Scholarlink

<p>This study investigates the mechanical performance of concrete incorporating treated sludge as a partial cement replacement, analyzing compressive, flexural, and split tensile strengths across various curing durations. Experimental results demonstrate strength improvement with extended curing time and optimal water-to-cement (W/C) ratios. While 10%?15% cement replacement maintains structural viability, higher substitution levels (beyond 17.5%) lead to strength deterioration, with concrete exceeding 22.5% sludge replacement exhibiting limited structural feasibility. To enhance predictive accuracy and optimize sustainable concrete mix design, machine learning models are employed to estimate compressive strength. machine learning models. Extra Trees Regressor, AdaBoost, Random Forest, and Gradient Boosting Regressor were developed to predict compressive strength. Among these, the Gradient Boosting and Random Forest models demonstrated the highest predictive accuracy, with R<sup>2</sup> values of 0.975 and 0.977, respectively. The study confirms that integrating machine learning with experimental methods offers a robust, data-driven approach for optimizing concrete mix design and supports the sustainable reuse of sewage sludge in construction applications.</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 optimization of concrete mixes incorporating treated sludge

  • 期刊论文

  • 发表日期：

    2025年6月20日

查看全文
  • Hrishikesh Kumar Singh,
  • Aditya Verma,
  • Salil Kumar Gupta,
  • Divyansh Singh,
  • Deepak V. P. Suman

摘要

This study investigates the mechanical performance of concrete incorporating treated sludge as a partial cement replacement, analyzing compressive, flexural, and split tensile strengths across various curing durations. Experimental results demonstrate strength improvement with extended curing time and optimal water-to-cement (W/C) ratios. While 10%?15% cement replacement maintains structural viability, higher substitution levels (beyond 17.5%) lead to strength deterioration, with concrete exceeding 22.5% sludge replacement exhibiting limited structural feasibility. To enhance predictive accuracy and optimize sustainable concrete mix design, machine learning models are employed to estimate compressive strength. machine learning models. Extra Trees Regressor, AdaBoost, Random Forest, and Gradient Boosting Regressor were developed to predict compressive strength. Among these, the Gradient Boosting and Random Forest models demonstrated the highest predictive accuracy, with R2 values of 0.975 and 0.977, respectively. The study confirms that integrating machine learning with experimental methods offers a robust, data-driven approach for optimizing concrete mix design and supports the sustainable reuse of sewage sludge in construction applications.