KMITL

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

Browse

Settings

Access type: UnknownAuthor: search.filters.author.Poovarodom, Nakhorn

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Machine learning approach to predict the strength of concrete confined with sustainable natural FRP composites
    (2024-07-01)
    Ali Talpur, Shabbir
    ;
    Thansirichaisree, Phromphat
    ;
    Poovarodom, Nakhorn
    ;
    Mohamad, Hisham
    ;
    Zhou, Mingliang
    Recent earthquakes have highlighted the need to strengthen existing structures with substandard designs. NFRPs provide a sustainable, cost-effective alternative for strengthening, but accurately predicting their performance remains a challenge. This study investigates the use of machine learning algorithms for predicting the compressive strength concrete specimens confined with various NFRPs. Four algorithms were employed: decision tree, random forest, neural network, and gradient boosting regressor. A diverse dataset encompassing various geometries, material properties, and confinement configurations was used to train and evaluate the models. Gradient boosting regressor (GBR) achieved the highest performance, with an average R-squared value of 0.94 and low mean absolute error (MAE) and root mean squared error (RMSE) during training and k-fold cross-validation. Neural network and random forest also demonstrated satisfactory performance, with average R-squared values of 0.88 and 0.86, respectively, during cross-validation. These results suggest that machine learning holds promise for predicting the compressive strength of concrete confined with NFRPs. GBR offers the most accurate predictions, making it a valuable tool for engineers seeking to optimize the design and performance of strengthened structures using sustainable materials.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Influence of natural fiber rope wrapping techniques on the compressive response of recycled aggregate concrete circular columns
    (2023-09-01)
    Chaiyasarn, Krisada
    ;
    Poovarodom, Nakhorn
    ;
    Ejaz, Ali
    ;
    Ng, Anne W.M.
    ;
    Hussain, Qudeer
    The utilization of recycled waste in the production of new concrete raises significant concerns regarding the quality of the resulting concrete. One prominent drawback of recycled aggregate concrete (RAC) is its inferior mechanical properties compared to natural aggregate concrete. In this study, we examine the impact of hemp fiber rope (HFR) confinement on improving the compressive stress-strain behavior of RAC, specifically using recycled brick aggregates from fired-clay solid bricks (RAC-FCSB) as a partial substitute for natural coarse aggregates. Furthermore, we explore and compare the effectiveness of HFR confinement in the form of strips versus fully wrapped confinement. To conduct the experiments, a comprehensive framework was developed, involving a total of 32 cylindrical specimens. The parameters of interest included the configuration of HFR confinement (strips or full wrapping), the number of HFR layers, and the inherent strength of the concrete. The results indicate that HFR strips can significantly enhance the compressive stress-strain response. However, their performance falls short when compared to the fully wrapped HFR confinement. Nonetheless, HFR strips were able to enhance the peak compressive stress and strain of RAC-FCSB up to 204% and 190%, respectively. The second part of the study investigated the performance of existing models of HFR confinement in predicting the peak compressive stress and strain of RAC-FCSB. The deficiencies in existing models were highlighted, and new models based on non-linear regression analysis were proposed to accurately predict the peak compressive stress and strain of HFR-confined RAC-FCSB.