Design of Alkali-Activated Slag-Fly Ash Concrete Mixtures Using Machine Learning

Gunasekara, C. and Lokuge, W. and Keskic, M. and Raj, N. and Law, D. W. and Setunge, S. (2020) Design of Alkali-Activated Slag-Fly Ash Concrete Mixtures Using Machine Learning. Materials Journal, 117 (5). pp. 263-278. ISSN 0889-325X

[img]
Preview
Text (Accepted Version)
Manuscript-Final.pdf

Download (901kB) | Preview

Abstract

So far, the alkali activated concrete has primarily focused on the effect of source material properties and ratio of mix proportions on the compressive strength development. A little research has focused on developing a standard mix design procedure for alkali activated concrete for a range of compressive strength grades. This study developed a standard mix design procedure for alkali activated slag‒fly ash (low calcium, class F) blended concrete using two machine learning techniques, Artificial Neural Networks (ANN) and Multivariate Adaptive Regression Spline (MARS). The algorithm for the predictive model for concrete mix design was developed using MATLAB programming environment by considering the five key input parameters; water/solid ratio, alkaline activator/binder ratio, Na-Silicate /NaOH ratio, fly ash/slag ratio and NaOH molarity. The targeted compressive strengths ranging from 25–45 MPa (3.63–6.53 ksi) at 28 days were achieved with laboratory testing, using the proposed machine learning mix design procedure. Thus, this tool has the capability to provide a novel approach for the design of slag-fly ash blended alkali activated concrete grades matching to the requirements of in-situ field constructions.


Statistics for USQ ePrint 41184
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Civil Engineering and Surveying (1 Jul 2013 -)
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Civil Engineering and Surveying (1 Jul 2013 -)
Date Deposited: 09 Feb 2021 05:45
Last Modified: 04 Mar 2021 05:24
Uncontrolled Keywords: Alkali Activated Concrete; Artificial Neural Networks; Multivariate Adaptive Regression Spline model; Mix design; Compressive strength
Fields of Research (2008): 09 Engineering > 0905 Civil Engineering > 090503 Construction Materials
09 Engineering > 0905 Civil Engineering > 090506 Structural Engineering
09 Engineering > 0912 Materials Engineering > 091202 Composite and Hybrid Materials
Fields of Research (2020): 40 ENGINEERING > 4005 Civil engineering > 400510 Structural engineering
40 ENGINEERING > 4016 Materials engineering > 401602 Composite and hybrid materials
40 ENGINEERING > 4005 Civil engineering > 400505 Construction materials
Socio-Economic Objectives (2008): E Expanding Knowledge > 97 Expanding Knowledge > 970109 Expanding Knowledge in Engineering
Socio-Economic Objectives (2020): 28 EXPANDING KNOWLEDGE > 2801 Expanding knowledge > 280110 Expanding knowledge in engineering
12 CONSTRUCTION > 1203 Construction materials performance and processes > 120301 Cement and concrete materials
Identification Number or DOI: doi:10.14359/51727019
URI: http://eprints.usq.edu.au/id/eprint/41184

Actions (login required)

View Item Archive Repository Staff Only