Interpretable and Uncertainty-Aware Machine Learning for Shear Strength Prediction of FRCM-Strengthened RC Beams

Interpretable machine learning for predicting shear capacity of ultra-high-performance concrete beams

Accurate prediction of shear capacity in reinforced concrete beams is crucial for structural safety assessment. Conventional theoretical methods exhibit significant variability due to the complexity of shear failure mechanisms. This study presents an interpretable machine learning (ML) framework to enhance shear capacity prediction. A comprehensive database of 1175 beam specimens was developed, including normal concrete (NC) and ultra-high-performance concrete (UHPC) beams across three distinct cross-sectional geometries. The ML algorithms–support vector regression, artificial neural network, K-Nearest neighbors, decision tree, random forest, gradient boosting machine, light gradient boosting machine, adaptive boosting, categorical boosting, and extreme gradient boosting (XGBoost)–were optimized using 10-fold cross-validation and random search. The XGBoost algorithm demonstrated superior performance, achieving an R2 of 0.986 on the aggregated data set. Interpretability analysis with Shapley additive explanations identified beam depth (h), shear-span ratio (m), cross-sectional area (Ac) and fibre factor (λf) as critical features, highlighting their individual and interactive contributions. Moreover, a unified ML-based shear strength prediction model was developed that simultaneously captures the shear behaviour of both NC and UHPC beams, incorporating physically meaningful input features derived from the data set, thereby overcoming the limitations of separate empirical formulations. The proposed ML-based model significantly improved the accuracy of shear strength predictions compared to traditional empirical methods, enhancing reliability in structural design.

Explainable ensemble learning framework for bond strength prediction in 3D printed concrete structures

A comprehensive data-driven framework integrating ensemble machine learning models with systematic hyperparameter sensitivity analysis and explainable artificial intelligence techniques is proposed, demonstrating that the XGB model significantly outperforms the other approaches, achieving superior accuracy and robust generalization.

Machine Learning Models for Predicting Mechanical Properties of FRP-Confined Concrete Columns Across Low- to Ultra-High-Strength Concrete

This study presents a comprehensive analysis and predictive modeling framework for the axial compressive strength (fcc) and ultimate axial strain (εcu) of concrete columns confined within fiber-reinforced polymer (FRP) systems. Large databases comprising 3312 samples for fcc and 3319 for εcu were compiled from the literature, encompassing a wide range of key variables, including unconfined concrete strength from 7 MPa to 204 MPa and diverse FRP confinement configurations. The datasets were subjected to extensive statistical and multivariate analyses to identify the primary factors influencing axial behavior and guide feature selection for predictive modeling. Three groups of machine learning (ML) algorithms were subsequently considered: (i) artificial neural networks (including multilayer perceptrons with one and two hidden layers), (ii) kernel-based models (Gaussian process regression and support vector regression), and (iii) tree-based ensemble models (gradient boosting machine, eXtreme gradient boosting, and light gradient boosting machine). Hyperparameters were optimized using grid search cross-validation, while feature importance analyses were performed to quantify the contribution of each input variable. Among all ML models, eXtreme gradient boosting demonstrated superior predictive performance, effectively capturing the nonlinear and multivariate interactions governing confinement effectiveness. Comparative analysis with the top performing regression-based formulations further highlighted the accuracy, robustness, and generalization capability of the eXtreme gradient boosting model. The findings provide a data-driven and interpretable framework for the design and prediction of FRP-confined concrete columns.

Interpretable machine learning with Bayesian optimization for bond strength prediction of steel reinforcement in geopolymer concrete

Accurate estimation of bond strength between steel reinforcement and geopolymer concrete is essential for the reliable design of sustainable reinforced concrete structures. However, the highly nonlinear interactions reduce the applicability and accuracy of conventional empirical models. This study proposes a Bayesian-optimized interpretable machine learning framework to predict the ultimate bond strength of reinforced geopolymer concrete using a comprehensive experimental database compiled from published studies. A dataset of 238 samples with 20 influential input variables was assembled to represent material properties, geopolymer chemistry, and specimen geometry. Six advanced machine learning algorithms, including Support Vector Regression (SVR), Random Forest (RF), Extra Trees Regressor (ETR), Gradient Boosting Machine (GBM), XGBoost, and CatBoost, were developed and systematically compared. Hyperparameter tuning was performed using Bayesian optimization to improve model performance. The results indicate that all models achieved strong predictive capability, while the optimized CatBoost model (BO-CatBoost) provided the best performance with testing metrics of R² = 0.950, MAE = 1.173, MAPE = 11.608%, and RMSE = 1.669. A comparative evaluation with existing empirical equations further demonstrated the superior accuracy and lower prediction variability of the proposed model. To enhance model transparency, SHAP-based explainability analysis was conducted to quantify the contribution of each input parameter. The global importance analysis revealed that compressive strength, the embedment length-to-bar diameter ratio, and the cover-to-bar diameter ratio are the most influential factors governing bond strength. Additional mixture-related parameters, including the alkaline solution-to-binder ratio, curing temperature, CaO content in the binder, and the SiO₂/Al₂O₃ ratio, also contribute to the bond mechanism by influencing geopolymerization and matrix densification. The proposed framework provides both high predictive accuracy and interpretable insights, demonstrating the potential of Bayesian-optimized interpretable machine learning to support the design and optimization of sustainable reinforced geopolymer concrete structures.

Evaluating the Shear Strength Capacity of Reinforced Concrete Deep Beam using Deep Learning Neural Network for Enhanced Structural Performance Analysis

Interpretable Constrained Monotonic Neural Network Model for Fiber-Reinforced Polymer (FRP) Shear Contribution in Strengthened Reinforced Concrete (RC) Beams

This study includes an interpretable machine learning (ML) framework for predicting the shear contribution of externally bonded fiber-reinforced polymer (FRP) composites in reinforced concrete beams. A database including total 313 experimental specimens was collected from previous experimental research. The data screening process has been conducted using the Isolation Forest algorithm, resulting in 268 cleaned specimens. The cleaned database was divided into a training subset containing 214 specimens and an independent test set containing 54 specimens. The trained subset was enlarged into 5204 synthetic data using two advanced generative models including Wasserstein generative adversarial network and conditional Variational autoencoder (CVAE). Separate constrained monotonic neural network (CMNN) models were then trained on both datasets and WGAN-based CMNN achieved R2=0.9524 for the synthetic training dataset and R2=0.9120 for the independent test set, whereas the CVAE-based CMNN achieved corresponding values of 0.9632 and 0.9011. To improve practical applicability, response functions were extracted from WGAN-based CMNN and fitted with analytical expressions to derive a closed-form prediction equation. The proposed equation was independently validated using separate unseen test specimens, which were not used in CMNN training and achieved R2 = 0.79, RMSE = 24.98 kN, MAE = 19.65 kN, MAPE = 21.72%, VAF = 79.35%, U95 = ±54.94 kN, SI = 3.04, and PI = 0.11. Compared with ACI 440.2R-17, CSA-S806.12, CNR-DT200 R1.2013, TR-55, and JSCE, the proposed equation showed superior accuracy while maintaining a transparent and design-oriented format.