Prediction of Strength of Plain and Blended Cement Concretes Cured Under Hot Weather Using Quadratic Regression and ANN Tools

Muhammad Nasir, Uneb Gazder, Muhammad Umar Khan, Mehboob Rasul*, Mohammed Maslehuddin, Omar S.Baghabra Al-Amoudi

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Concreting and curing under hot climatic conditions pose adverse effects on the characteristics of concrete. These challenges have prompted cement and concrete technologists to incorporate pozzolanic materials for the dual advantages from technical and sustainable perspectives. In this research, the impact of: (1) casting temperature between the range of 25–45 °C, (2) curing regimes, namely water ponding, burlap covering or curing compound, and (3) pozzolanic materials, namely fly ash, very fine fly ash, silica fume, natural pozzolan and ground granulated blast furnace slag on the long-term strength development of concrete have been investigated. Prediction models correlating the investigated variables and concrete strength were developed utilizing quadratic regression models and artificial neural networks (ANNs). ANN models were able to predict the compressive strength of concrete with higher accuracy than that of regression model. This model is expected to be applied for designing concrete of higher strengths under hot weather conditions.

Original languageEnglish
Pages (from-to)12697-12709
Number of pages13
JournalArabian Journal for Science and Engineering
Volume47
Issue number10
DOIs
StatePublished - Oct 2022

Bibliographical note

Publisher Copyright:
© 2022, King Fahd University of Petroleum & Minerals.

Keywords

  • Artificial neural network
  • Compressive strength
  • Curing regime
  • Fresh concrete temperature
  • Quadratic regression models

ASJC Scopus subject areas

  • General

Fingerprint

Dive into the research topics of 'Prediction of Strength of Plain and Blended Cement Concretes Cured Under Hot Weather Using Quadratic Regression and ANN Tools'. Together they form a unique fingerprint.

Cite this