This study presents a machine learning framework for predicting the axial compressive strength of circular concrete-filled steel tube (CFST) columns subjected to concentric and eccentrically applied axial loads. A harmonized database of 1287 test specimens was compiled, encompassing diverse material strengths, geometric configurations, and eccentricity levels. Among the trained models, the CatBoost (CatB) algorithm exhibited the highest predictive performance. A 300-run Monte Carlo simulation yielded a mean R² of 0.966 (Min: 0.804; Max: 0.996), with a mean RMSE of 588.8 kN and MAPE of 8.36%, demonstrating accuracy and robustness across repeated randomized splits. Comparative benchmarking against current design equations revealed that CatBoost substantially reduced prediction scatter, improving the mean ratio and reducing the COV from 70–75% (ACI/AIJ/Wang) to 5.43%, while maintaining a nearly unbiased mean prediction ratio of 1.00. In addition, inverse prediction models based on CatBoost achieved test-set R² values of 0.908 for compressive strength and 0.945, 0.900, and 0.816 for key design parameters (D, t, L), indicating promising capability for supporting preliminary sizing and parameter selection. The outcomes of this study highlight the potential of data-driven modelling to complement existing design provisions and assist engineers in early-stage decision-making for axially loaded circular CFST columns.

This study investigates the applicability of machine learning models for predicting the shear strength of rectangular reinforced concrete (RC) walls subjected to axial load. A comprehensive experimental database consisting of 456 wall specimens was compiled, including geometric parameters, reinforcement ratios, material properties, and axial load effects. Four supervised learning models Decision Tree (DT), Random Forest (RF), CatBoost, and Extreme Gradient Boosting (XGBoost) were first evaluated using default hyperparameters. Although RF achieved the best testing performance (R² = 0.910, RMSE = 137.40 kN), XGBoost showed greater consistency between validation and testing results (R² = 0.884–0.900; RMSE = 136.03–141.31 kN). Considering both predictive accuracy and generalization stability, XGBoost was selected for further optimization using Gaussian Process (GP)-based Bayesian optimization. The optimized model achieved improved accuracy (R² = 0.914, RMSE = 131.11 kN), indicating enhanced generalization capability. Comparison with conventional design provisions such as ACI 318-19 shows that the machine learning model provides lower mean error and reduced dispersion, particularly for walls with large geometric aspect ratios. SHAP analysis reveals that geometric parameters (wall length lw, height hw, and thickness tw), reinforcement ratios (horizontal ρh and longitudinal ρL), and axial load P are dominant factors governing shear strength. Notably, the XGBoost model captures the combined influence of longitudinal and transverse reinforcement, whereas ACI 318-19 primarily considers horizontal reinforcement through the shear component Vs and does not explicitly account for longitudinal reinforcement contribution. The results highlight the superiority of machine learning in modeling complex nonlinear interactions among design parameters and demonstrate the strong potential of GP-optimized XGBoost for structural design and assessment of RC walls.

Predicting the brittle response of reinforced concrete (RC) frames remains an active research problem. Different industries and research tools predict brittle responses with varying accuracy and analysis times, due to their inherent limitations. Also, the sophisticated Finite Element Tools, i.e., (ABAQUS, ANSYS, and DIANA), require costly computational costs and deep knowledge of defining material compared to the industry tool (SAP 2000). An Artificial Neural Network Finite Element Analysis (ANN-FEA) method is proposed to address this issue without incurring additional computational costs. This ANN-FEA method is designed for the analysis and design of both new and existing RC structures, such as Double-story single-bay (DSSB) Frames. For this study, one experimental control model (ECM) frame with three additional finite element models (FEM) is examined. The additional FEM models have: (i) Half Diameter of Stirrups in the Beam (HDB), (ii) Half Diameter of Stirrups in both Beam and Columns (HDBC), and (iii) Double Spacing of Stirrups in Beam and Columns (DSBC), as compared to the experimental model. This assessment focused on measuring the influence of critical design parameters, such as transverse reinforcement ratio (ρt), on the load-carrying capacity of DSSB, especially in a brittle manner. The findings confirmed that all the new FEA models and ANN-FEA exhibited less lateral load than CM, with reductions of 4.45% for HDB, 13.8% for HDBC, and 5.2% for DSBC.