Exploring the Connection Between Ultimate Punching Resistance and Failure Mode of Slab-Column Joints with Machine Learning Algorithms

Huajun  Yan; Zuohua Li; Chao Gong; Dandan Shen

doi:10.56748/ejse.26947

Authors

Huajun Yan School of Civil Engineering, Beijing Jiaotong University, Beijing 100044, China https://orcid.org/0009-0007-5819-2649
Zuohua Li School of Intelligent Civil and Ocean Engineering
Chao Gong Central Research Institute of Building and Construction (Shenzhen) Co.
Dandan Shen SANY Heavy Industry Co.

DOI:

https://doi.org/10.56748/ejse.26947

Keywords:

Slab-column joint, Punching resistance, Failure mode, Metaheuristic optimization, Machine learning, Shapley additive explanations

Abstract

While reinforced concrete (RC) flat slab systems offer an advantage in terms of architectural flexibility and construction efficiency, they remain susceptible to abrupt punching shear failures at the slab-column joints. The current methods for assessing failure modes and punching resistance have considerable limitations, primarily due to an incomplete understanding of how failure mechanisms affect ultimate resistance, resulting in substantial uncertainty in prediction. By utilizing machine learning (ML) algorithms, this study contributes to the persistent problem of determining a quantitative correlation between failure mode progression and punching shear capacity. The method for identifying failure modes is presented using three ML algorithms (DT, RF, and XGBoost) and approach to accurately predict punching resistance, using failure modes as fundamental input variables integrated with two metaheuristic optimization (BFO and GWO) techniques. There has been extensive validation of the BFO-XGBoost model, which has shown superior performance in the classification of failure modes (F1=93.8%, Acc=98.3%) as well as prediction of punching resistance (R² = 0.967, MAE = 0.032MN, and RMSE = 0.049MN). By analyzing the interpretability of models using Shapley additive explanations (SHAP), crucial parameters and their interactions can be identified. It offers unique insights into the mechanism by which failure characteristics are related to ultimate resistance, as well as practical recommendations for mitigating brittle failure risks and enhancing ultimate resistance.

Downloads

Download data is not yet available.

References

Abbas, Y. M., & Alsaif, A. (2025). Hybrid machine learning models and simplified design formulations for predicting punching shear strength in internal SFRC slab-column connections. Construction and Building Materials 478, 141383.

ACI 318-19. (2019). Building Code Requirements for Structure Concrete and Commentary. ACI (American Concrete Institute), Farmington Hills.

Alavi, S. A., Noel, M., Moradi, F., & Layssi, H. (2024). Development of a machine learning model for on-site evaluation of concrete compressive strength by SonReb. Journal of Building Engineering 82, 108328.

Alizamir, M., Kim, S., Ikram, R.M.A., Ahmed, K.O., Heddam, S., & Gholampour, A. (2025). A reliable hybrid extreme learning machine-metaheuristic framework for enhanced strength prediction of 3D-printed fiber-reinforced concrete. Results in Engineering 27, 105715.

Alkhonaini, M. A., Aljaffan, N., Said, Y., Alsamri, J., Nemri, N., Obayya, M., Alzubaidi, A. A., Alsariera, Y. A., & Alnfiai, M. M. (2025). Leveraging osprey optimization algorithm with deep ensemble learning for cybersecurity in CPS environment. Ain Shams Engineering Journal 16(10), 103612.

Babiker, A., Abbas, Y. M., Khan, M. I., & Masmoudi, R. (2025). Enhancing design and behavioral understanding of steel fiber-reinforced concrete flat slabs through a robust machine learning framework. Journal of Building Engineering 111, 113133.

Çiftçioglu, A. Ö. (2025). Exploring failure mechanisms in reinforced concrete slab-column joints: Machine learning and causal analysis. Engineering Failure Analysis 174, 109549.

El-aal, S. A., Deifalla, A., Ghali, N. I., & Naim, A. A. (2025). A deep learning model for the punching shear strength of prestressed concrete slabs. International Journal of Machine Learning and Cybernetics 16(10), 7809-7828.

Erdogan, H. (2024). Strain-Based Grid Beam Model for Predicting Punching Failure of Slab-Column Connections. Arabian Journal for Science and Engineering 49(4), 6007-6026.

Eurocode 2. (2004). Design of concrete structures – Part 1-1: General rules and rules for buildings. European Committee for Standardization, Brussels.

Ewees, M. H., Gabr, A. S. A., & Farrag, M. R. (2024). Effect of tension and compression flexural reinforcement on punching shear strength of reinforced concrete flat slab. Alexandra Engineering Journal 99, 282-302.

Gesund, A., & Kaushik, Y. P. (1970) Analysis of punching shear failures in slabs. In: International Association for Bridge and Structural Engineering, Zurich, Switzerland, pp, 41-60.

Hanoon, D. S., Zareei, S. A., Hassan, R. F., & Zafarani, M. M. (2025). Experimentally investigating hybrid two-way slabs behavior of fiber reinforced concrete slabs casting with different concrete types. Structures 79, 109619.

Khajavi, E., Khanghah, A. R. T., & Khiavi, A. J. (2025). An efficient prediction of punching shear strength in reinforced concrete slabs through boosting methods and metaheuristic algorithms. Structures 74, 108519.

Kumarawadu, H. R., Weerasinghe, T. G. P. L., & Perera, J. S. (2024). Evaluating the Performance of Ensemble Machine Learning Algorithms Over Traditional Machine Learning Algorithms for Predicting Fire Resistance in FRP Strengthened Concrete Beams. Electronic Journal of Structural Engineering 24(3), 46-52.

