Reliability analysis of structures using neural network method

A.Hosni Elhewy, E. Mesbahi, Y. Pu

Research output: Contribution to journalArticle

122 Citations (Scopus)

Abstract

In order to predict the failure probability of a complicated structure, the structural responses usually need to be estimated by a numerical procedure, such as finite element method. To reduce the computational effort required for reliability analysis, response surface method could be used. However the conventional response surface method is still time consuming especially when the number of random variables is large. In this paper, an artificial neural network (ANN)-based response surface method is proposed. In this method, the relation between the random variables (input) and structural responses is established using ANN models. ANN model is then connected to a reliability method, such as first order and second moment (FORM), or Monte Carlo simulation method (MCS), to predict the failure probability. The proposed method is applied to four examples to validate its accuracy and efficiency. The obtained results show that the ANN-based response surface method is more efficient and accurate than the conventional response surface method.

Original languageEnglish
Pages (from-to)44-53
JournalProbabilistic Engineering Mechanics
Volume21
Issue number1
DOIs
Publication statusPublished - Jan 2006
Externally publishedYes

Keywords

  • artificial neural network
  • reliability analysis
  • response surface method
  • composite material

Cite this

@article{6f8ee604b9594a22bb092feefa356556,
title = "Reliability analysis of structures using neural network method",
abstract = "In order to predict the failure probability of a complicated structure, the structural responses usually need to be estimated by a numerical procedure, such as finite element method. To reduce the computational effort required for reliability analysis, response surface method could be used. However the conventional response surface method is still time consuming especially when the number of random variables is large. In this paper, an artificial neural network (ANN)-based response surface method is proposed. In this method, the relation between the random variables (input) and structural responses is established using ANN models. ANN model is then connected to a reliability method, such as first order and second moment (FORM), or Monte Carlo simulation method (MCS), to predict the failure probability. The proposed method is applied to four examples to validate its accuracy and efficiency. The obtained results show that the ANN-based response surface method is more efficient and accurate than the conventional response surface method.",
keywords = "artificial neural network, reliability analysis, response surface method, composite material",
author = "A.Hosni Elhewy and E. Mesbahi and Y. Pu",
year = "2006",
month = "1",
doi = "10.1016/j.probengmech.2005.07.002",
language = "English",
volume = "21",
pages = "44--53",
journal = "Probabilistic Engineering Mechanics",
issn = "0266-8920",
publisher = "Elsevier B.V.",
number = "1",

}

Reliability analysis of structures using neural network method. / Elhewy, A.Hosni ; Mesbahi, E.; Pu, Y.

In: Probabilistic Engineering Mechanics, Vol. 21, No. 1, 01.2006, p. 44-53.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Reliability analysis of structures using neural network method

AU - Elhewy, A.Hosni

AU - Mesbahi, E.

AU - Pu, Y.

PY - 2006/1

Y1 - 2006/1

N2 - In order to predict the failure probability of a complicated structure, the structural responses usually need to be estimated by a numerical procedure, such as finite element method. To reduce the computational effort required for reliability analysis, response surface method could be used. However the conventional response surface method is still time consuming especially when the number of random variables is large. In this paper, an artificial neural network (ANN)-based response surface method is proposed. In this method, the relation between the random variables (input) and structural responses is established using ANN models. ANN model is then connected to a reliability method, such as first order and second moment (FORM), or Monte Carlo simulation method (MCS), to predict the failure probability. The proposed method is applied to four examples to validate its accuracy and efficiency. The obtained results show that the ANN-based response surface method is more efficient and accurate than the conventional response surface method.

AB - In order to predict the failure probability of a complicated structure, the structural responses usually need to be estimated by a numerical procedure, such as finite element method. To reduce the computational effort required for reliability analysis, response surface method could be used. However the conventional response surface method is still time consuming especially when the number of random variables is large. In this paper, an artificial neural network (ANN)-based response surface method is proposed. In this method, the relation between the random variables (input) and structural responses is established using ANN models. ANN model is then connected to a reliability method, such as first order and second moment (FORM), or Monte Carlo simulation method (MCS), to predict the failure probability. The proposed method is applied to four examples to validate its accuracy and efficiency. The obtained results show that the ANN-based response surface method is more efficient and accurate than the conventional response surface method.

KW - artificial neural network

KW - reliability analysis

KW - response surface method

KW - composite material

U2 - 10.1016/j.probengmech.2005.07.002

DO - 10.1016/j.probengmech.2005.07.002

M3 - Article

VL - 21

SP - 44

EP - 53

JO - Probabilistic Engineering Mechanics

JF - Probabilistic Engineering Mechanics

SN - 0266-8920

IS - 1

ER -