Přístupnostní navigace
E-application
Search Search Close
Publication detail
LEHKÝ, D. ŠOMODÍKOVÁ, M.
Original Title
Utilization of Artificial Neural Network Based Response Surface Method for Reliability Analysis of Structures
Type
abstract
Language
English
Original Abstract
The key step of the reliability and lifetime assessment of structures is the determination of reliability level, described by failure probability or reliability index. Some of the simulation or approximation techniques can be used for this purpose. In case of large structures analyzed using the nonlinear finite element method, it is necessary to develop more efficient procedures, reducing the number of evaluations of original limit state function to a minimum. Here, artificial neural network based response surface method in combination with small-sample simulation technique Latin Hypercube Sampling is utilized for the approximation of a limit state function. Thanks to ability of artificial neural network to generalize it is efficient to fit limit state function with a sufficiently small number of simulations.
Keywords
artificial neural network, Latin hypercube sampling, load bearing capacity, probability of failure, reliability index
Authors
LEHKÝ, D.; ŠOMODÍKOVÁ, M.
Released
11. 5. 2015
Publisher
Náprstek, J. & Fischer, C.
Location
Svratka, Česká republika
ISBN
978-80-86246-42-0
Book
Engineering Mechanics 2015 – 21st International Conference: Extended Abstracts, May 11–14, 2015, Svratka, Czech Republic
Pages from
182
Pages to
183
Pages count
2
BibTex
@misc{BUT120743, author="David {Lehký} and Martina {Sadílková Šomodíková}", title="Utilization of Artificial Neural Network Based Response Surface Method for Reliability Analysis of Structures", booktitle="Engineering Mechanics 2015 – 21st International Conference: Extended Abstracts, May 11–14, 2015, Svratka, Czech Republic", year="2015", pages="182--183", publisher="Náprstek, J. & Fischer, C.", address="Svratka, Česká republika", isbn="978-80-86246-42-0", note="abstract" }