”, Advanced Cement Based Materials, 1(3), 142-149, 1994. DOI: https://doi.org/10.1016/1065-7355(94)90045-0.
[9] Li V. C., “On engineered cementitious composites (ECC) a review of the material and its applications”, Journal of Advanced Concrete Technology, 1(3), 215-230, 2003.
[10] Li V. C., “Tailoring ECC for special attributes: A review”, International Journal of Concrete Structures and Materials, 6(3), 135-144, 2012.
[11] Li V. C., Engineered cementitious composites (ECC): bendable concrete for sustainable and resilient infrastructure. Springer, 2019.
[12] Yu K., Wang Y., Yu J., and Xu S., “A strain-hardening cementitious composites with the tensile capacity up to 8%”, Construction and Building Materials, 137, 410-419, 2017. DOI: https://doi.org/10.1016/j.conbuildmat.2017.01.060.
[13] Yu, K., Ding, Y., Liu, J. and Bai, Y. “Energy dissipation characteristics of all-grade polyethylene fiber-reinforced engineered cementitious composites (PE-ECC)”, Cement and Concrete Composites, 106, 103459, 2020.
[14] Yu, K., Li, L., Yu, J., Wang, Y., Ye, J., and Xu, Q., “Direct tensile properties of engineered cementitious composites: A review”, Construction and Building Materials, 165, 346-362, 2018.DOI: https://doi.org/10.1016/j.conbuildmat.2017.12.124.
[15] Meng, D., Lee, C. K., and Zhang, Y. X., “Flexural and shear behaviours of plain and reinforced polyvinyl alcohol-engineered cementitious composite beams”, Engineering Structures, 151, 261-272, 2017. DOI: https://doi.org/10.1016/j.engstruct.2017.08.036
[16] Yu, K. Q., Dai, J. G., Lu, Z. D., and Poon, C. S., “Rate-dependent tensile properties of ultra-high performance engineered cementitious composites (UHP-ECC)”, Cement and Concrete Composites, 93, 218-234, 2018.
[17] Yu, K., Zhu, H., Hou, M., and Li, V. C., “Self-healing of PE-fiber reinforced lightweight high-strength engineered cementitious composite”, Cement and Concrete Composites, 123, 104209, 2021.
[18] Nguyen C. L. and Lee C.K. “Flexural behaviours of Engineered Cementitious Composites - High strength steel composite beams”. Engineering Structures, 2021, 249. https://doi.org/10.1016/j.engstruct.2021.113324
[19] Nguyen C.-L., and Lee C.-K., “Development of analytical models for predicting the flexural behaviour of engineered cementitious composites-high strength steel composite beams”, Advanced Steel Construction, 2023, 19(3): 197-208
[20] Mai A D, Lee C K, and Nguyen C L., “Flexural performance of composite beam with high-strength steel girder and ECC slab: A comprehensive parametric study”, Res. Eng. Struct. Mater; 11(3): 1345-1367, 2025.
[21] Zhang, Tao, Danying Gao, and Chengcheng Xue. "Flexural strength prediction of concrete beams reinforced with hybrid FRP and steel bars based on machine learning", Structures. Vol. 65. Elsevier, 2024.
[22] Naser MZ. “An engineer’s guide to explainable artificial intelligence and interpretable machine learning: navigating causality, forced goodness, and the false perception of inference”, Autom Constr;129:103821, 2021.
[23] Raza Ali, El Ouni Mohamed Hechmi, Baili Jamel, and uz Zaman Khan Qaiser, “Datadriven analysis on axial strength of GFRP-NSC columns based on practical artificial neural network Tool”, Compos Struct; 291:115598, 2022.
[24] Karimipour Arash, Mohebbi Najm Abad Javad, and Fasihihour Nazanin, “Predicting the load-carrying capacity of GFRP-reinforced concrete columns using ANN and evolutionary strategy”, Compos Struct; 275:114470, 2021
[25] Naderpour H, Poursaeidi O, and Ahmadi M, “Shear resistance prediction of concrete beams reinforced by FRP bars using artificial neural networks”, Measurement, 126:299–308, 2018.
