Neural Network Prognostic Model for Predicting the Fire Resistance of Eccentrically Loaded RC Columns

Using the concept of the artificial neural networks and the results of the performed numerical analyses as input parameters, the prediction model for defining the fire resistance of RC columns incorporated in walls and exposed to standard fire from one side, has been made. A short description of the numerical analyses of columns exposed to standard fire ISO 834, conducted by the computer software FIRE are presented in this paper. The software is capable of predicting the nonlinear response of reinforced concrete elements and plane frame structures subjected to fire loading, carrying out the nonlinear transient heat flow analysis and nonlinear stress-strain response associated with fire.