Fire Analysis of Steel Frames with the use of Artificial Neural Networks

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.

[1]  K. Washizu.  Variational Methods in Elasticity and Plasticity , 1982 .

[2]  Shigenori Tanaka,et al.  Neural Network System for Reasoning Residual Axial Forces of High-Strength Bolts in Steel Bridges , 1998 .

[3]  T. Z. Harmathy.  A Comprehensive Creep Model , 1967 .

[4]  K. V. Sudhakar,et al.  ANN based prediction model for fatigue crack growth in DP steel , 2001 .

[5]  Miran Saje,et al.  On materially and geometrically non-linear analysis of reinforced concrete planar frames , 2004 .

[6]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[7]  G. M. Seed,et al.  THE APPLICABILITY OF NEURAL NETWORKS IN MODELLING THE GROWTH OF SHORT FATIGUE CRACKS , 1998 .

[8]  Kang Hai Tan,et al.  Effects of external bending moments and heating schemes on the responses of thermally restrained steel columns , 2004 .

[9]  Kazuhiko Kawashima,et al.  Neural Network Modeling of Confined Compressive Strength and Strain of Circular Concrete Columns , 2003 .

[10]  G. Williams-leir,et al.  Creep of structural steel in fire: Analytical expressions , 1983 .

[11]  Zhiye Zhao,et al.  Steel columns under fire - a neural network based strength model , 2006, Adv. Eng. Softw..

[12]  Tsong Yen,et al.  Modeling Confinement Efficiency of Reinforced Concrete Columns with Rectilinear Transverse Steel using Artificial Neural Networks , 2003 .

[13]  Miran Saje,et al.  On the local stability condition in the planar beam finite element , 2001 .

[14]  T Harmathy,et al.  Elevated-Temperature Tensile and Creep Properties of Some Structural and Prestressing Steels , 1970 .

[15]  B. R. Kirby,et al.  High temperature properties of hot-rolled, structural steels for use in fire engineering design studies , 1988 .

[16]  Yngve Anderberg,et al.  Modelling Steel Behaviour , 1988 .

[17]  John Norrish,et al.  Artificial neural networks for modelling the mechanical properties of steels in various applications , 2005 .

[18]  Goran Turk,et al.  Non-linear fire resistance analysis of reinforced concrete frames , 2001 .

[19]  E. Reissner.  On one-dimensional finite-strain beam theory: The plane problem , 1972 .

[20]  Manolis Papadrakakis,et al.  Design optimization of steel structures considering uncertainties , 2005 .

[21]  Sherief S.S. Sakla.  Neural network modeling of the load-carrying capacity of eccentrically-loaded single-angle struts , 2004 .

[22]  Ian Burgess,et al.  Failure of steel columns in fire , 1992 .