Scholarlink

<p>This research addresses the growing scarcity of natural aggregates across India and explores the use of recycled asphalt pavement (RAP) aggregates as a sustainable alternative in road construction. The study investigates the impact of incorporating RAP on the compressive and tensile strength of concrete, with results indicating that the excessive use of RAP (over 50% of natural aggregate) adversely affects these properties. However, there is a notable gap in research on predicting the compressive strength of concrete mixes containing RAP aggregates. To bridge this gap, machine learning algorithms, specifically extreme gradient boosting (XGBoost) and random forest regressor (RFR), are employed to predict the concrete strength at various curing ages. The models are evaluated using three statistical performance indices: the coefficient of determination (R<sup>2</sup>), mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), and root mean square error (RMSE). The results demonstrate that the XGBoost model provides superior prediction accuracy (R<sup>2</sup> = 0.937) compared to the random forest model. Additionally, sensitivity analysis reveals that washed recycled fine aggregates (WRFA) significantly contribute to the strength of cement concrete mixes. These findings suggest that WRFA aggregates can be considered a promising, sustainable alternative for concrete pavements, potentially reducing reliance on natural aggregates and offering cost-effective, environmentally friendly solutions for the construction industry.</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

Monitoring optimal content of recycled fine aggregates using improved grey wolf optimization for sustainable concrete

  • 期刊论文

  • 发表日期：

    2025年5月27日

查看全文
  • Kumar Shubham,
  • M. K. Diptikanta Rout,
  • Sabita Dash

摘要

This research addresses the growing scarcity of natural aggregates across India and explores the use of recycled asphalt pavement (RAP) aggregates as a sustainable alternative in road construction. The study investigates the impact of incorporating RAP on the compressive and tensile strength of concrete, with results indicating that the excessive use of RAP (over 50% of natural aggregate) adversely affects these properties. However, there is a notable gap in research on predicting the compressive strength of concrete mixes containing RAP aggregates. To bridge this gap, machine learning algorithms, specifically extreme gradient boosting (XGBoost) and random forest regressor (RFR), are employed to predict the concrete strength at various curing ages. The models are evaluated using three statistical performance indices: the coefficient of determination (R2), mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), and root mean square error (RMSE). The results demonstrate that the XGBoost model provides superior prediction accuracy (R2 = 0.937) compared to the random forest model. Additionally, sensitivity analysis reveals that washed recycled fine aggregates (WRFA) significantly contribute to the strength of cement concrete mixes. These findings suggest that WRFA aggregates can be considered a promising, sustainable alternative for concrete pavements, potentially reducing reliance on natural aggregates and offering cost-effective, environmentally friendly solutions for the construction industry.