Using ANNs to predict the mechanical properties of recycled aggregate concrete prepared with old concrete with different strength grades

Zhen Hua Duan, Shi Cong Kou, Chi Sun Poon

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)

Abstract

In this paper, five parent concretes with 28-day strengths of 30, 45, 60, 80 and 100 MPa were prepared and crushed to produce recycled aggregates (RA) in the sizes ranges of coarse aggregates (5-10 mm and 10-20 mm), which were then used to fully replace the natural aggregate (NA) in producing new concrete mixes. The physical and mechanical properties of RA were tested to study their influence on the mechanical properties of recycled aggregate concrete (RAC). The experimental results were then compared with those produced by Artificial Neural Networks (ANNs) models. The results indicated that ANNs has a fairly high accuracy on predicting the compressive strength and elastic modulus of RAC even when RA are derived from different old concrete with different strength grades.
Original languageEnglish
Title of host publicationfib Symposium 2012
Subtitle of host publicationConcrete Structures for Sustainable Community - Proceedings
Pages75-78
Number of pages4
Publication statusPublished - 1 Dec 2012
Eventfib Symposium 2012: Concrete Structures for Sustainable Community - Stockholm, Sweden
Duration: 11 Jun 201214 Jun 2012

Conference

Conferencefib Symposium 2012: Concrete Structures for Sustainable Community
Country/TerritorySweden
CityStockholm
Period11/06/1214/06/12

Keywords

  • Artificial Neural Network
  • Parent concrete
  • Physical and mechanical properties
  • Recycled aggregate

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction

Fingerprint

Dive into the research topics of 'Using ANNs to predict the mechanical properties of recycled aggregate concrete prepared with old concrete with different strength grades'. Together they form a unique fingerprint.

Cite this