Creep predicting model in masonry structure utilizing dynamic neural network

Mustafa M. Abed, A. El-Shafie, Siti Aminah Osman

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Problem statement: When the loads are applied to a brickwork structure, visco-elastic behavior upon their stress-strain relationships is exhibited, where the response can be classified into two separate parts: an instantaneous elastic strains and time-dependent creep strains. The creep strain represents the non-instantaneous strain that happens with time when the stress is sustained. Through the previous century, along with the alter in brickwork construction, A chain of creep tests on brickwork has shown that creep in brickwork be able to result in deformation that rise gradually with the way of time. Brickwork has considerable creep strain that is complicated to predict because of its reliance on several unrestrained parameters (e.g., relative humidity, time of load application, stress level). Dependable and precise prediction models for the long term, time-dependent creep deformation of brickwork structures are required. Artificial Neural Network (ANN) models have been determined useful and efficient especially in such problems for which the characteristics of the processes are difficult to describe using numerical models. Approach: This study introduces a creep prediction model based Focused Time-Delay Neural Network (FTDNN) which could detect and consider within its architecture the time dependency which is major factor in creep deformation in brickwork structure. Results: Performance of the proposed FTDNN model was examined with experimental creep data from brickwork assemblages collected over the last 15 years. Results showed that the FTDNN model has a relatively small prediction error compared to the other models with the error less than 15%. Conclusion: The results showed that the FTDNN model outperformed the existing ANN models and significantly enhance the accuracy of creep prediction.

Original languageEnglish
Pages (from-to)597-605
Number of pages9
JournalJournal of Computer Science
Volume6
Issue number5
DOIs
Publication statusPublished - 2010

Fingerprint

Creep
Neural networks
Time delay
Numerical models
Loads (forces)
Atmospheric humidity

Keywords

  • Creep predicting
  • Dynamic neural network
  • Masonry

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

Creep predicting model in masonry structure utilizing dynamic neural network. / Abed, Mustafa M.; El-Shafie, A.; Osman, Siti Aminah.

In: Journal of Computer Science, Vol. 6, No. 5, 2010, p. 597-605.

Research output: Contribution to journalArticle

@article{97502ee6a53d48c48cc53bbf04f73416,
title = "Creep predicting model in masonry structure utilizing dynamic neural network",
abstract = "Problem statement: When the loads are applied to a brickwork structure, visco-elastic behavior upon their stress-strain relationships is exhibited, where the response can be classified into two separate parts: an instantaneous elastic strains and time-dependent creep strains. The creep strain represents the non-instantaneous strain that happens with time when the stress is sustained. Through the previous century, along with the alter in brickwork construction, A chain of creep tests on brickwork has shown that creep in brickwork be able to result in deformation that rise gradually with the way of time. Brickwork has considerable creep strain that is complicated to predict because of its reliance on several unrestrained parameters (e.g., relative humidity, time of load application, stress level). Dependable and precise prediction models for the long term, time-dependent creep deformation of brickwork structures are required. Artificial Neural Network (ANN) models have been determined useful and efficient especially in such problems for which the characteristics of the processes are difficult to describe using numerical models. Approach: This study introduces a creep prediction model based Focused Time-Delay Neural Network (FTDNN) which could detect and consider within its architecture the time dependency which is major factor in creep deformation in brickwork structure. Results: Performance of the proposed FTDNN model was examined with experimental creep data from brickwork assemblages collected over the last 15 years. Results showed that the FTDNN model has a relatively small prediction error compared to the other models with the error less than 15{\%}. Conclusion: The results showed that the FTDNN model outperformed the existing ANN models and significantly enhance the accuracy of creep prediction.",
keywords = "Creep predicting, Dynamic neural network, Masonry",
author = "Abed, {Mustafa M.} and A. El-Shafie and Osman, {Siti Aminah}",
year = "2010",
doi = "10.3844/jcssp.2010.597.605",
language = "English",
volume = "6",
pages = "597--605",
journal = "Journal of Computer Science",
issn = "1549-3636",
publisher = "Science Publications",
number = "5",

}

TY - JOUR

T1 - Creep predicting model in masonry structure utilizing dynamic neural network

AU - Abed, Mustafa M.

AU - El-Shafie, A.

AU - Osman, Siti Aminah

PY - 2010

Y1 - 2010

N2 - Problem statement: When the loads are applied to a brickwork structure, visco-elastic behavior upon their stress-strain relationships is exhibited, where the response can be classified into two separate parts: an instantaneous elastic strains and time-dependent creep strains. The creep strain represents the non-instantaneous strain that happens with time when the stress is sustained. Through the previous century, along with the alter in brickwork construction, A chain of creep tests on brickwork has shown that creep in brickwork be able to result in deformation that rise gradually with the way of time. Brickwork has considerable creep strain that is complicated to predict because of its reliance on several unrestrained parameters (e.g., relative humidity, time of load application, stress level). Dependable and precise prediction models for the long term, time-dependent creep deformation of brickwork structures are required. Artificial Neural Network (ANN) models have been determined useful and efficient especially in such problems for which the characteristics of the processes are difficult to describe using numerical models. Approach: This study introduces a creep prediction model based Focused Time-Delay Neural Network (FTDNN) which could detect and consider within its architecture the time dependency which is major factor in creep deformation in brickwork structure. Results: Performance of the proposed FTDNN model was examined with experimental creep data from brickwork assemblages collected over the last 15 years. Results showed that the FTDNN model has a relatively small prediction error compared to the other models with the error less than 15%. Conclusion: The results showed that the FTDNN model outperformed the existing ANN models and significantly enhance the accuracy of creep prediction.

AB - Problem statement: When the loads are applied to a brickwork structure, visco-elastic behavior upon their stress-strain relationships is exhibited, where the response can be classified into two separate parts: an instantaneous elastic strains and time-dependent creep strains. The creep strain represents the non-instantaneous strain that happens with time when the stress is sustained. Through the previous century, along with the alter in brickwork construction, A chain of creep tests on brickwork has shown that creep in brickwork be able to result in deformation that rise gradually with the way of time. Brickwork has considerable creep strain that is complicated to predict because of its reliance on several unrestrained parameters (e.g., relative humidity, time of load application, stress level). Dependable and precise prediction models for the long term, time-dependent creep deformation of brickwork structures are required. Artificial Neural Network (ANN) models have been determined useful and efficient especially in such problems for which the characteristics of the processes are difficult to describe using numerical models. Approach: This study introduces a creep prediction model based Focused Time-Delay Neural Network (FTDNN) which could detect and consider within its architecture the time dependency which is major factor in creep deformation in brickwork structure. Results: Performance of the proposed FTDNN model was examined with experimental creep data from brickwork assemblages collected over the last 15 years. Results showed that the FTDNN model has a relatively small prediction error compared to the other models with the error less than 15%. Conclusion: The results showed that the FTDNN model outperformed the existing ANN models and significantly enhance the accuracy of creep prediction.

KW - Creep predicting

KW - Dynamic neural network

KW - Masonry

UR - http://www.scopus.com/inward/record.url?scp=78049524398&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78049524398&partnerID=8YFLogxK

U2 - 10.3844/jcssp.2010.597.605

DO - 10.3844/jcssp.2010.597.605

M3 - Article

AN - SCOPUS:78049524398

VL - 6

SP - 597

EP - 605

JO - Journal of Computer Science

JF - Journal of Computer Science

SN - 1549-3636

IS - 5

ER -