Scholarlink

<p>Geopolymer concrete (GPC) offers a sustainable alternative to conventional Portland cement concrete by utilizing industrial by-products, reducing the carbon footprint associated with construction. The research focuses on evaluating the compressive strength (Cr), tensile strength (Tr), and flexural strength (Fr) of geopolymer concrete mixes with varying proportions of fly ash and sugarcane bagasse ash. An Artificial Neural Network (ANN) model is employed to predict the mechanical properties of the geopolymer concrete based on the input parameters, including fly ash, bagasse ash, SS/SH ratio, NaOH concentration, fine aggregate, and coarse aggregate. As the molarity of the sodium hydroxides (SH) solution was raised from 10&#xa0;M to 16&#xa0;M, the GPC specimens’ compressive strength increased. The mixes including 0.0% and 15.0% sugarcane bagasse ash (SCBA) showed a little reduction in compressive strength after reaching a 14&#xa0;M SH concentration. The prediction accuracy of the ANN model is evaluated by contrasting the expected and actual test results after it has been trained and verified using experimental data. With high R<sup>2</sup> values of 0.9053, 0.9559, and 0.9461, respectively, the ANN model performs well in predicting Cr, Fr, and Tr on the training data, suggesting a significant connection between anticipated and actual values.</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

Influence of sodium hydroxide molarity on strength development of fly ash and sugarcane bagasse ash geopolymer concrete using artificial neural networks

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月18日

查看全文
  • Mohammed Ali M. Rihan,
  • Tajebe Bezabih,
  • Bheem Pratap,
  • Tanu H M

摘要

Geopolymer concrete (GPC) offers a sustainable alternative to conventional Portland cement concrete by utilizing industrial by-products, reducing the carbon footprint associated with construction. The research focuses on evaluating the compressive strength (Cr), tensile strength (Tr), and flexural strength (Fr) of geopolymer concrete mixes with varying proportions of fly ash and sugarcane bagasse ash. An Artificial Neural Network (ANN) model is employed to predict the mechanical properties of the geopolymer concrete based on the input parameters, including fly ash, bagasse ash, SS/SH ratio, NaOH concentration, fine aggregate, and coarse aggregate. As the molarity of the sodium hydroxides (SH) solution was raised from 10 M to 16 M, the GPC specimens’ compressive strength increased. The mixes including 0.0% and 15.0% sugarcane bagasse ash (SCBA) showed a little reduction in compressive strength after reaching a 14 M SH concentration. The prediction accuracy of the ANN model is evaluated by contrasting the expected and actual test results after it has been trained and verified using experimental data. With high R2 values of 0.9053, 0.9559, and 0.9461, respectively, the ANN model performs well in predicting Cr, Fr, and Tr on the training data, suggesting a significant connection between anticipated and actual values.