Scholarlink

<p>The degradation of reinforced cement concrete (RCC) due to organic acids poses critical challenges for infrastructure longevity, particularly in agro-industrial, dairy, and wastewater environments. This study investigates the compressive strength performance of silica fume–modified RCC exposed to citric acid and proposes a machine learning (ML) framework for predictive modeling. A total of six mixes incorporating 0% to 15% silica fume were experimentally evaluated for compressive strength at 7, 28, and 56 days. Post-curing, samples were exposed to citric acid concentrations ranging from 0% to 10% to simulate organic degradation. Experimental results showed that 10% silica fume significantly enhanced strength and acid resistance. A synthetic dataset (<i>n</i> = 1000) was generated using controlled domain-informed sampling across seven input variables. Five ML models—Support Vector Regression, Decision Tree, Extra Trees, Random Forest, and XGBoost—were trained and validated using R², RMSE, MAE, MAPE, a20, and IOA. XGBoost achieved the highest performance (R² = 0.9782; MAPE = 2.81%). SHAP and PDP interpretability techniques identified curing age, silica fume content, and acid concentration as critical features. The proposed model demonstrates strong predictive accuracy and robustness, offering a reliable tool for optimizing RCC design in acid-exposed environments.</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

Predictive modeling of compressive strength in silica fume–modified RCC using ML under organic acid attack

  • 期刊论文

  • 发表日期：

    2026年4月22日

查看全文
  • Abhishek Mishra,
  • Mukesh Pandey,
  • Rakesh Gupta

摘要

The degradation of reinforced cement concrete (RCC) due to organic acids poses critical challenges for infrastructure longevity, particularly in agro-industrial, dairy, and wastewater environments. This study investigates the compressive strength performance of silica fume–modified RCC exposed to citric acid and proposes a machine learning (ML) framework for predictive modeling. A total of six mixes incorporating 0% to 15% silica fume were experimentally evaluated for compressive strength at 7, 28, and 56 days. Post-curing, samples were exposed to citric acid concentrations ranging from 0% to 10% to simulate organic degradation. Experimental results showed that 10% silica fume significantly enhanced strength and acid resistance. A synthetic dataset (n = 1000) was generated using controlled domain-informed sampling across seven input variables. Five ML models—Support Vector Regression, Decision Tree, Extra Trees, Random Forest, and XGBoost—were trained and validated using R², RMSE, MAE, MAPE, a20, and IOA. XGBoost achieved the highest performance (R² = 0.9782; MAPE = 2.81%). SHAP and PDP interpretability techniques identified curing age, silica fume content, and acid concentration as critical features. The proposed model demonstrates strong predictive accuracy and robustness, offering a reliable tool for optimizing RCC design in acid-exposed environments.