Scholarlink

<p>This study investigates the use of natural pozzolana (PZ) and glass powder (GP) as binary and ternary cementitious materials to improve the sustainability of self-compacting mortar (SCM) for construction applications. The study assessed the effects of PZ and GP on the flowability, mechanical strength, and durability of SCM. Artificial Neural Networks (ANNs) were employed to simulate and predict the performance of these materials, while a statistical ternary mixture design approach was used to explore the interactions between the components and optimize the mixture proportions. This integrated methodology yielded comprehensive insights into the impact of these novel materials on the characteristics of the mortar. The findings indicated that the inclusion of GP enhanced the workability and filling capacity of the mortars by roughly 30% in comparison to the control mixture. A ternary mix containing 5% GP and 10% PZ increased compressive strength by 16%, concurrently achieving a 40% reduction in water absorption and a 50% decrease in porosity. This resulted in a denser microstructure that reduces moisture-induced degradation and improves resistance to environmental conditions. The ANN models effectively predicted the behavior of the mortars and their impact on the mixture parameters. Substituting PZ and GP with sustainable cementitious additives improved the structural properties of the mortar and decreased energy consumption during production, resulting in a 14% reduction in CO₂ emissions. </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

Optimizing sustainable self-compacting mortar properties using natural pozzolan and glass powder as cementitious materials: a combination of artificial neural networks and statistical mixture design approach

  • 期刊论文

  • 发表日期：

    2025年5月14日

查看全文
  • Younes Ouldkhaoua,
  • Mohamed Sahraoui,
  • Zine El Abiddine Laidani,
  • Benchaa Benabed,
  • Rajab Abousnina,
  • Mohamed El Ghazali Belgacem

摘要

This study investigates the use of natural pozzolana (PZ) and glass powder (GP) as binary and ternary cementitious materials to improve the sustainability of self-compacting mortar (SCM) for construction applications. The study assessed the effects of PZ and GP on the flowability, mechanical strength, and durability of SCM. Artificial Neural Networks (ANNs) were employed to simulate and predict the performance of these materials, while a statistical ternary mixture design approach was used to explore the interactions between the components and optimize the mixture proportions. This integrated methodology yielded comprehensive insights into the impact of these novel materials on the characteristics of the mortar. The findings indicated that the inclusion of GP enhanced the workability and filling capacity of the mortars by roughly 30% in comparison to the control mixture. A ternary mix containing 5% GP and 10% PZ increased compressive strength by 16%, concurrently achieving a 40% reduction in water absorption and a 50% decrease in porosity. This resulted in a denser microstructure that reduces moisture-induced degradation and improves resistance to environmental conditions. The ANN models effectively predicted the behavior of the mortars and their impact on the mixture parameters. Substituting PZ and GP with sustainable cementitious additives improved the structural properties of the mortar and decreased energy consumption during production, resulting in a 14% reduction in CO₂ emissions.