Key points are not available for this paper at this time.
Rapid health assessment of essential buildings such as hospitals, fire stations, and large residential complexes is crucial after damaging earthquakes. The use of advanced technologies such as wireless sensors, learning algorithms, and signal processing methods became more attractive in such fast applications due to their higher reliabilities and efficiencies compared to the conventional visual inspection methods. This paper presents a robust post-earthquake damage detection framework for predicting the extent and location of damage occurrence in the braced-frame structures after an earthquake. To do so, features derived from acceleration response of the structure were used along with a classification learner to determine the health condition of the structure. Decision tree classifiers are used for the purpose of damage classification where the Bayesian optimization algorithm is implemented to optimize the architecture of the mentioned classifier. A one-story chevron steel-braced frame, a three-story X-braced steel-frame, and a five-story three-dimensional building are considered to validate the proposed method. The total number of 3774 and 1887 nonlinear response history analyses were respectively performed for 2D and 3D numerical models under scaled SAC motions, using the OpenSees simulation platform. Furthermore, in order to simulate the field condition, a maximum level of 10% white Gaussian noise is added to the output signals. Results obtained from the three case studies show that the proposed framework is robust and reliable in predicting the extent of damage level in the braced-frame structures in a short time after an earthquake.
Salkhordeh et al. (Tue,) studied this question.