Scholarlink

<p>The research examines the potential of employing nano technology to modify the physical characteristics of fly ash and improve the engineering performance of mortar. Utilizing Nano Fly Ash (NFA) as a substitute for cement at different ratios demonstrated that the meticulous approach impacted the sample size and surface area, but did not alter the chemical structure and constituents. The analysis of X-ray diffraction (XRD) indicated a reduction in particle size and a complex lattice phase strain in the Fly Ash nanoparticles. The analysis showed that the particles exhibited non-spherical shapes and dimensions measuring under 5&#xa0;μm. The results of the compressive strength test indicated that the mortar with 15% Nano Fly Ash replacement exceeded the control mortar. Moreover, it was demonstrated that machine learning algorithms can accurately forecast experimental data and the connections between variables, as evidenced by metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R<sup>2</sup>). The RSM model demonstrated a high level of accuracy in predicting the mechanical properties, achieving a degree of precision with R2 values equal to or greater than 0.9539. The ANN model showed its capability to capture the variability of the data, as shown by a robust R<sup>2</sup> threshold (R<sup>2</sup> &gt; 0.9995) across training, testing, and validation phases. Utilizing high volumes of Fly Ash allows for the conservation of renewable resources, reduction of carbon emissions in cement production, and effective management of the disposal and contamination of inland Fly Ash.</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

Machine learning–driven insights into nano fly ash synergy for advanced mortar performance optimization

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月25日

查看全文
  • L. Krishnaraj,
  • G. Nakkeeran,
  • Sumant Nivarutti Shinde,
  • S. Thenmozhi,
  • George Uwadiegwu Alaneme,
  • Mutiu Shola Bakare,
  • Ebenezer Esenogho

摘要

The research examines the potential of employing nano technology to modify the physical characteristics of fly ash and improve the engineering performance of mortar. Utilizing Nano Fly Ash (NFA) as a substitute for cement at different ratios demonstrated that the meticulous approach impacted the sample size and surface area, but did not alter the chemical structure and constituents. The analysis of X-ray diffraction (XRD) indicated a reduction in particle size and a complex lattice phase strain in the Fly Ash nanoparticles. The analysis showed that the particles exhibited non-spherical shapes and dimensions measuring under 5 μm. The results of the compressive strength test indicated that the mortar with 15% Nano Fly Ash replacement exceeded the control mortar. Moreover, it was demonstrated that machine learning algorithms can accurately forecast experimental data and the connections between variables, as evidenced by metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R2). The RSM model demonstrated a high level of accuracy in predicting the mechanical properties, achieving a degree of precision with R2 values equal to or greater than 0.9539. The ANN model showed its capability to capture the variability of the data, as shown by a robust R2 threshold (R2 > 0.9995) across training, testing, and validation phases. Utilizing high volumes of Fly Ash allows for the conservation of renewable resources, reduction of carbon emissions in cement production, and effective management of the disposal and contamination of inland Fly Ash.