Publication detail

Metodika použití umělých neuronových sítí pro identifikaci parametrů výpočtových modelů konstrukcí

NOVÁK, D. LEHKÝ, D.

Original Title

Metodika použití umělých neuronových sítí pro identifikaci parametrů výpočtových modelů konstrukcí

English Title

Methodology of using artificial neural networks for identification of computational model parameters

Type

conference paper

Language

Czech

Original Abstract

The paper suggests a new approach of inverse analysis to obtain parameters of FEM computational model in order to obtain best agreement with experimental data. The proposed inverse analysis approach is based on coupling of FEM computational model and the stochastic training of artificial neural network. Identification parameters play the role of basic random variables with a scatter reflecting the physical range of possible values. Novelty of the approach is the utilization of efficient small-sample simulation method Latin Hypercube Sampling (LHS) used for stochastic training of neural network. Once the network is trained it represents an approximation consequently utilized in an opposite way: For given experimental data to provide the best possible set of model parameters. The approach is general and can be applied easily to any inverse problem of engineering mechanics.

English abstract

The paper suggests a new approach of inverse analysis to obtain parameters of FEM computational model in order to obtain best agreement with experimental data. The proposed inverse analysis approach is based on coupling of FEM computational model and the stochastic training of artificial neural network. Identification parameters play the role of basic random variables with a scatter reflecting the physical range of possible values. Novelty of the approach is the utilization of efficient small-sample simulation method Latin Hypercube Sampling (LHS) used for stochastic training of neural network. Once the network is trained it represents an approximation consequently utilized in an opposite way: For given experimental data to provide the best possible set of model parameters. The approach is general and can be applied easily to any inverse problem of engineering mechanics.

Key words in English

Inverse analysis, computational model, stochastic neural network, small-sample simulation.

Authors

NOVÁK, D.; LEHKÝ, D.

RIV year

2006

Released

11. 5. 2006

Location

Brno, ČR

ISBN

80-214-3164-4

Book

Dynamicky namáhané konstrukce - DYNA

Pages from

115

Pages to

122

Pages count

8

BibTex

@inproceedings{BUT24290,
  author="Drahomír {Novák} and David {Lehký}",
  title="Metodika použití umělých neuronových sítí pro identifikaci parametrů výpočtových modelů konstrukcí",
  booktitle="Dynamicky namáhané konstrukce - DYNA",
  year="2006",
  pages="115--122",
  address="Brno, ČR",
  isbn="80-214-3164-4"
}