Scholarlink

<p>In this study, an integrated experimental and machine learning–based framework was developed to predict and optimize the fresh, mechanical, and durability properties of basalt fiber–reinforced ground GGBS based GPC. A total of 100 systematically designed mix proportions were prepared by varying NaOH (12–17%), Na<sub>2</sub>SiO<sub>3</sub> (28–37%), activator-to-binder ratio (0.40–0.53), liquid-to-binder ratio (0.30–0.38), and BF dosage (0–1.0%). Experimental results indicated that the 28-day CS ranged from 52.3 to 85.3&#xa0;MPa, TS from 5.5 to 9.0&#xa0;MPa, and FS from 6.8 to 10.9&#xa0;MPa. Durability performance was characterized by water absorption of 3.25–4.85%, sorptivity of 5.05–7.85 × 10⁻<sup>7</sup> mm/√s, and rapid chloride penetration resistance of 980–1850 Coulombs at 28&#xa0;days, while UPV values exceeding 4.5&#xa0;km/s confirmed excellent internal matrix quality. RSM models demonstrated strong predictive capability with R<sup>2</sup> values between 0.87 and 0.99, enabling multi-response optimization. An ANN model developed using a 5–10–8 architecture achieved an overall RMSE of 0.204, MAE of 0.157, and R<sup>2</sup> of 0.242 under aggregated multi-output evaluation, highlighting its ability to capture complex nonlinear behavior. Optimal performance was consistently obtained at activator-to-binder ratios of 0.46–0.50, liquid-to-binder ratios of 0.32–0.36, and BF contents of 0.50–0.75%. The proposed experimental ML framework provides a robust decision-support tool for designing high-performance and durable geopolymer concrete, supporting its application in sustainable construction.</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-based prediction and optimization of mechanical and durability properties of geopolymer concrete

  • 期刊论文

  • 发表日期：

    2026年4月22日

查看全文
  • U. R. Kawade,
  • Prital Kalasur,
  • B. S. Karthik,
  • Praveen Oggu,
  • Ravikumar Seenivasan,
  • N. Lingeshwaran

摘要

In this study, an integrated experimental and machine learning–based framework was developed to predict and optimize the fresh, mechanical, and durability properties of basalt fiber–reinforced ground GGBS based GPC. A total of 100 systematically designed mix proportions were prepared by varying NaOH (12–17%), Na2SiO3 (28–37%), activator-to-binder ratio (0.40–0.53), liquid-to-binder ratio (0.30–0.38), and BF dosage (0–1.0%). Experimental results indicated that the 28-day CS ranged from 52.3 to 85.3 MPa, TS from 5.5 to 9.0 MPa, and FS from 6.8 to 10.9 MPa. Durability performance was characterized by water absorption of 3.25–4.85%, sorptivity of 5.05–7.85 × 10⁻7 mm/√s, and rapid chloride penetration resistance of 980–1850 Coulombs at 28 days, while UPV values exceeding 4.5 km/s confirmed excellent internal matrix quality. RSM models demonstrated strong predictive capability with R2 values between 0.87 and 0.99, enabling multi-response optimization. An ANN model developed using a 5–10–8 architecture achieved an overall RMSE of 0.204, MAE of 0.157, and R2 of 0.242 under aggregated multi-output evaluation, highlighting its ability to capture complex nonlinear behavior. Optimal performance was consistently obtained at activator-to-binder ratios of 0.46–0.50, liquid-to-binder ratios of 0.32–0.36, and BF contents of 0.50–0.75%. The proposed experimental ML framework provides a robust decision-support tool for designing high-performance and durable geopolymer concrete, supporting its application in sustainable construction.