Search

To avoid the limitations of the assumptions for the traditional probabilistic seismic demand model (PSDM), this study proposed a novel PSDM for conducting fragility analysis of subway stations based on artificial neural network (ANN). The proposed ANN-based PSDM consists of an ANN-based trend model and a probabilistic-neural-network (PNN)-based error model. A two-story and three-span subway station in Shanghai was taken as a case. The results show that compared with the traditional PSDM, the proposed ANN-based PSDM can better predict the seismic responses of structures and describes the nonhomogeneous variance of residuals of the predicted seismic responses. [ABSTRACT FROM AUTHOR]