Evaluating the Performance of Ensemble Machine Learning Algorithms Over Traditional Machine Learning Algorithms for Predicting Fire Resistance in FRP Strengthened Concrete Beams

Helani Kumarawadu; Pasindu Weerasinghe; Jude Shalitha  Perera

doi:10.56748/ejse.24661

Authors

Helani Kumarawadu University of Moratuwa https://orcid.org/0009-0007-0229-6297
Pasindu Weerasinghe University of Moratuwa https://orcid.org/0000-0002-7288-690X
Jude Shalitha Perera University of Melbourne https://orcid.org/0000-0003-1432-8851

DOI:

https://doi.org/10.56748/ejse.24661

Keywords:

Ensemble Machine Learning, Fire Resistance, FRP Strengthened Concrete Beams, Machine Learning

Abstract

In recent years, fiber-reinforced polymers (FRP) have emerged as a highly effective solution for strengthening reinforced concrete (RC) structures. However, accurately assessing the fire resistance of FRP-strengthened members remains a significant challenge due to the limited guidance available in current building codes, often leading to conservative and cost-intensive evaluations. Experimental testing and numerical analysis required for such assessments are resource-demanding, highlighting the need for more efficient methods. This study investigates the application of machine learning (ML) techniques to predict the fire resistance of FRP-strengthened RC beams. Twelve ML models, including eight ensemble methods and four traditional approaches, were employed. The models were trained using a comprehensive dataset comprising over 21,000 data points obtained from numerical simulations and experimental tests. The dataset captured variations in geometric configurations, insulation strategies, loading conditions, and material properties. To enhance predictive accuracy, Bayesian optimization and k-fold cross-validation were applied for model tuning, while the Shapley Additive Explanations (SHAP) method was utilized to assess the relative importance of features influencing fire resistance. Among the models tested, Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Light Gradient Boosting (LGBoost), and Gradient Boosting (GRB) demonstrated superior performance, achieving accuracy rates exceeding 92%. Key factors identified as significantly affecting fire resistance included loading ratio, area of tensile reinforcement, insulation depth, concrete cover thickness, and FRP area. The findings underscore the potential of ensemble ML techniques over traditional methods for accurately predicting the fire resistance of FRP-strengthened RC beams, offering critical insights for optimizing design practices and enhancing structural fire safety.

Downloads

Download data is not yet available.

References

Abuodeh, O. R., Abdalla, J. A., & Hawileh, R. A. (2020). Prediction of shear strength and behavior of RC beams strengthened with externally bonded FRP sheets using machine learning techniques. Composite Structures, 234, 111698. DOI: https://doi.org/10.1016/j.compstruct.2019.111698

Ahmed, A., & Kodur, V. (2011). The experimental behavior of FRP-strengthened RC beams subjected to design fire exposure. Engineering Structures, 33(7), 2201–2211. DOI: https://doi.org/10.1016/j.engstruct.2011.03.010

Alabdullh, A. A., Biswas, R., Gudainiyan, J., Khan, K., Bujbarah, A. H., Alabdulwahab, Q. A., Amin, M. N., & Iqbal, M. (2022). Hybrid Ensemble Model for Predicting the Strength of FRP Laminates Bonded to the Concrete. Polymers, 14(17), 3505. DOI: https://doi.org/10.3390/polym14173505

American Society for Testing and Materials. (n.d.). ASTM E119: Standard Test Methods for Fire Tests of Building Construction and Materials. www.aslm.org

Amin, M. N., Iqbal, M., Khan, K., Qadir, M. G., Shalabi, F. I., & Jamal, A. (2022). Ensemble Tree-Based Approach towards Flexural Strength Prediction of FRP Reinforced Concrete Beams. Polymers, 14(7), 1303. DOI: https://doi.org/10.3390/polym14071303

Baduge, S. K., Thilakarathna, S., Perera, J. S., Arashpour, M., Sharafi, P., Teodosio, B., Shringi, A., & Mendis, P. (2022). Artificial intelligence and smart vision for building and construction 4.0: Machine and deep learning methods and applications. In Automation in Construction (Vol. 141). Elsevier B.V. DOI: https://doi.org/10.1016/j.autcon.2022.104440

Baduge, S. K., Thilakarathna, S., Perera, J. S., Ruwanpathirana, G. P., Doyle, L., Duckett, M., Lee, J., Saenda, J., & Mendis, P. (2023). Assessment of crack severity of asphalt pavements using deep learning algorithms and geospatial system. Construction and Building Materials, 401, 132684. DOI: https://doi.org/10.1016/j.conbuildmat.2023.132684

Bhatt, P. P., Kodur, V. K. R., & Naser, M. Z. (2024). Dataset on fire resistance analysis of FRP-strengthened concrete beams. Data in Brief, 52, 110031. DOI: https://doi.org/10.1016/j.dib.2024.110031

Bhatt, P. P., & Sharma, N. (2021). Deep Neural Network to Predict Fire Resistance of FRP-Strengthened Beams. SP-350: The Concrete Industry in the Era of Artificial Intelligence.

Blontrock H, T. L. V. P. (2000). Fire tests on concrete beams strengthened with fibre composite laminates. In: Third Ph.D. symposium.

Chen, S.-Z., Feng, D.-C., & Han, W.-S. (2020). Comparative Study of Damage Detection Methods Based on Long-Gauge FBG for Highway Bridges. Sensors, 20(13), 3623. DOI: https://doi.org/10.3390/s20133623

Chen, S.-Z., Feng, D.-C., Han, W.-S., & Wu, G. (2021). Development of data-driven prediction model for CFRP-steel bond strength by implementing ensemble learning algorithms. Construction and Building Materials, 303, 124470. DOI: https://doi.org/10.1016/j.conbuildmat.2021.124470

Deuring, M. (1994). Brandversuche an Nachtraglich Verstarkten Tragern aus Beton," Research Report EMPA No. 148,795, Swiss Federal Laboratories for Materials Testing and Research (EMPA), Dubendorf, Switzerland.

