Improved machine learning modeling for predicting shear capacity of RC deep beams
Muhammad ARIF, Muhammad LUQMAN, Usama Iftikhar KHAWAJA, Nasrumin ALLAH
Abstract. Pile caps, underground structures, bridges, floor diaphragms, and multistory RC structures use RC deep beams (RCDBs), the fundamental structural components carrying heavy loads. RCDBs have a lower clear span-to-total depth ratio (usually below 4) with distinct structural behaviour like slender beams. Despite being widely used, RCDBs shear design is still challenging due to the applicability and reliability of different design techniques considering the architectural configuration/restriction, code provisions, and other nonlinear variables for optimal geometric design. RCDBs are prone to shear failures, initiating an abrupt, catastrophic collapse that poses severe challenges to public and infrastructural assets. Previous studies developed machine learning (ML) models for forecasting RCDBs’ shear strength, overlooking some influential features and yielding low validation accuracy compared to experimental work. This paper deploys data-driven techniques to forecast the shear strength of RCDBs using more reliable results and accuracy than previous research studies. This study employed two different ML models, including Multi Expression Programming (MEP) and eXtreme Gradient Boosting (XGBoost), to forecast the shear strength of the RCDBs. The established database collected from experimental studies consists of 224 data points with 15 key input features, which determine the shear mechanism of the RCDBs. The dataset was split using the K-fold method into thirty percent data points to test model and remaining seventy percent for training. Shapley explanation identified Top Plate Width (Wtp) from the experimental setup and nominal yield strength of steel (Fyk) from material properties as the most influential factors. The model’s accuracy and applicability were evaluated using several statistical parameters, including correlation coefficients (R2), mean absolute errors (MAE), Root mean square error (RMSE), a-10 Index and Median Absolute Error (MdAE). With R2 of 0.979 for validation, MAE of 30.842, RMSE of 32.848, MdAE of 29.58296 and a-10 Index of 0.4478, respectively, the XGboost model surpasses all the previous studies. Compared to MEP, the developed XGBoost model performed well overall, exhibiting excellent prediction accuracy in testing and validation datasets that forecasted the RCDBs’ shear strength . However, to make the model more practical in the design industry, this study proposes the collection of datasets with different concrete mixture compositions and reinforcement profiles. Moreover, applying Physics Informed Neural Networks (PINNs) on a more extensive and diverse dataset is advisable to decrease overfitting and in situ consideration of RCDBs.
Keywords
RCDBs, Machine Learning, Shear Mechanism, Artificial Intelligence, Shear Strength and Physics Informed Neural Networks (PINNs)
Published online 2/25/2025, 11 pages
Copyright © 2025 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Muhammad ARIF, Muhammad LUQMAN, Usama Iftikhar KHAWAJA, Nasrumin ALLAH, Improved machine learning modeling for predicting shear capacity of RC deep beams, Materials Research Proceedings, Vol. 48, pp 252-262, 2025
DOI: https://doi.org/10.21741/9781644903414-28
The article was published as article 28 of the book Civil and Environmental Engineering for Resilient, Smart and Sustainable Solutions
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] “318-14: Building Code Requirements for Structural Concrete and Commentary,” 318-14: Building Code Requirements for Structural Concrete and Commentary. [Online]. Available: https://www.concrete.org/store/productdetail.aspx?ItemID=318U14
[2] “CEN (European Committee for Standardization). Eurocode 2: Design of concrete structures, Part 1-1: General rules and rules for buildings, NV 1992-1-1,” 2004.
[3] “NZS (Standards New Zealand). Concrete structures standard, NZS3101-2006, Wellington.”
[4] C. Y. Tang and K. H. Tan, “Interactive Mechanical Model for Shear Strength of Deep Beams,” Journal of Structural Engineering, vol. 130, no. 10, pp. 1534–1544, Oct. 2004. https://doi.org/10.1061/(ASCE)0733-9445(2004)130:10(1534)
[5] R. Russo, G., Pauletta, M. & Venir, “Reinforced Concrete Deep Beams- Shear Strength Model and Design Formula,” ACI Struct J, vol. 102, no. 3, 2005. https://doi.org/10.14359/14414.