Laouissi, A., Benkhelladi, A., Boumaaza, M., Karmi, Y., Hani, M., Belaadi, A., Zaitri, R., Alshaikh, I. M. H., Ghernaout, D., & Chetbani, Y. (2025). Deep neural network modeling of the properties of sustainable high-performance concrete from industrial waste materials. Results in Engineering 27, 106818.

Liang, S. X., Shen, Y. X., & Ren, X. D. (2022). Comparative study of influential factors for punching shear resistance/failure of RC slab-column joints using machine-learning models. Structures 45, 1333-1349.

Ma, C. L., Wang, S. X., Zhao, J. P., Xiao, X. F., Xie, C. X., & Feng, X. L. (2023). Prediction of shear strength of RC deep beams based on interpretable machine learning. Construction and Building Materials 387, 131640.

Makoond, N., Setiawan, A., Buitrago, M., & Adam, J. M. (2024). Arresting failure propagation in buildings through collapse isolation. Nature 629, 8012.

Mellios, N., Uz, O., & Spyridis, P. (2023). Data-based modeling of the punching shear capacity of concrete structures. Engineering Structures 275(A), 115195.

Momani, Y., Alawadi, R., Jweihan, Y. S., Tarawneh, A. N., Al-Kheetan, M. J., & Aldiabat, A. (2024). Machine learning-based evaluation of punching shear resistance for steel/ FRP-RC slabs. Ain Shams Engineering Journal 15(5), 102668.

Monserrat-López, A., Bairán, J. M., de la Fuente, A., & Ruiz, M. F. (2024). Resistance partial factor calibration for SFRC elements without shear reinforcement subjected to punching shear according to EN 1992-1-1:2023. Engineering Structures 343(D), 121219.

Muttoni, A. (2008). Punching shear strength of reinforced concrete slabs without transverse reinforcement. ACI Structural Journal 105(4), 440-450.

Parisi, F., Nettis, A., & Uva, G. (2024). Machine learning-aided cloud analysis for seismic fragility assessment of multi-span bridges. Engineering Structures 343(D), 121175.

Pang, B., Wang, F. L., Yang, J., Nyunn, S., & Azim, I. (2021). Performance of slabs in reinforced concrete structures to resist progressive collapse. Structures 33, 4843-4856.

Ramdane, K. E. (1996). Punching shear of high-performance concrete slabs. In: 4th International Symposium on Utilization of High strength/High-performance concrete, Paris, France, pp, 1015-1026.

Ren, X. D., & Liu, X. P. (2025). Probabilistic modeling and mechanism analysis of punching shear failure of RC slab-column joints based on NGBoost model. Engineering Failure Analysis 182(A), 110057.

Ren, X. K., Wang, K., Han, X, F., & Zhang, J. Y. (2025). Identification and Damage Detection in Concrete Structures Based on Genetic Algorithm Combined with Cluster Analysis. Electronic Journal of Structural Engineering 25(3), 30-36.

Wang, Z. B. (2025). Hybrid and Ensemble Machine Learning Approaches for Predicting Axial Load Capacity in Rectangular CFST Stub Columns. Electronic Journal of Structural Engineering 25(3), 37-44.

Wu, Y. Q., & Zhou, Y. S. (2022). Prediction and feature analysis of punching shear strength of two-way reinforced concrete slabs using optimized machine learning algorithm and Shapley additive explanations. Mechanics of Advanced Materials and Structures 30(15), 3086-3096.

Shen, Y. X., Wu, L. F., & Liang, S. X. (2022). Explainable machine learning-based model for failure mode identification of RC flat slabs without transverse reinforcement. Engineering Failure Analysis 141, 106647.

Tusher, T. H., Ahmed, K. S., Pal, A., Shahjalal, M., & Yazdani, N. (2022). ML models for predicting compressive strength of concrete containing various fibers types. Computers and Concrete 35(6), 645-667.

Xiao, R. Y., & Chin, C. S. (2007). Flat slabs at slab-column connection: Nonlinear finite element modelling and punching shear capacity design criterion. Advances in Structural Engineering 10(5), 567-579.

Yan, H. J., & Xie, N. (2024). Optimized Machine Learning Algorithms for Predicting the Punching Shear Resistance of Flat Slabs with Transverse Reinforcement. International Journal of Concrete Structures and Materials, 18(1), 76.

Yan, H. J., Xie, N., & Shen, D. D. (2025). Hybrid optimized algorithms for predicting punching shear strength in flat slabs considering failure modes. KSCE Journal of Civil Engineering 29(5), 100079.

Yang, Y., Chen, Y., Zhang P., & Zhang W. N. (2025). Predictive Modeling of Compressive Strength and Slump in High-Performance Concrete Utilizing Machine Learning. Electronic Journal of Structural Engineering, 25(2), 9-16.

Zheng, C. Y., Liu, Y., Liao, Y., Yu, W. H., & Xiong, F. (2025). Flexural behavior of bolted precast concrete floors at the serviceability limit state. Journal of Building Engineering 111, 113215.

Zou, D., Wu, L., Hao, Y., Xu, L., & Chen, J. (2023). Composition-strength relationship study of ultrahigh performance fiber reinforced concrete (UHPFRC) using an interpretable data-driven approach. Construction and Building Materials 392, 131973.