Lateral–torsional buckling resistance prediction model for steel cellular beams generated by Artificial Neural Networks (ANN)

Rabee Shamass; Vireen Limbachiya

doi:10.1016/j.tws.2021.108592

Lateral–torsional buckling resistance prediction model for steel cellular beams generated by Artificial Neural Networks (ANN)

Rabee Shamass, Vireen Limbachiya

Research output: Contribution to journal › Article › peer-review

65 Citations (Scopus)

Abstract

The present paper aims to develop an Artificial Neural Network (ANN) formula to predict the LTB resistance of steel cellular beams. A finite element model is developed and validated through experimental tests. A parametric study is then conducted. 768 models are employed to train the ANN. The results are compared with the analytical models, as well as the equation predicted by ANN. The ANN model with seven neurons can accurately predict the LTB resistance of cellular beams as well the LTB combined with web-post buckling or web distortional buckling modes. Hence, the ANN-based formula can be adopted as design tool.

Original language	English
Article number	108592
Pages (from-to)	108592
Journal	Thin-Walled Structures
Volume	170
DOIs	https://doi.org/10.1016/j.tws.2021.108592
Publication status	Published - 15 Nov 2021
Externally published	Yes

Keywords

Artificial neural network; Machine learning; Steel cellular beams; Lateral-torsional buckling; Finite element method.

Access to Document

10.1016/j.tws.2021.108592

Lateral-torsional buckling resistance prediction model for steel cellular beams generated by Artificial Neural Networks

Cite this

@article{42ec6a61bb4349fabf110bd3fc7da7c2,

title = "Lateral–torsional buckling resistance prediction model for steel cellular beams generated by Artificial Neural Networks (ANN)",

abstract = "The present paper aims to develop an Artificial Neural Network (ANN) formula to predict the LTB resistance of steel cellular beams. A finite element model is developed and validated through experimental tests. A parametric study is then conducted. 768 models are employed to train the ANN. The results are compared with the analytical models, as well as the equation predicted by ANN. The ANN model with seven neurons can accurately predict the LTB resistance of cellular beams as well the LTB combined with web-post buckling or web distortional buckling modes. Hence, the ANN-based formula can be adopted as design tool.",

keywords = "Artificial neural network; Machine learning; Steel cellular beams; Lateral-torsional buckling; Finite element method.",

author = "Rabee Shamass and Vireen Limbachiya",

year = "2021",

month = nov,

day = "15",

doi = "10.1016/j.tws.2021.108592",

language = "English",

volume = "170",

pages = "108592",

journal = "Thin-Walled Structures",

issn = "0263-8231",

publisher = "Elsevier Ltd",

}

TY - JOUR

T1 - Lateral–torsional buckling resistance prediction model for steel cellular beams generated by Artificial Neural Networks (ANN)

AU - Shamass, Rabee

AU - Limbachiya, Vireen

PY - 2021/11/15

Y1 - 2021/11/15

N2 - The present paper aims to develop an Artificial Neural Network (ANN) formula to predict the LTB resistance of steel cellular beams. A finite element model is developed and validated through experimental tests. A parametric study is then conducted. 768 models are employed to train the ANN. The results are compared with the analytical models, as well as the equation predicted by ANN. The ANN model with seven neurons can accurately predict the LTB resistance of cellular beams as well the LTB combined with web-post buckling or web distortional buckling modes. Hence, the ANN-based formula can be adopted as design tool.

AB - The present paper aims to develop an Artificial Neural Network (ANN) formula to predict the LTB resistance of steel cellular beams. A finite element model is developed and validated through experimental tests. A parametric study is then conducted. 768 models are employed to train the ANN. The results are compared with the analytical models, as well as the equation predicted by ANN. The ANN model with seven neurons can accurately predict the LTB resistance of cellular beams as well the LTB combined with web-post buckling or web distortional buckling modes. Hence, the ANN-based formula can be adopted as design tool.

KW - Artificial neural network; Machine learning; Steel cellular beams; Lateral-torsional buckling; Finite element method.

U2 - 10.1016/j.tws.2021.108592

DO - 10.1016/j.tws.2021.108592

M3 - Article

SN - 0263-8231

VL - 170

SP - 108592

JO - Thin-Walled Structures

JF - Thin-Walled Structures

M1 - 108592

ER -

Lateral–torsional buckling resistance prediction model for steel cellular beams generated by Artificial Neural Networks (ANN)

Abstract

Keywords

Access to Document

Fingerprint

Cite this