Scholarlink

<p>This study presents a comprehensive investigation into the age-dependent strength development and predictive modeling of sustainable concrete incorporating Ground Granulated Blast Furnace Slag (GGBS), Silica Fume (SF), and Phosphogypsum (PG) as partial replacements for Ordinary Portland Cement (OPC). Twelve mix proportions were designed, including a control mix and ternary blends with varying percentages of GGBS (5–15%), SF (5–10%), and a constant 5% PG. Compressive and flexural strengths were evaluated at 7, 28, and 90 days to capture the time-dependent evolution of mechanical performance. The findings showed that the ternary SCM concrete, especially the mixture of 15% GGBS, 10% SF, and 5% PG, had the best long-term strength, reaching 55.3&#xa0;MPa in compressive strength and 5.21&#xa0;MPa in flexural strength after 90 days. Predictive models using Random Forest and XGBoost were developed to supplement the experimental results, both of which presented excellent accuracy (<InlineEquation ID="IEq1"> <EquationSource Format="MATHML"><math> <msup> <mi mathvariant="normal">R</mi> <mn>2</mn> </msup> <mo>&gt;</mo> <mn>0.99</mn> </math></EquationSource> <EquationSource Format="TEX">$\mathrm{R}^{2} &gt; 0.99$</EquationSource> </InlineEquation>) and were more accurate than the linear regression in predicting strength evolution. Reliability evaluation using Weibull analysis confirmed that the failure probability decreased with curing age, thus indicating the improved durability of the SCM-based mixes. It provides an excellent framework to understand and predict time-dependent performance through experimental results, state-of-the-art machine-learning algorithms, and probabilistic reliability analysis for sustainable concrete systems, suggesting potential applications in durable infrastructure.</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

Predictive modeling of age-dependent strength in concrete incorporating GGBS, silica fume, and phosphogypsum using XGBoost, Random Forest, and Weibull analysis

  • 期刊论文

  • 发表日期：

    2026年1月2日

查看全文
  • Priya Velusamy,
  • Johnpaul V,
  • Nisha N,
  • Subbulakshmi T,
  • Kumaran N,
  • Ravindaran Thangavel,
  • Athibaranan S

摘要

This study presents a comprehensive investigation into the age-dependent strength development and predictive modeling of sustainable concrete incorporating Ground Granulated Blast Furnace Slag (GGBS), Silica Fume (SF), and Phosphogypsum (PG) as partial replacements for Ordinary Portland Cement (OPC). Twelve mix proportions were designed, including a control mix and ternary blends with varying percentages of GGBS (5–15%), SF (5–10%), and a constant 5% PG. Compressive and flexural strengths were evaluated at 7, 28, and 90 days to capture the time-dependent evolution of mechanical performance. The findings showed that the ternary SCM concrete, especially the mixture of 15% GGBS, 10% SF, and 5% PG, had the best long-term strength, reaching 55.3 MPa in compressive strength and 5.21 MPa in flexural strength after 90 days. Predictive models using Random Forest and XGBoost were developed to supplement the experimental results, both of which presented excellent accuracy ( R 2 > 0.99 $\mathrm{R}^{2} > 0.99$ ) and were more accurate than the linear regression in predicting strength evolution. Reliability evaluation using Weibull analysis confirmed that the failure probability decreased with curing age, thus indicating the improved durability of the SCM-based mixes. It provides an excellent framework to understand and predict time-dependent performance through experimental results, state-of-the-art machine-learning algorithms, and probabilistic reliability analysis for sustainable concrete systems, suggesting potential applications in durable infrastructure.