Publication result detail

Sensitivity analysis of prestressed concrete girders based on artificial neural network surrogate model.

PAN, L.; LEHKÝ, D.; NOVÁK, D.; SLOWIK, O.

Original Title

Sensitivity analysis of prestressed concrete girders based on artificial neural network surrogate model.

English Title

Sensitivity analysis of prestressed concrete girders based on artificial neural network surrogate model.

Type

Paper in proceedings outside WoS and Scopus

Original Abstract

The paper describes a neural network ensemble-based parameter sensitivity analysis, which is compared with selected sensitivity analysis techniques usually utilized in stochastic structural modeling. The accuracy, stability and efficiency of the mentioned sensitivity analysis techniques are compared on example of prestressed concrete girder.

English abstract

The paper describes a neural network ensemble-based parameter sensitivity analysis, which is compared with selected sensitivity analysis techniques usually utilized in stochastic structural modeling. The accuracy, stability and efficiency of the mentioned sensitivity analysis techniques are compared on example of prestressed concrete girder.

Keywords

Sensitivity analysis, prestressed concrete girders, neural network

Key words in English

Sensitivity analysis, prestressed concrete girders, neural network

Authors

PAN, L.; LEHKÝ, D.; NOVÁK, D.; SLOWIK, O.

RIV year

2019

Released

12.09.2018

Book

16th International Probabilistic Workshop

ISBN

1437-1006

Periodical

Beton- und Stahlbetonbau

Volume

113

Number

S2

State

Federal Republic of Germany

Pages from

1

Pages to

5

Pages count

5

URL

BibTex

@inproceedings{BUT156408,
  author="Lixia {Pan} and David {Lehký} and Drahomír {Novák} and Ondřej {Slowik}",
  title="Sensitivity analysis of prestressed concrete girders based on artificial neural network surrogate model.",
  booktitle="16th International Probabilistic Workshop",
  year="2018",
  journal="Beton- und Stahlbetonbau",
  volume="113",
  number="S2",
  pages="1--5",
  issn="0005-9900",
  url="https://onlinelibrary.wiley.com/action/downloadSupplement?doi=10.1002%2Fbest.201800059&file=best201800059-sup-0001-suppinfo.pdf"
}