Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/65476
Title: Using artificial neural networks to assess the applicability of recycled aggregate classification by different specifications
Authors: Duan, Z
Poon, CS 
Xiao, J
Keywords: Artificial neural networks
Compressive strength
Elastic modulus
Recycled coarse aggregate
Specifications
Issue Date: 2017
Publisher: Springer
Source: Materials and structures (Materiaux et constructions), 2017, v. 50, no. 2, 107 How to cite?
Journal: Materials and structures (Materiaux et constructions) 
Abstract: Due to their high variability, the use of recycled coarse aggregates (RAs) in new structural concrete is not so common. While there are guidelines published in various countries providing advice on the use of RAs, the classification and requirements differ significantly. This study presents a novel method of using artificial neural networks (ANN) to evaluate the feasible use of RAs, classified by several national standards/specifications, to fully or partially substitute natural coarse aggregates in concrete with different strength grades. The evaluation is conducted through the comparison of the predicted compressive strength and elastic modulus of natural aggregate concrete (NAC) with those of RAC by using self-developed ANN models, ANN16-fc and ANN16-Ec, respectively. The predictions suggest that, most of the RAs classified by different specifications are of sufficient quality to be used in low-grade concrete (C30), but good quality control of RA is still necessary to produce RAC with equivalent compressive strength to that of NAC. As RAs investigated in this study are only considered in their minimum quality (critical) conditions, it is reasonable to be optimistic about the use of RAs in concrete production with a higher replacement level, especially for structural uses.
URI: http://hdl.handle.net/10397/65476
ISSN: 1359-5997
DOI: 10.1617/s11527-016-0972-8
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

47
Last Week
2
Last month
Checked on Nov 13, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.