Fatigue life prediction of sandwich composite materials under flexural tests using a Bayesian trained artificial neural network

A. Bezazi, S.G. Pierce, K. Worden, E. Harkati

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

The authors discuss the use of an artificial neural network (ANN) to estimate fatigue lifetime of a sandwich composite material structure subjected to cyclic three-point bending loads. A total of 27 samples (three different loading levels for nine samples each) were investigated to provide training, validation and testing data for a series of multi-layer perceptron ANNs. The networks were implemented using both conventional maximum likelihood and Bayesian evidence based training algorithms. It was found that the Bayesian evidence based approach provided a superior and smoother fit to the experimental data. Completely independent fatigue tests were conducted at intermediate levels of loading to evaluate the capacity of the fitted ANN model to interpolate to previously unseen regions of data. Excellent agreement was obtained between the model predicted outputs and the new experimental data. The capability and estimation of predication error when using the Bayesian technique is discussed along with the application of the model to generate classical S–N lifetime curves.
Original languageEnglish
Pages (from-to)738-747
Number of pages10
JournalInternational Journal of Fatigue
Volume29
Issue number4
Early online date6 Sep 2006
DOIs
Publication statusPublished - Apr 2007

Fingerprint

Fatigue Life Prediction
Sandwich
Composite Materials
Artificial Neural Network
Fatigue of materials
Neural networks
Fatigue
Lifetime
Composite materials
Experimental Data
Training Algorithm
Multilayer neural networks
Perceptron
Neural Network Model
Maximum likelihood
Maximum Likelihood
Multilayer
Interpolate
Testing
Curve

Keywords

  • sandwich composites
  • fatigue
  • neural networks
  • lifetime prediction

Cite this

@article{ee51293523e04e71ab54f22b47101ebb,
title = "Fatigue life prediction of sandwich composite materials under flexural tests using a Bayesian trained artificial neural network",
abstract = "The authors discuss the use of an artificial neural network (ANN) to estimate fatigue lifetime of a sandwich composite material structure subjected to cyclic three-point bending loads. A total of 27 samples (three different loading levels for nine samples each) were investigated to provide training, validation and testing data for a series of multi-layer perceptron ANNs. The networks were implemented using both conventional maximum likelihood and Bayesian evidence based training algorithms. It was found that the Bayesian evidence based approach provided a superior and smoother fit to the experimental data. Completely independent fatigue tests were conducted at intermediate levels of loading to evaluate the capacity of the fitted ANN model to interpolate to previously unseen regions of data. Excellent agreement was obtained between the model predicted outputs and the new experimental data. The capability and estimation of predication error when using the Bayesian technique is discussed along with the application of the model to generate classical S–N lifetime curves.",
keywords = "sandwich composites, fatigue, neural networks, lifetime prediction",
author = "A. Bezazi and S.G. Pierce and K. Worden and E. Harkati",
year = "2007",
month = "4",
doi = "10.1016/j.ijfatigue.2006.06.013",
language = "English",
volume = "29",
pages = "738--747",
journal = "International Journal of Fatigue",
issn = "0142-1123",
number = "4",

}

Fatigue life prediction of sandwich composite materials under flexural tests using a Bayesian trained artificial neural network. / Bezazi, A.; Pierce, S.G.; Worden, K.; Harkati, E.

In: International Journal of Fatigue, Vol. 29, No. 4, 04.2007, p. 738-747.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fatigue life prediction of sandwich composite materials under flexural tests using a Bayesian trained artificial neural network

AU - Bezazi, A.

AU - Pierce, S.G.

AU - Worden, K.

AU - Harkati, E.

PY - 2007/4

Y1 - 2007/4

N2 - The authors discuss the use of an artificial neural network (ANN) to estimate fatigue lifetime of a sandwich composite material structure subjected to cyclic three-point bending loads. A total of 27 samples (three different loading levels for nine samples each) were investigated to provide training, validation and testing data for a series of multi-layer perceptron ANNs. The networks were implemented using both conventional maximum likelihood and Bayesian evidence based training algorithms. It was found that the Bayesian evidence based approach provided a superior and smoother fit to the experimental data. Completely independent fatigue tests were conducted at intermediate levels of loading to evaluate the capacity of the fitted ANN model to interpolate to previously unseen regions of data. Excellent agreement was obtained between the model predicted outputs and the new experimental data. The capability and estimation of predication error when using the Bayesian technique is discussed along with the application of the model to generate classical S–N lifetime curves.

AB - The authors discuss the use of an artificial neural network (ANN) to estimate fatigue lifetime of a sandwich composite material structure subjected to cyclic three-point bending loads. A total of 27 samples (three different loading levels for nine samples each) were investigated to provide training, validation and testing data for a series of multi-layer perceptron ANNs. The networks were implemented using both conventional maximum likelihood and Bayesian evidence based training algorithms. It was found that the Bayesian evidence based approach provided a superior and smoother fit to the experimental data. Completely independent fatigue tests were conducted at intermediate levels of loading to evaluate the capacity of the fitted ANN model to interpolate to previously unseen regions of data. Excellent agreement was obtained between the model predicted outputs and the new experimental data. The capability and estimation of predication error when using the Bayesian technique is discussed along with the application of the model to generate classical S–N lifetime curves.

KW - sandwich composites

KW - fatigue

KW - neural networks

KW - lifetime prediction

U2 - 10.1016/j.ijfatigue.2006.06.013

DO - 10.1016/j.ijfatigue.2006.06.013

M3 - Article

VL - 29

SP - 738

EP - 747

JO - International Journal of Fatigue

JF - International Journal of Fatigue

SN - 0142-1123

IS - 4

ER -