Predicting the Load-Bearing Capacity of Square-Section Pipe-Concrete Columns Using Machine Learning Methods

Introduction. In this paper, we consider the problem of predicting the strength of square-section centrally compressed short concrete-filled tubular columns using machine learning methods. Traditional methods, such as the finite element method and the theoretical-experimental approach involving selection of empirical formulas require significant computational resources and time. At the same time, these methods are not always capable of accounting for complex nonlinear dependencies between the parameters. The key objective is to develop a high-precision model capable of predicting the load-bearing capacity of columns using the major parameters.

Materials and Methods. For the current study, a database was generated containing the results of numerical experiments on calculating the load-bearing capacity of square-section concrete-filled tubular columns in a physically nonlinear formulation. As part of the study, models based on machine learning methods were designed and implemented using the Jupyter Notebook interactive computing platform. The main method is the CatBoost mechanism (Gradient Boosting Regressor). The resulting models were trained by means of nonlinear optimization methods.

Results. The article evaluates the degree of impact of each of the input parameters on the final predictions of the model. The results on the degree of impact for the CatBoost and Random Forrest Regressor (RFR) models are obtained. The quality of the resulting models evaluated using the R² value was 98% for CatBoost and 94% for RFR.

Discussion and Conclusions. The resulting approach has proved to be highly efficient in predicting the load-bearing capacity of concrete-filled tubular columns, providing a balance between the accuracy of the results and computational complexity.

1. Abd‐El‐Nabi E, El‐Helloty A, Summra A. Numerical analysis of reinforced concrete buildings subjected to blast load. Structural Concrete. 2023;24(3):3727–3743. https://doi.org/10.1002/suco.202200726

2. Jianguo Ning, Fanlin Meng, Tianbao Ma, Xiangzhao Xu. Failure analysis of reinforced concrete slab under impact loading using a novel numerical method. International Journal of Impact Engineering. 2020;144:103647. https://doi.org/10.1016/j.ijimpeng.2020.103647

3. Kumar V, Kartik KV, Iqbal MA. Experimental and numerical investigation of reinforced concrete slabs under blast loading. Engineering Structures. 2020;(206):110125. https://doi.org/10.1016/j.engstruct.2019.110125

4. Beskopylny AN, Stel’makh SA, Shcherban’ EM, Mailyan LR, Meskhi B, Razveeva I. et al. Prediction of the Compressive Strength of Vibrocentrifuged Concrete Using Machine Learning Methods. Buildings. 2024;14(377). https://doi.org/10.3390/buildings14020377

5. Beskopylny AN, Stel’makh SA, Shcherban’ EM, Razveeva I, Kozhakin A, Kondratieva TN et al. Prediction of the Properties of Vibro-Centrifuged Variatropic Concrete in Aggressive Environments Using Machine Learning Methods. Buildings 2024;(14):1198. https://doi.org/10.3390/buildings14051198

6. Kondratieva TN, Chepurnenko AS. Prediction of Rheological Parameters of Polymers by Machine Learning Methods. Advanced Engineering Research. 2024;24(1):36–47. https://doi.org/10.23947/2687-1653-2024-24-1-36-47

7. Klemczak B, Żmij A. Insight into thermal stress distribution and required reinforcement reducing early-age cracking in mass foundation slabs. Materials. 2021;14(3):477. https://doi.org/10.3390/ma14030477

8. Talaat M, Yehia E, Mazek SA, Genidi M, Sherif A. Finite element analysis of RC buildings subjected to blast loading. Ain Shams engineering journal. 2022;13(4):101689. https://doi.org/10.1016/j.asej.2021.101689

9. Chepurnenko AS, Kondratieva TN, Deberdeev TR, Akopyan VF, Avakov AA. Prediction of Rheological Parameters of Polymers Using the CatBoost Gradient Boosting Algorithm. Polymer Science, Series D. 2024;17(1):121–128. https://doi.org/10.1134/S199542122370020X

10. Kondratieva TN, Chepurnenko AS, Poliakova KA, Rodionov KA. CatBoost algorithms to predict the load-bearing capacity of centrally compressed short CFST columns of circular cross-section. E3S Web Conf. 2024;583:06009. https://doi.org/10.1051/e3sconf/202458306009

