Fire analysis of steel frames with the use of artifical neural networks

Hozjan, Tomaž (author), Turk, Goran (author), Srpčič, Stane (author)

The paper presents an alternative approach to the modelling of the mechanical behaviour of steel frame material when exposed to the high temperatures expected in fires. Based on a series of stress-strain curves obtained experimentally for various temperature levels, an artificial neural network (ANN) is employed in the material modelling of steel. Geometrically and materially, a non-linear analysis of plane frame structures subjected to fire is performed by FEM. The numerical results of a simply supported beam are compared with our measurements, and show a good agreement, although the temperature-displacement curves exhibit rather irregular shapes. It can be concluded that ANN is an efficient tool for modelling the material properties of steel frames in fire engineering design studies. (c) 2007 Elsevier Ltd. All rights reserved.

• Language: English
• Keywords: steel beam, fire analysis, artifical neural network, material modelling
• Typology: 1.01 - Original Scientific Article
• Organization: FGG - Faculty of Civil and Geodetic Engineering
• Publisher: Elsevier
• Year: 2007
• Number of pages: Str. 1396-1403
• Numbering: letn. 63, št. 10
• PID: 20.500.12556/RUL-32114
• UDC: 624.072.2:624.014.2
• ISSN on article: 0143-974X
• DOI: 10.1016/j.jcsr.2007.01.013
• COBISS.SI-ID: 3663201
• Publication date in RUL: 10.07.2015

Record is a part of a journal

• Title: Journal of constructional steel research
• Shortened title: J. Constr. steel res.
• Publisher: Elsevier Science
• ISSN: 0143-974X
• COBISS.SI-ID: 1326341

Secondary language

• Language: English
• Keywords: jekleni nosilec, požarna analiza, umetna nevronska mreža, modeliranje materiala