Scholarlink

<p>This paper presents a study focused on predicting the punching shear resistance of reinforced concrete flat slabs subjected to horizontal eccentricity and fiber reinforcement using machine learning (ML) models. A dataset of 221 experimental test results from literature sources was utilized, covering parameters such as slab geometry, material strengths, reinforcement ratios, and loading eccentricity. Five ML methods were employed: decision tree, random forest, adaptive boosting, gradient boosting, and extreme gradient boosting. Through random partitioning of data and evaluation on test sets, the extreme gradient boosting model emerged as the most accurate, achieving a coefficient of determination exceeding 0.9154. This data-driven model offers promise in assisting structural engineers during the design phase of eccentric flat slabs containing steel fiber reinforcement, with slab thickness identified as a key influencing factor. The study highlights the potential of ML techniques in addressing the complex challenges associated with predicting punching shear strength in reinforced concrete structures.</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

Estimating the punching shear strength of reinforced concrete flat slabs using machine learning

  • 期刊论文

  • 发表日期：

    2026年2月9日

查看全文
  • Tesfaye Alemu Mohammed,
  • Bayou Muche Yirdaw,
  • Habtamu A. Tadesse

摘要

This paper presents a study focused on predicting the punching shear resistance of reinforced concrete flat slabs subjected to horizontal eccentricity and fiber reinforcement using machine learning (ML) models. A dataset of 221 experimental test results from literature sources was utilized, covering parameters such as slab geometry, material strengths, reinforcement ratios, and loading eccentricity. Five ML methods were employed: decision tree, random forest, adaptive boosting, gradient boosting, and extreme gradient boosting. Through random partitioning of data and evaluation on test sets, the extreme gradient boosting model emerged as the most accurate, achieving a coefficient of determination exceeding 0.9154. This data-driven model offers promise in assisting structural engineers during the design phase of eccentric flat slabs containing steel fiber reinforcement, with slab thickness identified as a key influencing factor. The study highlights the potential of ML techniques in addressing the complex challenges associated with predicting punching shear strength in reinforced concrete structures.