Search results

This paper aims to predicting the behavior of welded angle connections (moment-rotation-temperature) in fire using artificial neural network 10.

An artificial neural networking model is described to predict the moment-rotation response of semi-rigid beam-to-column joints at elevated temperature.

Data from 47 experimental fire tests and verified finite element model are used for training and testing and validating the neural network models. The model’s predicted values are compared with actual test results. The results indicate that the models can predict the moment-rotation-temperature behavior of semi-rigid beam-to-column joints with very high accuracy. The developed model can be modified easily to investigate other parameters that influence the performance of joints in fire.

The results indicate that the models can predict the moment-rotation-temperature behavior of semi-rigid beam-to-column joints with very high accuracy. The developed model can be modified easily to investigate other parameters that influence the performance of joints in fire.

In this paper, the seismic behavior of the gusset plate moment connection (GPMC) exposed to the post-earthquake fire (PEF) is investigated.

For this purpose, for the sake of verification, first, a numerical model is built using ABAQUS software and then exposed to earthquakes and high temperatures. Afterward, the effects of a series of parameters, such as gusset plate thickness, gap width, steel grade, vertical load value and presence of the stiffeners, are evaluated on the behavior of the connection in the PEF conditions.

Based on the results obtained from the parametric study, all parameters effectively played a role against the seismic loads, although, when exposed to fire, it was found that the vertical load value and presence of the stiffener revealed a great contribution and the other parameters could not significantly affect the connection performance. Finally, to develop the modeling and further study the performance of the connection, the 4 and 8-story frames are subjected to 11 accelerograms and 3 different fire scenarios. The findings demonstrate that high temperatures impose rotations on the structure, such that the story drifts were changed compared to the post-earthquake drift values.

The obtained results can be used by engineers to design the GPMC for the combined action of earthquake and fire.

Offshore structures are among the structures exposed to fire more often. Most of these structures are likely to be associated with flammable materials. In this research, some of the structures constructed on top of marine decks have been studied.

For this purpose, the upper-bound theory of plastic analysis has been used to investigate its collapse behavior. In this way, genetic algorithm has been used for application of the combination of elementary mechanisms in the classic plastic analysis problem.

The studied structures are optimized by plastic analysis theory before and after the fire and their failure modes are compared with each other. The comparison of the results indicates significant changes in the load factor value, as well as the critical collapse mode of the structure before and after the fire.

Results indicate that the combination of plastic analysis and a genetic algorithm can predict the collapse mode of the structure before and after the fire accurately.

This paper aims to predict the fire resistance of steel-reinforced concrete columns by application of the genetic algorithm.

In total, 11 effective parameters are considered including mechanical and geometrical properties of columns and loading values as input parameters and the duration of concrete resistance at elevated temperatures as the output parameter. Then, experimental data of several studies – with extensive ranges – are collected and divided into two categories.

Using the first set of the data along with the gene expression programming (GEP), the fire resistance predictive model of steel-reinforced concrete (SRC) composite columns is presented. By application of the second category, evaluation and validation of the proposed model are investigated as well, and the correspondent time-temperature diagrams are derived.

The relative error of 10% and the R coefficient of 0.9 for the predicted model are among the highlighted results of this validation. Based on the statistical errors, a fair agreement exists between the experimental data and predicted values, indicating the appropriate performance of the proposed GEP model for fire resistance prediction of SRC columns.