El-Mahdy, O., Hamdy, G., & Abdullah, M. (2018). NUMERICAL INVESTIGATION OF THE PERFORMANCE OF INSULATED FRP-STRENGTHENED REINFORCED CONCRETE BEAMS IN FIRE. Stavební Obzor - Civil Engineering Journal, 27(4). DOI: https://doi.org/10.14311/CEJ.2018.04.0046

Gates, T. S. (1991). Effects of elevated temperature on the viscoplastic modeling of graphite/polymeric composites.

Gudonis, E., Timinskas, E., Gribniak, V., Kaklauskas, G., Arnautov, A. K., & Tamulėnas, V. (2014). FRP REINFORCEMENT FOR CONCRETE STRUCTURES: STATE-OF-THE-ART REVIEW OF APPLICATION AND DESIGN. Engineering Structures and Technologies, 5(4), 147–158. DOI: https://doi.org/10.3846/2029882X.2014.889274

Hazan, E., Klivans, A., & Yuan, Y. (2017). Hyperparameter Optimization: A Spectral Approach. http://arxiv.org/abs/1706.00764

Ilievski, I., Akhtar, T., Feng, J., & Shoemaker, C. A. (2016). Efficient Hyperparameter Optimization of Deep Learning Algorithms Using Deterministic RBF Surrogates. DOI: https://doi.org/10.1609/aaai.v31i1.10647

Kim, B., Lee, D.-E., Hu, G., Natarajan, Y., Preethaa, S., & Rathinakumar, A. P. (2022). Ensemble Machine Learning-Based Approach for Predicting of FRP–Concrete Interfacial Bonding. Mathematics, 10(2), 231. DOI: https://doi.org/10.3390/math10020231

Kodur, V. K. R., & Ahmed, A. (2010). Numerical Model for Tracing the Response of FRP-Strengthened RC Beams Exposed to Fire. Journal of Composites for Construction, 14(6), 730–742. DOI: https://doi.org/10.1061/(ASCE)CC.1943-5614.0000129

Kodur, V. K. R. ; B. D. (1996). Fire resistance of FRP reinforced concrete slabs.

Kodur, V. K. R., Baingo, D., & Baingo, D. (1996). I*I Council Canada de recherches Canada Fire Resistance of FRP Reinforced Concrete Slabs FIRE RESISTANCE OF FRP REINFORCED CONCRETE SLABS.

Kodur, V. K. R., & Yu, B. (2016). Rational Approach for Evaluating Fire Resistance of FRP-Strengthened Concrete Beams. Journal of Composites for Construction, 20(6). DOI: https://doi.org/10.1061/(ASCE)CC.1943-5614.0000697

Kumarawadu, H. R., Weerasinghe, T. G. P. L., & Perera, J. S. (2024). Using Machine Learning to Predict Fire Resistance of FRP Strengthened Concrete Beams. 2024 Moratuwa Engineering Research Conference (MERCon), 121–126. DOI: https://doi.org/10.1109/MERCon63886.2024.10688449

Mashrei, M. A., Seracino, R., & Rahman, M. S. (2013). Application of artificial neural networks to predict the bond strength of FRP-to-concrete joints. Construction and Building Materials, 40, 812–821. DOI: https://doi.org/10.1016/j.conbuildmat.2012.11.109

Milad, A., Hussein, S. H., Khekan, A. R., Rashid, M., Al-Msari, H., & Tran, T. H. (2022). Development of ensemble machine learning approaches for designing fiber-reinforced polymer composite strain prediction model. Engineering with Computers, 38(4), 3625–3637. DOI: https://doi.org/10.1007/s00366-021-01398-4

Naser, M., Abu-Lebdeh, G., & Hawileh, R. (2012). Analysis of RC T-beams strengthened with CFRP plates under fire loading using ANN. Construction and Building Materials, 37, 301–309. DOI: https://doi.org/10.1016/j.conbuildmat.2012.07.001

Naser, M. Z., Kodur, V., Thai, H.-T., Hawileh, R., Abdalla, J., & Degtyarev, V. V. (2021). StructuresNet and FireNet: Benchmarking databases and machine learning algorithms in structural and fire engineering domains. Journal of Building Engineering, 44, 102977. DOI: https://doi.org/10.1016/j.jobe.2021.102977

Silverman, E. M. (1983). Elevated temperature testing for comparison of glass/resin composites. Polymer Composites, 4(4), 214–218. DOI: https://doi.org/10.1002/pc.750040404

Uematsu, Y., Kitamura, T., & Ohtani, R. (1995). Delamination behavior of a carbon-fiber-reinforced thermoplastic polymer at high temperatures. Composites Science and Technology, 53(3), 333–341. DOI: https://doi.org/10.1016/0266-3538(95)00005-4

Williams B, K. V. G. M. B. L. (2008). Fire Endurance of Fiber-Reinforced Polymer Strengthened Concrete T-Beams. ACI Structural Journal, 105(1). DOI: https://doi.org/10.14359/19069

Yang, L., & Shami, A. (2020). On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing, 415, 295–316. DOI: https://doi.org/10.1016/j.neucom.2020.07.061

Ye, Z., Hsu, S.-C., & Wei, H.-H. (2022). Real-time prediction of structural fire responses: A finite element-based machine-learning approach. Automation in Construction, 136, 104165. DOI: https://doi.org/10.1016/j.autcon.2022.104165