[6] Y. M. Yun, Y. J. Lee, and S. H. Kim, “Optimum Strut-and-Tie Models for Reinforced Concrete Beams,” KSCE Journal of Civil Engineering, vol. 28, no. 5, pp. 1903–1915, May 2024. https://doi.org/10.1007/s12205-024-0484-y
[7] D. Park, J.W. and Kuchma, “Strut-and-Tie Model Analysis for Strength Prediction of Deep Beams,” ACI Struct J, vol. 104, no. 6, 2007. https://doi.org/10.14359/18947
[8] M. P. Vecchio, F. J. & Collins, “The Modified Compression-Field Theory for Reinforced Concrete Elements Subjected to Shear,” ACI J, vol. 83, no. 22, pp. 219–231, 1986.
[9] K. Le Nguyen, H. Thi Trinh, T. T. Nguyen, and H. D. Nguyen, “Comparative study on the performance of different machine learning techniques to predict the shear strength of RC deep beams: Model selection and industry implications,” Expert Syst Appl, vol. 230, p. 120649, Nov. 2023. https://doi.org/10.1016/j.eswa.2023.120649
[10] M.-Y. Cheng and M.-T. Cao, “Evolutionary multivariate adaptive regression splines for estimating shear strength in reinforced-concrete deep beams,” Eng Appl Artif Intell, vol. 28, pp. 86–96, Feb. 2014. https://doi.org/10.1016/j.engappai.2013.11.001
[11] D.-C. Feng, W.-J. Wang, S. Mangalathu, and E. Taciroglu, “Interpretable XGBoost-SHAP Machine-Learning Model for Shear Strength Prediction of Squat RC Walls,” Journal of Structural Engineering, vol. 147, no. 11, Nov. 2021. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003115
[12] M.-Y. Liu, Z. Li, and H. Zhang, “Probabilistic Shear Strength Prediction for Deep Beams Based on Bayesian-Optimized Data-Driven Approach,” Buildings, vol. 13, no. 10, p. 2471, Sep. 2023. https://doi.org/10.3390/buildings13102471
[13] M. Shahnewaz, A. Rteil, and M. S. Alam, “Shear strength of reinforced concrete deep beams – A review with improved model by genetic algorithm and reliability analysis,” Structures, vol. 23, pp. 494–508, Feb. 2020. https://doi.org/10.1016/j.istruc.2019.09.006
[14] T. Wakjira, M. Ibrahim, B. Sajjad, and U. Ebead, “Shear capacity of reinforced concrete deep beams using genetic algorithm,” IOP Conf Ser Mater Sci Eng, vol. 910, no. 1, p. 012002, Aug. 2020. https://doi.org/10.1088/1757-899X/910/1/012002
[15] K. H. Matamoros, A. B. & Wong, “Design of simply supported deep beams using strut-and-tie models,” ACI Struct. J., vol. 100, no. 6, pp. 704–712, 2003
[16] H. Chen, W.-J. Yi, and H.-J. Hwang, “Cracking strut-and-tie model for shear strength evaluation of reinforced concrete deep beams,” Eng Struct, vol. 163, pp. 396–408, May 2018. https://doi.org/10.1016/j.engstruct.2018.02.077
[17] P. Chetchotisak, J. Teerawong, and S. Yindeesuk, “Modified interactive strut-and-tie modeling of reinforced concrete deep beams and corbels,” Structures, vol. 45, pp. 284–298, Nov. 2022. https://doi.org/10.1016/j.istruc.2022.08.116
[18] S. Fan, Y. Zhang, Y.-X. Ma, and K. H. Tan, “Strut-and-tie and finite element modelling of unsymmetrically-loaded deep beams,” Structures, vol. 36, pp. 805–821, Feb. 2022. https://doi.org/10.1016/j.istruc.2021.12.037
[19] M.Y. Mansour, M. Dicleli, J.Y. Lee, J. Zhang, “Predicting the shear strength of reinforced concrete beams using artificial neural networks,” , Eng. Struct, vol. 26, no. 6, pp. 781–799, 2004.
