This paper presents the results of a deep neural network (DNN) model predicting the axial load-carrying capacity of fire-damaged concrete square and rectangular reinforced concrete columns subsequently repaired using carbon fiber-reinforced polymer (CFRP) composites. An experimental database comprising 143 column specimen samples was collected from the literature. Thirteen parameters were noted, including Length of Columns (mm), Width of Columns (mm), Corner Radius (mm), Height of Column (mm), Initial Compressive Strength of Concrete (MPa), Initial Tensile Strength of Steel (MPa), Longitudinal Reinforcement Ratio (As/Ag, %), Temperature of Fire (°C), Fire Exposure Time (Minutes), Number of Layers of CFRP(Count), Thickness of CFRP (mm), and Tensile Elastic Modulus of CFRP (GPa). These parameters served as inputs for the model, with the final axial compressive strength of the CFRP-repaired column considered as the target/output. DNN models were calibrated for numerous numbers of neurons in the hidden layers to achieve optimization. The proposed DNN model demonstrated strong agreement with the experimental database, exhibiting an overall correlation factor (R) of 0.99946. The predicted outcomes of the proposed model closely align with the experimental findings, as evidenced by a thorough comparison with prior experimental investigations. Consequently, this model holds potential value for engineers seeking speedy assistance in repairing fire-damaged structures using CFRP composites.

In the field of structural engineering, the repair and rehabilitation of fire-damaged circular and square columns pose significant challenges. Carbon Fiber Reinforced Polymer (CFRP) composites have gained popularity as a potentially effective method for restoring the structural integrity of damaged structural members. The purpose of this investigation is to provide a state-of-the-art review of existing experimental and numerical studies in the literature on repairing fire-damaged square/circular columns using CFRP composites. The effectiveness of CFRP as a repairing technique in restoring the axial load-carrying capacity and stiffness of fire-damaged circular, square, and rectangular columns is evaluated. Based on past investigations, it has been concluded that CFRP composites can restore 70-169.2% of the axial capacity and 0-29.2% of the lost resistance. Moreover, the review offers a critical assessment of previous experimental and numerical investigations, highlighting their significant contributions to the advancement of knowledge regarding CFRP-based column repair. A comparative analysis of the experimental results from available studies is carried out, accompanied by a concise examination of the gaps, and a pathway for future researchers is also suggested. In addition to this, probable challenges and limitations, such as stiffness loss after repairing fire-damaged columns with CFRP composites, and ways to counter them, are also summarized in this study. The article provides engineers, researchers, and practitioners involved in the restoration and repair of fire-damaged circular and square columns using CFRP composites with insightful recommendations derived from an exhaustive synthesis of prior literature and case studies.

Masonry buildings have shaped construction history since about 6500 BCE. They offer durability, strength, and cost effectiveness, especially in developing countries. Yet assessing compressive strength during construction remains challenging due to the constituent materials soil, cement, and stone, complicating standardization worldwide. In the present study, an innovative model based on a machine learning algorithm is put forth to predict the compressive strengths of prisms. Some important factors considered as input to the algorithm based on traditional methods are the brick and mortar strengths, prism geometry, mortar bed thickness, and empirically derived height-to-thickness (t) (h/t) ratios. Three different ANN algorithms are coded and trained on the input data, and they are based on the Levenberg–Marquardt algorithm, the resilient backpropagation algorithm, and the conjugate gradient algorithm. The optimal ANN model trained using the conjugate gradient Polak–Ribière algorithm (traincgp) achieves superior performance, with R² = 0.9881, R² = 0.9927, RMSE = 0.9914 MPa, MAE = 0.6039 MPa, MAPE = 20.9141%, VAF = 0.9881, and WI = 0.9970. Sensitivity analysis shows the height-to-thickness (h/t) ratio is the dominant influence on compressive strength, consistent with structural mechanics. The primary contributions are the systematically curated, richly parameterized dataset and its use to produce robust, physically interpretable predictions with established ANN methods.

Using waste materials in the manufacture of concrete has many environmental advantages. However, it can be difficult to estimate structural performance, especially when beams are reinforced with fiber-reinforced polymers (FRP). In order to provide a data-driven approach to sustainable structural design, this work explores the use of machine learning (ML) approaches to forecast the flexural strength of FRP-strengthened waste aggregate concrete beams. A total number of 92 experimental datasets were used to develop and assess four ML algorithms: Random Forest (RF), Decision Tree (DT), Neural Network (NN), and Extreme Gradient Boosting (XGBoost). Regression plots, Taylor diagrams, statistical measures (R2R^2R2, RMSE, MAE, MSE), and explainable AI (XAI) tools, including SHAP, LIME, and partial dependence plots (PDPs), were used to evaluate the model’s performance. RF outperformed NN in terms of predictive accuracy, while XGBoost exhibited similar performance to RF. The most significant predictors, according to a SHAP analysis, were beam length and fiber length, with the lower followed by steel tensile strength, fiber width, and concrete compressive strength. LIME offered local interpretability for individual predictions, but PDPs demonstrated optimal parameter ranges and a nonlinear feature strength relationship. The findings provide engineers with a strong decision-support tool for designing green infrastructure, since they show that ensemble-based models can accurately represent the intricate, nonlinear dynamics controlling flexural behavior in sustainable FRP-strengthened waste aggregate concrete beams.