Gritsada Sua-Iam

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.

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.

This study examines the compressive behavior and analytical modelling of natural and rubberized concretes (RuC) confined with low-cost glass chopped-strand mat (GCSM) jackets. A total of forty-two cylindrical specimens were tested under axial compression to assess the influence of rubber particle size, confinement configuration, and the number of GCSM layers. The RuC mixes were prepared by replacing 20% of fine aggregate by volume with crumb rubber of two size fractions: coarse (2.0 mm, retained on #10 sieve) and fine (0.425 mm, retained on #40 sieve). Both full- and strip-wrapping schemes were applied using two, four, and six layers of GCSM. The results demonstrated that GCSM jackets significantly enhanced the mechanical performance of both NAC and RuC specimens. Full wrapping provided the highest confinement efficiency, increasing compressive strength by up to 115% for NAC and 90% for RuC, while the ultimate axial strain increased by more than 1300% compared with unconfined specimens. Strip wrapping also improved performance, producing strength gains of 25–45% and strain increases of 250–500%. Analytical stress–strain models were developed through regression analysis, showing strong correlation with the experimental results (R² = 0.80–0.99). The proposed GCSM jacket system demonstrates high potential as a sustainable and economical alternative for strengthening and retrofitting rubberized concretes, offering improved ductility and energy absorption while supporting circular material utilization. It is noted that the confinement ratio, size of rubberized aggregates, and their percentage replacement of rubberized aggregates should be consistent with the values used in this work in order to use the proposed analytical expressions.

This study examines the confined compressive strength (Fcc) of circular, square, and rectangular column geometries under varying confinement conditions. Results indicate that circular columns have the highest Fcc values, exceeding those of square and rectangular shapes. Increased confinement through clamps significantly enhances compressive strength. Five machine learning models, Linear Regression, Decision Tree, Random Forest, AdaBoost, and Gradient Boosting, were used to predict Fcc based on geometric and confinement parameters. Linear Regression and Decision Tree models achieved moderate predictive performance, with R² values of 0.84 and 0.83, respectively, and relatively higher error measures (RMSE, MAE, and MAPE), indicating limited ability to capture complex nonlinear relationships in the data. In contrast, ensemble-based methods demonstrated superior performance. The Random Forest model improved the coefficient of determination to 0.90 while substantially reducing all error metrics, reflecting enhanced generalization through bagging. The boosting-based approaches yielded the best results, with AdaBoost achieving the highest R² value of 0.99 and the lowest RMSE, MAE, and MAPE among all models, followed closely by Gradient Boosting with an R² of 0.98. These results confirm that ensemble learning techniques, particularly boosting algorithms, yield more accurate and robust predictions than single learners for the problem studied. Data visualization techniques, including Regression Error Characteristic curves (REC) and SHapley Additive exPlanations (SHAP) value analysis, highlighted model performance and feature importance, emphasizing the roles of confinement and geometry in compressive strength. This research demonstrates the potential of machine learning to optimize structural engineering design and suggests further exploration of alternative shapes and confinement strategies to enhance structural integrity.

The construction cost overrun is an important issue that should be addressed, as it directly impacts many construction companies. Our research objective is to study and rank the impacts of empirical attitudes on construction cost overruns using the matrix analysis method. The research began with a focus group of 78 respondents, including 40 project engineers from contractor construction companies, 18 heads of government sectors related to construction projects, and 20 construction academicians. Based on expert interviews and the focus group discussion, 13 relevant factors were identified, and a questionnaire survey was subsequently conducted for data collection. The results showed that labor shortages were the most important factor influencing construction cost overruns, with the highest eigenvector value of 0.1687. The ranking of factors based on the percentages of average construction cost overruns includes labor shortages, variation orders, financial capacity, material price fluctuations, and drawing conditions, accounting for 18.3%, 15.7%, 12.8%, 10.2%, and 9.0%, respectively. These findings demonstrate the applicability of matrix analysis as a systematic approach for prioritizing empirical managerial attitudes influencing construction cost overruns, thereby providing a structured basis for decision-making in construction cost risk management.

This study investigates the application of the Circular Economy (CE) principles in cement–sand mortar by partially replacing natural fine aggregates with recycled materials. The aim is to promote sustainable construction practices while reducing ther environmental impacts associated with sand mining and waste disposal. Three types of recycled aggregates were evaluated: Recycled Concrete Aggregate (RCA), Crushed Brick (CB) aggregates (CBA, CBB, CBC, CBD), and crumb Rubber Aggregates (RB10, RB20, RB40). Each replaced 15% of the sand content by mass for the mineral wastes and by volume for the rubber, across three water-to-cement (w/c) ratios: 0.4, 0.5, and 0.6. The workability was assessed using the flow test as illustrated in [17]. The results revealed that the mortars with RCA and brick aggregates exhibited low workability at lower w/c ratios due to the high water absorption and the rough particle textures of the aggregates. In contrast, Rubberized Mortars (RB) showed excellent flowability across all ratios, attributed to rubber’s non-absorptive nature. Increasing the w/c ratio improved the flow in all mixes, though the rubber aggregates consistently outperformed others. The findings highlight the feasibility of using recycled waste materials, particularly rubber, to produce workable, eco-friendly mortars, supporting the shift toward a more sustainable construction industry.