Shear capacity estimation of reinforced concrete deep beams using machine learning techniques

Quadri, A.; Soretire, H.; Babalola, H.; Kupolati, W.; Ackerman, C.; Snyman, J.; Ndambuk, J.

Abstract: Conventionally, the deep beam shear strength is analyzed with codes (mechanics and empirical models). The purpose of this investigation is to provide an alternative way of accurately estimating the shear capacity of Reinforced Concrete Deep Beams (RCDBs), including those with and without shear reinforcements (WOR and WWR), by adopting machine learning models. Four machine learning algorithms: k-Nearest Neighbor (kNN), Random Forest, M5Rules, and Sequential Minimal Optimization for Regression (SMOReg), were considered, and the selection was based on their performance in previous related studies. A database of 733 samples for WWR and 378 samples for WOR was compiled, utilizing 14 and 8 input features, respectively, in each case. WEKA, an open-source software suite, was used in preprocessing the data and also tuning the hyperparameters. SMOReg beat other models for WOR with an R² value of 0.9607, while Random Forest did best for WWR with an R² value of 0.9667 in the testing sets. The shear strengths predicted by the machine learning models were compared to four traditional standard codes. The results show that the machine learning models beat conventional methods by a large margin, while also being consistent with earlier models generated using machine learning. This demonstrates the model's prediction accuracy and robustness.

How to cite this paper

        APA: Quadri, A., Soretire, H., Babalola, H., Kupolati, W., Ackerman, C., Snyman, J & Ndambuk, J. (2026). Shear capacity estimation of reinforced concrete deep beams using machine learning techniques. Engineering Solid Mechanics, 14(1), 53-66.
    

        Chicago/Turabian: Quadri, A., Soretire, H., Babalola, H., Kupolati, W., Ackerman, C., Snyman, J & Ndambuk, J. 2026. "Shear capacity estimation of reinforced concrete deep beams using machine learning techniques." Engineering Solid Mechanics 14, no. 1 (2026): 53-66.
    

        AMA: Quadri, A., Soretire, H., Babalola, H., Kupolati, W., Ackerman, C., Snyman, J & Ndambuk, J. Shear capacity estimation of reinforced concrete deep beams using machine learning techniques. Engineering Solid Mechanics. 2026;14(1):53-66.
    

