Analyzing uncertainties involved in estimating collapse risk with and without considering uncertainty probability distribution parameters

In the present study, modified Ibarra, Medina and Krawinkler moment-rotation parameters are used for modeling the uncertainties in concrete moment frame structures. Correlations of model parameters in a component and between two structural components were considered to analyze these uncertainties. In the first step, the structural collapse responses were obtained by producing 281 samples for the uncertainties using the Latin hypercube sampling (LHS) method, considering the probability distribution of the uncertainties and performing incremental dynamic analyses. In the second step, 281 new samples were produced for the uncertainties by the central composite design (CCD) method without considering the probability distribution of the uncertainties and calculating the structural collapse responses. Then, using the response surface method (RSM) and artificial neural network (ANN) for the two simulation modes, structural collapse responses were predicted. The results indicated that the collapse responses at levels of 0 to 100% obtained from the two simulations have a high correlation coefficient of 98%. This suggests that random variables can be simulated without considering the probability distribution of uncertainties, by performing uncertainty analysis to determine structural collapse responses.