Scholarlink

<p>The construction sector is always seeking innovative ways to improve concrete quality. Self-compacting concrete (SCC) has improved potentially due to its ability to flow and compact under its weight. SCC reduces the amount of concrete needed, labour costs, and enhances structural integrity. This investigation focuses on artificial neural networks (ANN) and multiple regression analysis (MRA) to predict key strength parameters of SCC. The prediction mode data from seven sets of concrete samples form an experimental setup. Concrete parameters such as cement, M-sand, coarse aggregate, Ground Granulated Blast-furnace Slag (GGBS), Micro Silica (MS), Water-Cement ratio and admixture are used as input variables, while compressive and tensile strengths R<sup>2</sup> value 0.99 &amp; 0.98 RMSE 0.99 and 0.98 are the output variables. In terms of Mechanical Properties, High Strength Self-Compacting Concrete (HSSCC) best mix 50% GGBS and 10% MS exhibited the maximum Compressive &amp; tensile Strength at 7, 28 &amp; 90&#xa0;days. Microstructural analyses using scanning electron microscopy (SEM) and energy dispersive X-ray spectroscopy (EDX) showed an improved morphological characteristic. Also, the chemical composition of concrete showed an enhanced C–S–H gel, which improved the mechanical properties and durability of the concrete pointing toward substantial potential for developing sustainable, high-strength construction materials. This study distinguishes itself by providing a detailed quantification of carbon reductions in SCC specifically, using a high-substitution ternary mix that maintains performance while minimizing environmental impact.</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

Data-driven optimization of self-compacting concrete strength via ANN techniques

  • 期刊论文

  • 发表日期：

    2025年10月11日

查看全文
  • S. M. Naveen Kumar,
  • M. Rame Gowda,
  • Y. M. Vijaya Kumar,
  • N. B. Pradeep

摘要

The construction sector is always seeking innovative ways to improve concrete quality. Self-compacting concrete (SCC) has improved potentially due to its ability to flow and compact under its weight. SCC reduces the amount of concrete needed, labour costs, and enhances structural integrity. This investigation focuses on artificial neural networks (ANN) and multiple regression analysis (MRA) to predict key strength parameters of SCC. The prediction mode data from seven sets of concrete samples form an experimental setup. Concrete parameters such as cement, M-sand, coarse aggregate, Ground Granulated Blast-furnace Slag (GGBS), Micro Silica (MS), Water-Cement ratio and admixture are used as input variables, while compressive and tensile strengths R2 value 0.99 & 0.98 RMSE 0.99 and 0.98 are the output variables. In terms of Mechanical Properties, High Strength Self-Compacting Concrete (HSSCC) best mix 50% GGBS and 10% MS exhibited the maximum Compressive & tensile Strength at 7, 28 & 90 days. Microstructural analyses using scanning electron microscopy (SEM) and energy dispersive X-ray spectroscopy (EDX) showed an improved morphological characteristic. Also, the chemical composition of concrete showed an enhanced C–S–H gel, which improved the mechanical properties and durability of the concrete pointing toward substantial potential for developing sustainable, high-strength construction materials. This study distinguishes itself by providing a detailed quantification of carbon reductions in SCC specifically, using a high-substitution ternary mix that maintains performance while minimizing environmental impact.