Estimation of the temperature profiles of reinforced concrete cross sections exposed to standard fires by using artificial neural networks with different topologies

The thermal analysis in structural members can be extremely complex, especially for materials that retain moisture and have a low thermal conductivity. The simplest method of defining the temperature profile through the cross section is to use test data presented in tables or charts, which are published in codes or design guides. These tabulated data are generally based on standard fire conditions. Annex A of TS-EN1992-1-2 provides a series of calculated temperature profiles for concrete slabs or walls, beams, and columns. But these profiles are given for specific cross-section dimensions and standard fire resistance durations. The main purpose of this study is to estimate the temperature profiles of reinforced concrete beam and column cross sections by using artificial neural networks (ANN) with different topologies. When modeling ANN, it is benefited from multi-layer ANN, which uses supervised learning rule. During training and testing stage of ANN, the results obtained from the aforementioned temperature profiles are used. The temperatures values were read from the temperature profile charts according to standard fire durations, cross-sections height and widths, and x and y coordinates of the points by the reference point. By testing ANN with different topologies in conclusions, its usability, advantages, and disadvantages are evaluated.