Fire resistance prediction of slim-floor asymmetric steel beams using single hidden layer ANN models that employ multiple activation functions

Panagiotis G. Asteris, Chrysanthos Maraveas, Athanasios T. Chountalas, Dimitrios S. Sophianopoulos, Naveed Alam

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper a mathematical model for the prediction of the fire resistance of slim-floor steel beams based on an Artificial Neural Network modelling procedure is presented. The artificial neural network models are trained and tested using an analytical database compiled for this purpose from analytical results based on FEM. The proposed model was selected as the optimum from a plethora of alternatives, employing different activation functions in the context of Artificial Neural Network technique. The performance of the developed model was compared against analytical results, employing several performance indices. It was found that the proposed model achieves remarkably improved predictions of the fire resistance of slim-floor steel beams. Moreover, based on the optimum developed AN model a closed-form equation for the estimation of fire resistance is derived, which can prove a useful tool for researchers and engineers, while at the same time can effectively support the teaching of this subject at an academic level.
Original languageEnglish
JournalSteel and Composite Structures
Volume44
Issue number6
DOIs
Publication statusAccepted/In press - 15 Sep 2022

Keywords

  • activation functions
  • artificial neural networks
  • slim-floor steel beams
  • fire resistance
  • soft computing

Fingerprint

Dive into the research topics of 'Fire resistance prediction of slim-floor asymmetric steel beams using single hidden layer ANN models that employ multiple activation functions'. Together they form a unique fingerprint.

Cite this