Sensitivity Analysis on the Drift Ratio of Bridge Piers Using a Neural Network Approach

This paper aims to perform a sensitivity analysis (SA) to identify the parameters that are most relevant to the drift ratio of bridge piers as a first step toward improving seismic resilience. The parameters represent seismic source and attenuation effects, structural geometric effects, site conditions, and column-scale effects. The SA is conducted through dataset-based exploration and by using an artificial neural network (ANN). Parameter relevance is evaluated using statistical metrics including the F-test score. Because near-fault recordings are scarce in low-seismicity regions, point-source stochastic simulations are used to generate synthetic data. Six datasets are created to train the ANN. The input variables include moment magnitude (Mw), hypocentral distance (Rhyp), average shear-wave velocity in the top 30 m of soil (Vs30), column height (H), column diameter (D), and column spacing (R). The output variable is the peak pier drift. The datasets differ in their H/D ratios and in whether local site effects are included. Six ANN models are trained to predict drift. The results show that Rhyp is the most influential parameter (F-test score = 56%), followed by Mw (32%), H/D ratio, and Vs30. The resulting ANN model provides rapid estimates of pier drift and supports preliminary assessment of bridge seismic performance.