[20] R. Bashir and A. Ashour, “Neural network modelling for shear strength of concrete members reinforced with FRP bars,” Compos B Eng, vol. 43, no. 8, pp. 3198–3207, Dec. 2012. https://doi.org/10.1016/j.compositesb.2012.04.011
[21] O. R. Abuodeh, J. A. Abdalla, and R. A. Hawileh, “Prediction of shear strength and behavior of RC beams strengthened with externally bonded FRP sheets using machine learning techniques,” Compos Struct, vol. 234, p. 111698, Feb. 2020. https://doi.org/10.1016/j.compstruct.2019.111698
[22] Z. M. Yaseen, M. T. Tran, S. Kim, T. Bakhshpoori, and R. C. Deo, “Shear strength prediction of steel fiber reinforced concrete beam using hybrid intelligence models: A new approach,” Eng Struct, vol. 177, pp. 244–255, Dec. 2018. https://doi.org/10.1016/j.engstruct.2018.09.074
[23] J. Rahman, K. S. Ahmed, N. I. Khan, K. Islam, and S. Mangalathu, “Data-driven shear strength prediction of steel fiber reinforced concrete beams using machine learning approach,” Eng Struct, vol. 233, p. 111743, Apr. 2021. https://doi.org/10.1016/j.engstruct.2020.111743
[24] D.-C. Feng, W.-J. Wang, S. Mangalathu, G. Hu, and T. Wu, “Implementing ensemble learning methods to predict the shear strength of RC deep beams with/without web reinforcements,” Eng Struct, vol. 235, p. 111979, May 2021. https://doi.org/10.1016/j.engstruct.2021.111979
[25] B. Kim. F. Doshi-Velez, “Towards a rigorous science of interpretable machine Learning, arXiv preprint arXiv:1702.08608,” 2017.
[26] D. W. Apley and J. Zhu, “Visualizing the effects of predictor variables in black box supervised learning models,” J R Stat Soc Series B Stat Methodol, vol. 82, no. 4, pp. 1059–1086, Dec. 2020. https://doi.org/10.1111/rssb.12377
[27] A. Goldstein, A. Kapelner, J. Bleich, and E. Pitkin, “Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation,” Journal of Computational and Graphical Statistics, vol. 24, no. 1, pp. 44–65, Jan. 2015. https://doi.org/10.1080/10618600.2014.907095
[28] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning. in Springer Series in Statistics. New York, NY: Springer New York, 2009. doi: 10.1007/978-0-387-84858-7.
[29] M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier,” Feb. 2016, [Online]. Available: http://arxiv.org/abs/1602.04938
[30] S. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” May 2017, [Online]. Available: http://arxiv.org/abs/1705.07874
[31] Y. Gamil, “Machine learning in concrete technology: A review of current researches, trends, and applications,” Front Built Environ, vol. 9, Feb. 2023. https://doi.org/10.3389/fbuil.2023.1145591
[32] S. Mangalathu, S.-H. Hwang, and J.-S. Jeon, “Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach,” Eng Struct, vol. 219, p. 110927, Sep. 2020. https://doi.org/10.1016/j.engstruct.2020.110927
[33] J.-G. Xu, S.-Z. Chen, W.-J. Xu, and Z.-S. Shen, “Concrete-to-concrete interface shear strength prediction based on explainable extreme gradient boosting approach,” Constr Build Mater, vol. 308, p. 125088, Nov. 2021. https://doi.org/10.1016/j.conbuildmat.2021.125088
[34] S. Ismail, K, “Shear behaviour of reinforced concrete deep beams (Doctoral dissertation),” PhD, University of Sheffield, 2016.
[35] P. Schober and L. A. Schwarte, “Correlation coefficients: Appropriate use and interpretation,” Anesth Analg, vol. 126, no. 5, pp. 1763–1768, May 2018. https://doi.org/10.1213/ANE.0000000000002864
[36] M. Khan, M. Ali, T. Najeh, and Y. Gamil, “Computational prediction of workability and mechanical properties of bentonite plastic concrete using multi-expression programming,” Sci Rep, vol. 14, no. 1, p. 6105, Mar. 2024. https://doi.org/10.1038/s41598-024-56088-0
[37] A. Gogineni, I. K. Panday, P. Kumar, and R. K. Paswan, “Predicting compressive strength of concrete with fly ash and admixture using XGBoost: a comparative study of machine learning algorithms,” Asian Journal of Civil Engineering, vol. 25, no. 1, pp. 685–698, Jan. 2024. https://doi.org/10.1007/s42107-023-00804-0
[38] J. Van Der Putten, R. A. Vijayan, G. De Schutter, and K. Van Tittelboom, “Development of 3d printable cementitious composites with the incorporation of polypropylene fibers,” Materials, vol. 14, no. 16, p. 4474, Aug. 2021. https://doi.org/10.3390/ma14164474
