Scholarlink

<p>This study addresses the application of advanced boosting-based ensemble machine learning techniques such as extreme gradient boosting (XGBoost), random forest (RF), category-aware gradient boosting (CATBoost), and adaptive boosting (ADABoost) algorithms to study the bond behavior of fiber-reinforced polymer (FRP) bars in reinforced concrete (RC) beams. To forecast the peak load (<i>P</i><sub>max</sub>) of the bond behavior between the FRP bars and concrete, five total input variables, namely, the elastic modulus of the bar (<i>E</i><sub>f</sub>), the tensile strength of the bar (<i>F</i><sub>f</sub>), the compressive strength of the concrete (<i>f</i>'<sub>c</sub>), the diameter of the bar (<i>d</i><sub>b</sub>), and the bar embedment length (<i>l</i><sub>b</sub>), were selected for machine learning model construction. The accuracy of the constructed predictive machine learning models was compared using several metric performances. However, rank analysis has also been used to ascertain which models perform the best. According to the findings of rank analysis using several metric performances, XGBoost outperformed RF, ADABoost, and CATBoost. Utilizing the developed advanced machine learning methods to examine the bond behavior of FRP bars in RC beams yields tangible advantages for the construction sector. This approach refines the design precision, minimizes expenses, and elevates the overall effectiveness and longevity of structures reinforced with FRP.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Boosting-based ensemble machine learning models to predict the bond behavior between concrete and fiberreinforced polymer bars

  • 期刊论文

  • 发表日期：

    2025年6月24日

查看全文
  • Irwan Afriadi,
  • Chanachai Thongchom,
  • Divesh Ranjan Kumar,
  • Warit Wipulanusat,
  • Suraparb Keawsawasvong

摘要

This study addresses the application of advanced boosting-based ensemble machine learning techniques such as extreme gradient boosting (XGBoost), random forest (RF), category-aware gradient boosting (CATBoost), and adaptive boosting (ADABoost) algorithms to study the bond behavior of fiber-reinforced polymer (FRP) bars in reinforced concrete (RC) beams. To forecast the peak load (Pmax) of the bond behavior between the FRP bars and concrete, five total input variables, namely, the elastic modulus of the bar (Ef), the tensile strength of the bar (Ff), the compressive strength of the concrete (f'c), the diameter of the bar (db), and the bar embedment length (lb), were selected for machine learning model construction. The accuracy of the constructed predictive machine learning models was compared using several metric performances. However, rank analysis has also been used to ascertain which models perform the best. According to the findings of rank analysis using several metric performances, XGBoost outperformed RF, ADABoost, and CATBoost. Utilizing the developed advanced machine learning methods to examine the bond behavior of FRP bars in RC beams yields tangible advantages for the construction sector. This approach refines the design precision, minimizes expenses, and elevates the overall effectiveness and longevity of structures reinforced with FRP.