KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Chaimahawan, PreedaSubject: search.filters.subject.analytical modeling

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    From Experiment to Prediction: Machine Learning Solutions for Concrete Strength Assessment with Steel Clamps
    (2026-02-01)
    Saingam, Panumas
    ;
    Chatveera, Burachat
    ;
    Sua-Iam, Gritsada
    ;
    Chaimahawan, Preeda
    ;
    Suthumma, Chisanuphong
    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 R<sup>2</sup> 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 R<sup>2</sup> value of 0.99 and the lowest RMSE, MAE, and MAPE among all models, followed closely by Gradient Boosting with an R<sup>2</sup> 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.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Eco-Friendly Structural Solutions: The Synergy of Waste Rubber and Hemp Fibers in Sustainable Concrete Design
    (2026-01-01)
    Thansirichaisree, Phromphat
    ;
    Mohamad, Hisham
    ;
    Chaimahawan, Preeda
    ;
    Hussain, Qudeer
    ;
    Jirasakjamroonsri, Amornthep
    The growing emphasis on sustainable construction has encouraged the integration of recycled and renewable materials into structural concrete. This study investigates the axial compressive behavior of rectangular columns incorporating waste-tire rubber as a partial replacement of fine aggregate (5% and 10%) and external confinement using low-cost hemp ropes. A total of twelve specimen configurations, including unconfined and hemp-confined columns with up to three wrapping layers, were tested under monotonic axial compression. The results show that rubber inclusion reduces initial stiffness and peak strength by up to 46%, yet significantly enhances deformability. Hemp-rope confinement effectively compensates for strength loss, increasing compressive strength by up to 53% and ultimate strain by over 500%, with more pronounced effects in rubberized mixes. Normalized strength and strain trends demonstrate a strong dependence on confinement ratio, particularly for highly deformable concrete. To generalize these behaviors, Popovics-based models were calibrated using nonlinear regression, yielding high predictive accuracy (R<sup>2</sup> = 0.94–0.98) for key parameters including peak stress, peak strain, post-peak modulus, and elastic modulus. The proposed expressions closely reproduce the experimental stress–strain response and provide practical tools for modeling confined conventional and rubberized concrete.