Detail publikačního výsledku

Application of soft computing techniques for reliability calculation of time demanding problems

ŠOMODÍKOVÁ, M.; LEHKÝ, D.

Originální název

Application of soft computing techniques for reliability calculation of time demanding problems

Anglický název

Application of soft computing techniques for reliability calculation of time demanding problems

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

The reliability analysis of complex structural systems requires utilization of approximation methods for calculation of reliability measures with the view of reduction of computational efforts to an acceptable level. In the paper, an artificial neural network based response surface method in combination with the small-sample simulation technique is presented. An artificial neural network is used as a surrogate model for approximation of original limit state function. Efficiency is emphasized by utilization of the stratified simulation for the selection of neural network training set elements. Response surface obtained is independent of the type of distribution or correlations among the basic variables which enables sensitivity studies with respect to these parameters without much computational effort. Subsequently, the ANN surrogate model is utilized in conjunction with Monte Carlo simulation method to obtain desired reliability measures. The proposed method is tested using nonlinear limit state function taken from the literature as well as employed for reliability assessment of concrete bridge.

Anglický abstrakt

The reliability analysis of complex structural systems requires utilization of approximation methods for calculation of reliability measures with the view of reduction of computational efforts to an acceptable level. In the paper, an artificial neural network based response surface method in combination with the small-sample simulation technique is presented. An artificial neural network is used as a surrogate model for approximation of original limit state function. Efficiency is emphasized by utilization of the stratified simulation for the selection of neural network training set elements. Response surface obtained is independent of the type of distribution or correlations among the basic variables which enables sensitivity studies with respect to these parameters without much computational effort. Subsequently, the ANN surrogate model is utilized in conjunction with Monte Carlo simulation method to obtain desired reliability measures. The proposed method is tested using nonlinear limit state function taken from the literature as well as employed for reliability assessment of concrete bridge.

Klíčová slova

reliability, failure probability, artificial neural networks

Klíčová slova v angličtině

reliability, failure probability, artificial neural networks

Autoři

ŠOMODÍKOVÁ, M.; LEHKÝ, D.

Rok RIV

2016

Vydáno

07.09.2015

Nakladatel

L. Podofillini et al.

Místo

Curych, Švýcarsko

ISBN

978-1-138-02879-1

Kniha

Safety and Reliability of Complex Engineered Systems: Proceedings of the 25th European Safety and Reliability Conference, ESREL 2015, Zürich, Switzerland, 7–10 September 2015

Strany od

4151

Strany do

4159

Strany počet

9

BibTex

@inproceedings{BUT120713,
  author="Martina {Sadílková Šomodíková} and David {Lehký}",
  title="Application of soft computing techniques for reliability calculation of time demanding problems",
  booktitle="Safety and Reliability of Complex Engineered Systems: Proceedings of the 25th European Safety and Reliability Conference, ESREL 2015, Zürich, Switzerland, 7–10 September 2015",
  year="2015",
  pages="4151--4159",
  publisher="L. Podofillini et al.",
  address="Curych, Švýcarsko",
  isbn="978-1-138-02879-1"
}