Publication result detail

Identification of Quasibrittle material parameters based on stochastic nonlinear simulation and artificial neural networks

NOVÁK, D.; LEHKÝ, D.

Original Title

Identification of Quasibrittle material parameters based on stochastic nonlinear simulation and artificial neural networks

English Title

Identification of Quasibrittle material parameters based on stochastic nonlinear simulation and artificial neural networks

Type

Paper in proceedings (conference paper)

Original Abstract

A new approach of inverse analysis is proposed to obtain material parameters of a constitutive law for quasibrittle material in order to achieve the best agreement with experimental data. The inverse analysis is based on the coupling of a stochastic simulation and an artificial neural network (ANN). The identification parameters play the role of basic random variables with a scatter reflecting the physical range of potential values. A novelty of the approach is the utilization of the efficient small-sample simulation method Latin Hypercube Sampling (LHS) used for the stochastic preparation of the training set utilized in training the neural network. Once the network has been trained, it represents an aapproximation consequently utilized to provide the best possible set of model parameters for the given experimental data.

English abstract

A new approach of inverse analysis is proposed to obtain material parameters of a constitutive law for quasibrittle material in order to achieve the best agreement with experimental data. The inverse analysis is based on the coupling of a stochastic simulation and an artificial neural network (ANN). The identification parameters play the role of basic random variables with a scatter reflecting the physical range of potential values. A novelty of the approach is the utilization of the efficient small-sample simulation method Latin Hypercube Sampling (LHS) used for the stochastic preparation of the training set utilized in training the neural network. Once the network has been trained, it represents an aapproximation consequently utilized to provide the best possible set of model parameters for the given experimental data.

Keywords

Identification, materila parameters, stochastic nonlinear simulation, artificial neural networks

Key words in English

Identification, materila parameters, stochastic nonlinear simulation, artificial neural networks

Authors

NOVÁK, D.; LEHKÝ, D.

Released

25.06.2007

Location

Praha, Česká republika

Book

MHM 2007

Pages from

94

Pages to

95

Pages count

2

BibTex

@inproceedings{BUT23249,
  author="Drahomír {Novák} and David {Lehký}",
  title="Identification of Quasibrittle material parameters based on stochastic nonlinear simulation and artificial neural networks",
  booktitle="MHM 2007",
  year="2007",
  pages="94--95",
  address="Praha, Česká republika"
}