Detail publikace

ANN inverse analysis based on stochastic small-sample training set simulation

Originální název

ANN inverse analysis based on stochastic small-sample training set simulation

Anglický název

ANN inverse analysis based on stochastic small-sample training set simulation

Jazyk

en

Originální abstrakt

A new approach of inverse analysis is proposed to obtain parameters of a computational model 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 scater reflecting the physical range of potential values. A nonovelty of the approach is the utilization of the efficient small-sample simulation method LatinHypercube Sampling (LHS) used for the stochastic preparation of the training set utilized in training the artificial neural network.

Anglický abstrakt

A new approach of inverse analysis is proposed to obtain parameters of a computational model 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 scater reflecting the physical range of potential values. A nonovelty of the approach is the utilization of the efficient small-sample simulation method LatinHypercube Sampling (LHS) used for the stochastic preparation of the training set utilized in training the artificial neural network.

BibTex


@article{BUT44443,
  author="Drahomír {Novák} and David {Lehký}",
  title="ANN inverse analysis based on stochastic small-sample training set simulation",
  annote="A new approach of inverse analysis is proposed to obtain parameters of a computational model 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 scater reflecting the physical range of potential values. A nonovelty of the approach is the utilization of the efficient small-sample simulation method LatinHypercube Sampling (LHS) used for the stochastic preparation of the training set utilized in training the artificial neural network.",
  address="Elsevier",
  chapter="44443",
  institution="Elsevier",
  journal="ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE",
  number="5",
  volume="19",
  year="2006",
  month="may",
  pages="731--740",
  publisher="Elsevier",
  type="journal article - other"
}