Neural network simulator model for optimization in high performance concrete mix design

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

High performance concrete is a highly complex material which involves many variables and includes various mineral and chemical admixtures which makes modeling its behavior a very difficult task. There is no systematic method in mix design for HPC similar to those developed for normal concrete. Since the types and amounts of admixtures may have a great influence on the strength characteristics and workability of HPC mixtures, a different approach is needed for determining the mix proportions of HPC instead of traditional method. To date, most of the method of mix design of HPC were based solely on trial and error and its involved large numbers of mixing and testing. As the cost of materials and labor increase, optimizing HPC mix proportions is more desirable. Furthermore, the complex properties and behavior of high performance concrete is hard to model with traditional mathematical tools. This study is aimed at demonstrating the possibilities of adapting ANN in the development of simulator and intelligent system and to predict the compressive strength and workability of High performance concrete. Training and testing the network will start immediately prior to the completion of the simulator development and data preparation. The training will follows exactly to the designed algorithm of the simulator. The developed neural network simulator model by using the back propagation architecture has demonstrated its ability in training the given input/output patterns. The application of artificial intelligence in the field of HPC mix design is very appropriate in order to preserve and disseminate valuable experience and innovation efficiently at reasonable cost.

Original languageEnglish
Pages (from-to)61-68
Number of pages8
JournalEuropean Journal of Scientific Research
Volume34
Issue number1
Publication statusPublished - 2009

Fingerprint

High performance concrete
Neural Networks (Computer)
Concrete mixtures
neural networks
simulator
Simulator
High Performance
Simulators
Neural Networks
Neural networks
Optimization
artificial intelligence
Compressive Strength
Costs and Cost Analysis
Proportion
Artificial Intelligence
Behavior Modeling
Testing
Minerals
Trial and error

Keywords

  • Artificial neural network
  • High performance concrete
  • Mix design
  • Strength
  • Workability

ASJC Scopus subject areas

  • General

Cite this

@article{e5510a29b8c34523a614b827424e01d3,
title = "Neural network simulator model for optimization in high performance concrete mix design",
abstract = "High performance concrete is a highly complex material which involves many variables and includes various mineral and chemical admixtures which makes modeling its behavior a very difficult task. There is no systematic method in mix design for HPC similar to those developed for normal concrete. Since the types and amounts of admixtures may have a great influence on the strength characteristics and workability of HPC mixtures, a different approach is needed for determining the mix proportions of HPC instead of traditional method. To date, most of the method of mix design of HPC were based solely on trial and error and its involved large numbers of mixing and testing. As the cost of materials and labor increase, optimizing HPC mix proportions is more desirable. Furthermore, the complex properties and behavior of high performance concrete is hard to model with traditional mathematical tools. This study is aimed at demonstrating the possibilities of adapting ANN in the development of simulator and intelligent system and to predict the compressive strength and workability of High performance concrete. Training and testing the network will start immediately prior to the completion of the simulator development and data preparation. The training will follows exactly to the designed algorithm of the simulator. The developed neural network simulator model by using the back propagation architecture has demonstrated its ability in training the given input/output patterns. The application of artificial intelligence in the field of HPC mix design is very appropriate in order to preserve and disseminate valuable experience and innovation efficiently at reasonable cost.",
keywords = "Artificial neural network, High performance concrete, Mix design, Strength, Workability",
author = "Maslina Jamil and {Mohd. Zain}, {Muhammad Fauzi} and Hassan Basri",
year = "2009",
language = "English",
volume = "34",
pages = "61--68",
journal = "European Journal of Scientific Research",
issn = "1450-202X",
publisher = "European Journals Inc.",
number = "1",

}

TY - JOUR

T1 - Neural network simulator model for optimization in high performance concrete mix design

AU - Jamil, Maslina

AU - Mohd. Zain, Muhammad Fauzi

AU - Basri, Hassan

PY - 2009

Y1 - 2009

N2 - High performance concrete is a highly complex material which involves many variables and includes various mineral and chemical admixtures which makes modeling its behavior a very difficult task. There is no systematic method in mix design for HPC similar to those developed for normal concrete. Since the types and amounts of admixtures may have a great influence on the strength characteristics and workability of HPC mixtures, a different approach is needed for determining the mix proportions of HPC instead of traditional method. To date, most of the method of mix design of HPC were based solely on trial and error and its involved large numbers of mixing and testing. As the cost of materials and labor increase, optimizing HPC mix proportions is more desirable. Furthermore, the complex properties and behavior of high performance concrete is hard to model with traditional mathematical tools. This study is aimed at demonstrating the possibilities of adapting ANN in the development of simulator and intelligent system and to predict the compressive strength and workability of High performance concrete. Training and testing the network will start immediately prior to the completion of the simulator development and data preparation. The training will follows exactly to the designed algorithm of the simulator. The developed neural network simulator model by using the back propagation architecture has demonstrated its ability in training the given input/output patterns. The application of artificial intelligence in the field of HPC mix design is very appropriate in order to preserve and disseminate valuable experience and innovation efficiently at reasonable cost.

AB - High performance concrete is a highly complex material which involves many variables and includes various mineral and chemical admixtures which makes modeling its behavior a very difficult task. There is no systematic method in mix design for HPC similar to those developed for normal concrete. Since the types and amounts of admixtures may have a great influence on the strength characteristics and workability of HPC mixtures, a different approach is needed for determining the mix proportions of HPC instead of traditional method. To date, most of the method of mix design of HPC were based solely on trial and error and its involved large numbers of mixing and testing. As the cost of materials and labor increase, optimizing HPC mix proportions is more desirable. Furthermore, the complex properties and behavior of high performance concrete is hard to model with traditional mathematical tools. This study is aimed at demonstrating the possibilities of adapting ANN in the development of simulator and intelligent system and to predict the compressive strength and workability of High performance concrete. Training and testing the network will start immediately prior to the completion of the simulator development and data preparation. The training will follows exactly to the designed algorithm of the simulator. The developed neural network simulator model by using the back propagation architecture has demonstrated its ability in training the given input/output patterns. The application of artificial intelligence in the field of HPC mix design is very appropriate in order to preserve and disseminate valuable experience and innovation efficiently at reasonable cost.

KW - Artificial neural network

KW - High performance concrete

KW - Mix design

KW - Strength

KW - Workability

UR - http://www.scopus.com/inward/record.url?scp=68849090458&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=68849090458&partnerID=8YFLogxK

M3 - Article

VL - 34

SP - 61

EP - 68

JO - European Journal of Scientific Research

JF - European Journal of Scientific Research

SN - 1450-202X

IS - 1

ER -