[26] Nguyen Hoan D, Zhang Qianhui, Choi Eunsoo, and Duan Wenhui, “An improved deflection model for FRP RC beams using an artificial intelligence-based approach”, Eng Struct ;219:110793, 2020.
[27] Golafshani EM, Rahai A, and Sebt MH, “Artificial neural network and genetic programming for predicting the bond strength of GFRP bars in concrete”, Mater Struct;48(5):1581–602, 2015.
[28] Sharifi Y., and Tohidi S., “Ultimate capacity assessment of web plate beams with pitting corrosion subjected to patch loading by artificial neural networks”, Advanced Steel Construction, 10(3), 325-350, 2014.
[29] Nguyen M. H., and Phan H. N., “A Bayesian-Optimized Neural Network Model For Shear Capacity Of A Perfobond Strip Connector In Various Types Of Composite Structures”, Advanced Steel Construction, 20(4), 376-384, 2024.
[30] Ge W., Zhang F., Wang Y., Ashour A., Luo L., Qiu L., and Cao D., “Machine learning predictions for bending capacity of ECC-concrete composite beams hybrid reinforced with steel and FRP bars”, Case Studies in Construction Materials, 21, e03670, 2024.
[31] Kumar A., Arora H. C., and Nehdi M. L., “Data-driven framework with graphical user interface for predicting flexural behavior of FRCM strengthened RC beams”, In Structures (Vol. 71, p. 107917). Elsevier, 2025.
[32] Ahmad M. S., Adnan S. M., Zaidi S., and Bhargava P., “A novel support vector regression (SVR) model for the prediction of splice strength of the unconfined beam specimens”, Construction and building materials, 248, 118475, 2020.
[33] Yuvaraj P., Murthy A. R., Iyer N. R., Sekar S. K., and Samui P., “Support vector regression based models to predict fracture characteristics of high strength and ultra high strength concrete beams”, Engineering fracture mechanics, 98, 29-43, 2013. .
[34] Pal M., and Deswal S, “Support vector regression based shear strength modelling of deep beams”, Computers & Structures, 89(13-14), 1430-1439, 2011.
[35] Taffese W. Z., and Zhu Y., “Explainable machine learning for predicting flexural capacity of reinforced UHPC beams”, Engineering Structures, 343, 121188, 2025.
[36] Ye M., Li L., Yoo D. Y., Li H., Zhou C., and Shao X., “Prediction of shear strength in UHPC beams using machine learning-based models and SHAP interpretation”, Construction and Building Materials, 408, 133752, 2023.
[37] de Oliveira V. M., de Carvalho A. S., Rossi A., Hosseinpour M., Sharifi Y., and Martins C. H., “Data-driven design approach for the lateral-distortional buckling in steel-concrete composite cellular beams using machine learning models”. In Structures (Vol. 61, p. 106018). Elsevier, 2024, March.
[38] Zhang Y., Chu Y., Zou J., and Yu C., “Machine learning prediction of steel–concrete composite beam temperatures during hot asphalt paving”, Measurement, 242, 116257, 2025.
[39] Almustafa M. K., and Nehdi M. L., “Machine learning model for predicting structural response of RC slabs exposed to blast loading”, Engineering Structures, 221, 111109, 2020.
[40] Haque M. A., Chen B., Kashem A., Qureshi T., and Ahmed A. A. M., “Hybrid intelligence models for compressive strength prediction of MPC composites and parametric analysis with SHAP algorithm”, Materials Today Communications, 35, 105547, 2023.
[41] Lundberg S. M., and Lee S. I., “A unified approach to interpreting model predictions”, Advances in neural information processing systems, 30, 2017.
[42] Ekanayake I. U., Meddage D. P. P., and Rathnayake U., “A novel approach to explain the black-box nature of machine learning in compressive strength predictions of concrete using Shapley additive explanations (SHAP)”, Case Studies in Construction Materials, 16, e01059, 2022.