An intelligent Adaptive Neuro-Fuzzy Inference System to Estimate the Behavior factor of EBF steel frames under Pulse-type Near-fault Earthquakes

One of the most important effective parameters in earthquake, is behavior factor, which is depends on various factors such as structural geometric properties, structure ductility (performance level), fundamental period of the structure, damping, soil properties, earthquake characteristics (near- or far- field) and effect of higher modes. The most important feature of the behavior factor is that it allows the structural designer, to be able to evaluate the structural seismic demand, using an elastic analysis, based on force-based principles quickly. In seismic codes such as the Standard 2800, this coefficient is merely dependent on the type of lateral resistance system and is introduced with a fixed number. However, there is a relationship between the behavior factor, ductility (performance level), structural geometric properties, and type of earthquake (near fault and far fault). The purpose of this paper is to establish an accurate intelligent model related to the geometrical characteristics of the structure, performance level and the behavior factor in eccentrically steel frames, under earthquakes near-fault. For this purpose, genetic algorithm is used. Initially a wide database consisting of 12960 data with 3-, 6-, 9-, 12-, 15- and 20- stories, 3 column stiffness types, and 3 brace slenderness types were designed, and analyzed under 20 pulse-type near-fault earthquakes for 4 different performance levels. To generate the proposed model, 6769 training data were used in the form of adaptive-neural fuzzy inference system (ANFIS). Subtractive clustering and Fuzzy C-Mean clustering (FCM) methods have been used to generate the purposed model. The results showed that Fuzzy C-Mean clustering provides more accurate results than the other fuzzy inference system (FIS). To validate the proposed model, 2257 test data were used to calculate the mean squared error of the model. The results of correlation analysis of the proposed model show that the proposed intelligent model has high accuracy.