A new predictive model for the minimum strength requirement of steel moment frames using artificial neural network

This study was aimed to propose an integrated formula developed based on artificial neural network and Bilin element of the OpenSEES software to predict the minimum strength requirement of steel moment frames (R) at any performance level (PL) and desired level of probabilistic response (Percentile). For this purpose, numerous equivalent SDOF systems were analyzed by changing ten different parameters including the period of vibration, PL, Percentile and those that affect the shape of the force-displacement capacity boundary of a moment frame. The proposed model was then compared to the one presented in FEMA P440A, which predicts the median R value at dynamic instability performance level, and the latest version of SPO2IDA software (Vamvatsikos and Cornell, 2005), which predicts the whole trend of an IDA curve. In addition to the simple form of the proposed model, results generally indicated that this model is more accurate than the other available models.