11. Chepurnenko AS, Kondratieva TN, Al-Wali E. Processing of Polymers Stress Relaxation Curves Using Machine Learning Methods. Baghdad Science Journal. 2023;20(6):2488–2488. https://doi.org/10.21123/bsj.2023.8819

12. Althoey F, Amin MN, Khan K, Usman MM, Khan MA. Machine learning based computational approach for crack width detection of self-healing concrete. Case Studies in Construction Materials. 2022;(17):e01610. https://doi.org/10.1016/j.cscm.2022.e0161

13. Koopas RN, Rezaei S, Rauter N, Ostwald R, Lammering R. A spatiotemporal deep learning framework for prediction of crack dynamics in heterogeneous solids: Efficient mapping of concrete microstructures to its fracture properties. Engineering Fracture Mechanics. 2025;(314):110675. https://doi.org/10.1016/j.engfracmech.2024.110675

14. Ali R, Chuah JH, Talip M, Mokhtar N, Shoaib MA. Structural crack detection using deep convolutional neural networks. Automation in Construction. 2022;(133):103989. https://doi.org/10.1016/j.autcon.2021.103989

15. Xinyu Ye, Tao Jin, Li ZX, Chen Pengyu, Ma Si Yuan, Yi Ding, Yihong Ou. Structural crack detection from benchmark data sets using pruned fully convolutional networks. Journal of Structural Engineering. 2021;147(11):04721008. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003140

16. Wang Weidong, Hu Wenbo, Wang Wenjuan, Xu Xinyue, Wang Mengdi, Shi Youyin et al. Automated crack severity level detection and classification for ballastless track slab using deep convolutional neural network. Automation in Construction. 2021;(124):103484. https://doi.org/10.1016/j.autcon.2020.103484

17. Ganesh Kolappan Geetha, Hyun-Jung Yang, Sung-Han Sim. Fast detection of missing thin propagating cracks during deep-learning-based concrete crack/non-crack classification. Sensors. 2023;23(3):1419. https://doi.org/10.3390/s23031419

18. Qijun Chen, Yuxi Xie, Yu Ao, Tiange Li, Guorong Chen, Shaofei Ren et al. A deep neural network inverse solution to recover pre-crash impact data of car collisions. Transportation research part C: emerging technologies. 2021;(126):103009. https://doi.org/10.1016/j.trc.2021.103009

19. Guorong Chen, Tiange Li, Qijun Chen, Shaofei Ren, Chao Wang, Shaofan Li. Application of deep learning neural network to identify collision load conditions based on permanent plastic deformation of shell structures. Computational Mechanics. 2019;(64):435–449. https://doi.org/10.1007/s00466-019-01706-2

20. Viet-Linh Tran, Duc-Kien Thai, Duy-Duan Nguyen. Practical artificial neural network tool for predicting the axial compression capacity of circular concrete-filled steel tube columns with ultra-high-strength concrete. Thin-Walled Structures. 2020;(151):106720. https://doi.org/10.1016/j.tws.2020.106720

21. Cigdem Avci-Karatas. Artificial neural network (ANN) based prediction of ultimate axial load capacity of concrete-filled steel tube columns (CFSTCs). International Journal of Steel Structures. 2022;22(5):1341–1358. https://doi.org/10.1007/s13296-022-00645-8

22. Abidhan Bardhan, Rahul Biswas, Navid Kardani, Mudassir Iqbal, Pijush Samui, Singh M.P. et al. A novel integrated approach of augmented grey wolf optimizer and ANN for estimating axial load carrying-capacity of concrete-filled steel tube columns. Construction and Building Materials. 2022;(337):127454. https://doi.org/10.1016/j.conbuildmat.2022.127454

23. Chepurnenko AS, Yazyev BM, Turina VS, Akopyan VF. Artificial intelligence models for determining the strength of centrally compressed pipe-concrete columns with square cross-section. Magazine of Civil Engineering. 2024;17(6):13008. https://doi.org/10.34910/MCE.130.8

24. Chepurnenko A, Yazyev B, Meskhi B, Beskopylny A, Khashkhozhev K, Chepurnenko V. Simplified 2D finite element model for calculation of the bearing capacity of eccentrically compressed concrete-filled steel tubular columns. Applied Sciences. 2021;11(24):11645. https://doi.org/10.3390/app112411645