References

Aksu, G., & Doğan, N. (2019). Veri Madenciliğinde Kullanılan Güncel Bir Analiz Programı: WEKA. Eğitimde ve Psikolojide Ölçme ve Değerlendirme Dergisi, 10(1), 80–95. https://doi.org/10.21031/epod.399832
Arabzadeh, A., Hizaji, R., & Yang, T. Y. (2020). Experimentally studying and development of curved STM to predict the load capacity and failure mode of fixed-ended RC deep beams. Structures, 23, 289–303. https://doi.org/10.1016/j.istruc.2019.09.011
Bui, X.-N., Moayedi, H., & Rashid, A. S. A. (2020). Developing a predictive method based on optimized M5Rules–GA predicting heating load of an energy-efficient building system. Engineering with Computers, 36(3), 931–940. https://doi.org/10.1007/s00366-019-00739-8
Duggal, H., & Singh, P. (2012). Comparative Study of the Performance of M5-Rules Algorithm with Different Algorithms. 2012. https://doi.org/10.4236/jsea.2012.54032
Dzięcioł, J., & Sas, W. (2024). Estimation of the coefficient of permeability as an example of the application of the Random Forest algorithm in Civil Engineering. Archives of Civil Engineering; 2024; Vol. 70; No 2; 119-134. https://journals.pan.pl/dlibra/publication/149854/edition/131700
Feng, D.-. C., Wang, W.-. J., Mangalathu, S., Hu, G., & Wu, T. (2021a). Implementing ensemble learning methods to predict the shear strength of RC deep beams with/without web reinforcements. Eng. Struct., 235. https://doi.org/10.1016/j.engstruct.2021.111979
Ghiasi, A., Ng, C.-T., & Sheikh, A. H. (2022). Damage detection of in-service steel railway bridges using a fine k-nearest neighbor machine learning classifier. Structures, 45, 1920–1935. https://doi.org/10.1016/j.istruc.2022.10.019
Guo, B., Lin, X., Wu, Y., & Zhang, L. (2023). Machine learning-driven evaluation and optimisation of compression yielded FRP-reinforced concrete beam with T section. Engineering Structures, 275, 115240. https://doi.org/10.1016/j.engstruct.2022.115240
Huang, S., Huang, M., & Lyu, Y. (2020). An Improved KNN‐Based Slope Stability Prediction Model. https://doi.org/10.1155/2020/8894109
Le, T.-T. (2022). Practical machine learning-based prediction model for axial capacity of square CFST columns. Mechanics of Advanced Materials and Structures, 29(12), 1782–1797. https://doi.org/10.1080/15376494.2020.1839608
Liang, S., Shen, Y., Gao, X., Cai, Y., & Fei, Z. (2023). Symbolic machine learning improved MCFT model for punching shear resistance of FRP-reinforced concrete slabs. J. Build. Eng., 69. https://doi.org/10.1016/j.jobe.2023.106257
Liu, C., Xu, D., & Duanmu, X. (2024). Analysis of shear strength influencing factors in reinforced concrete deep beams: A modified calculating model. Journal of Building Engineering, 95, 110243. https://doi.org/10.1016/j.jobe.2024.110243
Liu, J., Li, S., Guo, J., Xue, S., Chen, S., Wang, L., Zhou, Y., & Luo, T. X. (2023). Machine learning (ML) based models for predicting the ultimate bending moment resistance of high strength steel welded I-section beam under bending. Thin-Walled Structures, 191, 111051. https://doi.org/10.1016/j.tws.2023.111051
Ma, C., Wang, S., Zhao, J., Xiao, X., Xie, C., & Feng, X. (2023). Prediction of shear strength of RC deep beams based on interpretable machine learning. Constr. Build. Mater., 387. https://doi.org/10.1016/j.conbuildmat.2023.131640
Medjdoubi, A. (2024). Visual recognition for IoT-based smart city surveillance [Thesis]. http://dspace.univ-mascara.dz:8080/jspui/handle/123456789/1057
Megahed, K. (2024a). Prediction and reliability analysis of shear strength of RC deep beams. Scientific Reports, 14(1), 14590. https://doi.org/10.1038/s41598-024-64386-w
Megahed, K. (2024b). STM-based symbolic regression for strength prediction of RC deep beams and corbels. Scientific Reports, 14(1), 25066. https://doi.org/10.1038/s41598-024-74803-9
Nguyen, T.-A., Ly, H.-B., Mai, H.-V. T., & Tran, V. Q. (2021). On the Training Algorithms for Artificial Neural Network in Predicting the Shear Strength of Deep Beams. Complexity, 2021, 5548988. https://doi.org/10.1155/2021/5548988
Ogunsola, N. O., Quadri, A. I., & Bankole, A. O. (2025). Comparative Modeling of Compressive and Tensile Strengths in Thermally Exposed Pozzolanic Mortar Using ANN-LM, ANFIS, and MVRA with Closed-Form Equations. Iranian Journal of Science and Technology, Transactions of Civil Engineering. https://doi.org/10.1007/s40996-025-01960-w
Prayogo, D., Cheng, M.-Y., Wu, Y.-W., & Tran, D.-H. (2019). Combining machine learning models via adaptive ensemble weighting for prediction of shear capacity of reinforced-concrete deep beams. Engineering with Computers. https://doi.org/10.1007/s00366-019-00753-w
Quadri, A. I. (2023). Shear response of reinforced concrete deep beams with and without web opening. Innovative Infrastructure Solutions, 8(12), 316. https://doi.org/10.1007/s41062-023-01286-4
Quadri, A. I., Kupolati, W. K., Ackerman, C., Snyman, J., & Ndambuki, J. M. (2025). Assessment of shear capacity of reinforced concrete slender beams using tire steel fiber. Innovative Infrastructure Solutions, 10(3), 92. https://doi.org/10.1007/s41062-025-01879-1
Rehman, I., & Soomro, T. R. (2019). Data Mining for Forecasting OGDCL Share Prices Using WEKA. 2019 13th International Conference on Mathematics, Actuarial Science, Computer Science and Statistics (MACS), 1–7. https://doi.org/10.1109/MACS48846.2019.9024780
Russo, G., Pauletta, M., & Venir, R. (2005). Reinforced concrete deep beams-shear strength model and design formula. ACI Struct. J., 102. https://doi.org/10.14359/14414
Saad, S., Mohammed, I., & Hasmat, M. (2017). Selection of most relevant input parameters using WEKA for artificial neural network based concrete compressive strength prediction model. https://ieeexplore.ieee.org/abstract/document/8077368
Saini, R., & Ghosh, S. K. (2018). CROP CLASSIFICATION ON SINGLE DATE SENTINEL-2 IMAGERY USING RANDOM FOREST AND SUPPOR VECTOR MACHINE. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII–5, 683–688. https://doi.org/10.5194/isprs-archives-XLII-5-683-2018
Sancheti, G., Patil, H., Sharma, S., & Goswami, S. (2021). Analysis of Design for One-Way Reinforced Concrete Slabs using Machine Learning Models. IOP Conference Series: Materials Science and Engineering, 1099(1), 012052. https://doi.org/10.1088/1757-899X/1099/1/012052
Steinbach, M., & Tan, P.-N. (2009). kNN: K-Nearest Neighbors. In The Top Ten Algorithms in Data Mining. Chapman and Hall/CRC.
Suman, & Naib, B. B. (2013, July 1). Soil Classification and Fertilizer Recommendation using WEKA. | EBSCOhost.https://openurl.ebsco.com/contentitem/gcd:89747478?sid=ebsco:plink:crawler&id=ebsco:gcd:89747478
Yaseen, S. A., Aziz, O. Q., & Abu Bakar, B. H. (2017). Prediction of Shear Strength of Ultra High Performance Reinforced Concrete Deep Beams without Stirrups by Neural Network. Eurasian Journal of Science & Engineering, 3(1), 23. https://doi.org/10.23918/eajse.v3i1sip142
Zhang, G., Ali, Z. H., Aldlemy, M. S., Mussa, M. H., Salih, S. Q., & Hameed, M. M. (2022). Reinforced concrete deep beam shear strength capacity modelling using an integrative bio-inspired algorithm with an artificial intelligence model. Springer, 38, 15--28. https://doi.org/10.1007/s00366-020-01137-1
Zhang, S., Li, X., Zong, M., Zhu, X., & Cheng, D. (2017). Learning k for kNN Classification. ACM Trans. Intell. Syst. Technol., 8(3), 43:1-43:19. https://doi.org/10.1145/2990508

⭐ Highly Cited Articles

Journals

ESM Volumes

🔑 Keywords

✍️ Authors

🌍 Countries