Journal Published Online: 14 January 2019
Volume 8, Issue 1

An Artificial Intelligence Model for Computing Optimum Fly Ash Content for Structural-Grade Concrete

CODEN: ACEMF9

Abstract

Recent research has led to a point where a substantial number of industrial by-products with pozzolanic behavior can be used along with ordinary portland cement (OPC) without compromising the desired mechanical and durability properties. Literature reveals that fly ash, which is typically processed by burning ground coal in power plants, can easily replace up to 30–40 % of OPC, depending on its amorphous reactivity content, particle size, and loss on ignition content. The aim of this article is to determine the optimum amount of fly ash to be used as a critical factor for structural-grade concrete. A computational mathematical model is formulated using an artificial intelligence (AI) approach, such as an automated neural network search (ANS) modeling to explore the influence of mix designs on concrete compressive strength at 28 days. A total of 69 mixes were selected for formulation of the ANS model so that it could have decent precision, accuracy, and robust computing. The formulated computational ANS model was able to capture the complex relationship between compressive strength and different mix design parameters. Among all, percentage of fly ash was found to have the highest impact on 28-day strength development in high-volume fly ash concrete. The developed AI-based ANS model can be useful to researchers to accurately predict the mix design components for a structural-grade concrete. It can also be further improved by optimizing parameter setting in the network algorithm.

Author Information

Chandra Paul, Suvash
Civil Engineering, School of Engineering, Bandar Sunway, Subang Jaya, Selangor, Malaysia
Panda, Biranchi
IDMEC, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
Zhu, Hong-Hu
School of Earth Sciences and Engineering, Nanjing University, Nanjing, China
Garg, Ankit
Department of Civil and Environmental Engineering, Shantou University, Shantou, China
Pages: 15
Price: $25.00
Related
Reprints and Permissions
Reprints and copyright permissions can be requested through the
Copyright Clearance Center
Details
Stock #: ACEM20180079
ISSN: 2379-1357
DOI: 10.1520/ACEM20180079