An evolutionary-based prediction model of the 28-day compressive strength of high-performance concrete containing cementitious materials

Ehsan Sadrossadat, Hakan Basarir

Research output: Contribution to journalArticle

Abstract

High-performance concrete (HPC) is a class of concretes that may contain more cementitious materials other than portland cement, such as fly ash and blast furnace slag, in addition to chemical admixtures, e.g., plasticizers. Strength, durability, and rheological properties of the normal concrete are enhanced in HPC. The compressive strength of HPC can be considered as a key factor to identify the level of its quality in concrete technology and the construction industry. This parameter can be directly acquired by experimental observations. However, testing methods are often time consuming, expensive, or inefficient. This article aims to develop and propose a new mathematical equation formulating the compressive strength of HPC specimens 28 days in age through a robust artificial intelligence algorithm known as linear genetic programming (LGP) using a valuable experimental database. The LGP-based model proposed here can be used for manual calculations and is able to estimate the compressive strength of HPC samples with a good degree of accuracy. The performance of the LGP model is confirmed through comparing the results with those provided by other models. The sensitivity analysis is also conducted, and it is concluded that the amount of cementitious materials, such as cement and furnace slag, have more influence than other variables.

Original languageEnglish
Number of pages14
JournalAdvances in Civil Engineering Materials
Volume8
Issue number3
DOIs
Publication statusPublished - 29 May 2019

Fingerprint

High performance concrete
Compressive strength
Genetic programming
Concretes
Slags
Coal Ash
Plasticizers
Portland cement
Construction industry
Fly ash
Sensitivity analysis
Artificial intelligence
Cements
Durability
Furnaces
Testing

Cite this

@article{296aeaecd4a64ab7bd17e8650245ef7e,
title = "An evolutionary-based prediction model of the 28-day compressive strength of high-performance concrete containing cementitious materials",
abstract = "High-performance concrete (HPC) is a class of concretes that may contain more cementitious materials other than portland cement, such as fly ash and blast furnace slag, in addition to chemical admixtures, e.g., plasticizers. Strength, durability, and rheological properties of the normal concrete are enhanced in HPC. The compressive strength of HPC can be considered as a key factor to identify the level of its quality in concrete technology and the construction industry. This parameter can be directly acquired by experimental observations. However, testing methods are often time consuming, expensive, or inefficient. This article aims to develop and propose a new mathematical equation formulating the compressive strength of HPC specimens 28 days in age through a robust artificial intelligence algorithm known as linear genetic programming (LGP) using a valuable experimental database. The LGP-based model proposed here can be used for manual calculations and is able to estimate the compressive strength of HPC samples with a good degree of accuracy. The performance of the LGP model is confirmed through comparing the results with those provided by other models. The sensitivity analysis is also conducted, and it is concluded that the amount of cementitious materials, such as cement and furnace slag, have more influence than other variables.",
keywords = "Blast furnace slag, Compressive strength, Fly ash, High-performance concrete, Linear genetic programming, Predictive modeling",
author = "Ehsan Sadrossadat and Hakan Basarir",
year = "2019",
month = "5",
day = "29",
doi = "10.1520/ACEM20190016",
language = "English",
volume = "8",
journal = "Advances in Civil Engineering Materials",
issn = "2379-1357",
publisher = "ASTM International",
number = "3",

}

TY - JOUR

T1 - An evolutionary-based prediction model of the 28-day compressive strength of high-performance concrete containing cementitious materials

AU - Sadrossadat, Ehsan

AU - Basarir, Hakan

PY - 2019/5/29

Y1 - 2019/5/29

N2 - High-performance concrete (HPC) is a class of concretes that may contain more cementitious materials other than portland cement, such as fly ash and blast furnace slag, in addition to chemical admixtures, e.g., plasticizers. Strength, durability, and rheological properties of the normal concrete are enhanced in HPC. The compressive strength of HPC can be considered as a key factor to identify the level of its quality in concrete technology and the construction industry. This parameter can be directly acquired by experimental observations. However, testing methods are often time consuming, expensive, or inefficient. This article aims to develop and propose a new mathematical equation formulating the compressive strength of HPC specimens 28 days in age through a robust artificial intelligence algorithm known as linear genetic programming (LGP) using a valuable experimental database. The LGP-based model proposed here can be used for manual calculations and is able to estimate the compressive strength of HPC samples with a good degree of accuracy. The performance of the LGP model is confirmed through comparing the results with those provided by other models. The sensitivity analysis is also conducted, and it is concluded that the amount of cementitious materials, such as cement and furnace slag, have more influence than other variables.

AB - High-performance concrete (HPC) is a class of concretes that may contain more cementitious materials other than portland cement, such as fly ash and blast furnace slag, in addition to chemical admixtures, e.g., plasticizers. Strength, durability, and rheological properties of the normal concrete are enhanced in HPC. The compressive strength of HPC can be considered as a key factor to identify the level of its quality in concrete technology and the construction industry. This parameter can be directly acquired by experimental observations. However, testing methods are often time consuming, expensive, or inefficient. This article aims to develop and propose a new mathematical equation formulating the compressive strength of HPC specimens 28 days in age through a robust artificial intelligence algorithm known as linear genetic programming (LGP) using a valuable experimental database. The LGP-based model proposed here can be used for manual calculations and is able to estimate the compressive strength of HPC samples with a good degree of accuracy. The performance of the LGP model is confirmed through comparing the results with those provided by other models. The sensitivity analysis is also conducted, and it is concluded that the amount of cementitious materials, such as cement and furnace slag, have more influence than other variables.

KW - Blast furnace slag

KW - Compressive strength

KW - Fly ash

KW - High-performance concrete

KW - Linear genetic programming

KW - Predictive modeling

UR - http://www.scopus.com/inward/record.url?scp=85071325092&partnerID=8YFLogxK

U2 - 10.1520/ACEM20190016

DO - 10.1520/ACEM20190016

M3 - Article

VL - 8

JO - Advances in Civil Engineering Materials

JF - Advances in Civil Engineering Materials

SN - 2379-1357

IS - 3

ER -