Scholarlink

<p>Geopolymer concrete offers a sustainable alternative to Portland cement but poses challenges in compressive strength evaluation due to its complex chemistry. This study develops an artificial neural network (ANN) model using non-destructive testing methods, ultrasonic pulse velocity and Schmidt rebound hammer, as input features. A harmonized dataset of 680 samples was compiled from peer-reviewed sources. The optimized ANN achieved high accuracy (<i>R</i><sup>2</sup> = 0.956) with low prediction error. The results demonstrate a robust, non-invasive, and generalizable framework for in-situ compressive strength prediction of GPC.</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

Using artificial neural networks and non-destructive tests to predict the compressive strength of geopolymer concrete

  • 期刊论文

  • 发表日期：

    2025年10月10日

查看全文
  • Dina A. Emarah,
  • M. Anwar,
  • Yasser El-Hakem,
  • Elsayed H. Ali

摘要

Geopolymer concrete offers a sustainable alternative to Portland cement but poses challenges in compressive strength evaluation due to its complex chemistry. This study develops an artificial neural network (ANN) model using non-destructive testing methods, ultrasonic pulse velocity and Schmidt rebound hammer, as input features. A harmonized dataset of 680 samples was compiled from peer-reviewed sources. The optimized ANN achieved high accuracy (R2 = 0.956) with low prediction error. The results demonstrate a robust, non-invasive, and generalizable framework for in-situ compressive strength prediction of GPC.