A rapid neural network-based demand estimation for generic buildings considering the effect of soft/weak story

Recent earthquakes clarified that existing a soft/weak-story in a building could completely invert the failure mechanisms of the structure. Several studies were implemented to evaluate the potential risk subjected to the buildings under the earthquake hazard. However, these researchers discarded the effect of soft/weak-story on the demand parameters of their models. This paper presents a rapid demand estimation framework for generic buildings considering the effect of soft/weak-story. In this regard, the simplified model developed according to the HAZUS approach is rectified to apply the effect of soft/weak-story on the structural behavior of the generic buildings. Artificial neural networks are implemented to remove the required time-consuming nonlinear response history analyses from the post-earthquake actions. This research utilized a suite of 111 earthquake records, originally developed by the SAC project. These motions are uniformly scaled from 0.1g to 1.5g to obtain a generalized dataset with different intensities. Bayesian optimization algorithm is conducted to achieve a prediction model with optimized hyperparameters. Results clarify that the proposed method is reliable and computationally cost-effective in predicting the demand parameters of generic buildings. This framework can be used in the body of a risk assessment platform to facilitate the emergency response to the earthquake hazard.