Skip to main content

ORIGINAL RESEARCH article

Front. Built Environ.
Sec. Construction Materials
Volume 10 - 2024 | doi: 10.3389/fbuil.2024.1447800

Modeling properties of recycled aggregate concrete using gene expression programming and artificial neural network techniques

Provisionally accepted
Paul O. Awoyera Paul O. Awoyera 1Alireza Bahrami Alireza Bahrami 2*Chukwufumnanya Oranye Chukwufumnanya Oranye 1Lenin M. Romero Lenin M. Romero 3Ehsan Mansouri Ehsan Mansouri 4Javad Mortazavi Javad Mortazavi 5Jong W. Hu Jong W. Hu 5
  • 1 Department of Civil Engineering, Covenant University, Ota, Nigeria
  • 2 University of Gävle, Gävle, Sweden
  • 3 Escuela Professional de Ingenieria Cvil, Universidad Cesar Vallejo, SJL, Peru
  • 4 Department of Information Technology, Birjand University of Medical Sciences, Birjand,, Iran
  • 5 Department of Civil and Environmental Engineering, Incheon National University,, Incheon, Republic of Korea

The final, formatted version of the article will be published soon.

    Soft computing techniques have become popular for solving complex engineering problems and developing models for evaluating structural material properties. There are limitations to the available methods, including semi-empirical equations, such as overestimating or underestimating outputs, and, more importantly, they do not provide predictive mathematical equations. With genetic programming and artificial neural networks (ANNs), this study proposes models for estimating recycled aggregate concrete (RAC) properties. An experimental database compiled from parallel studies and a large amount of literature was used to develop models. For compressive strength prediction, gene expression programming yielded an R2 value of 0.95, while ANN achieved an R2 value of 0.93, demonstrating high reliability. The proposed predictive models are simple and robust, and improve the accuracy of RAC property estimation, providing a valuable tool in sustainable construction.

    Keywords: modeling, Recycled aggregate concrete, artificial neural network, Gene Expression Programming, Strength properties

    Received: 12 Jun 2024; Accepted: 28 Aug 2024.

    Copyright: © 2024 Awoyera, Bahrami, Oranye, Romero, Mansouri, Mortazavi and Hu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Alireza Bahrami, University of Gävle, Gävle, Sweden

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.