Rapid and accurate prediction of seismic response and fragility for bridge pile-group foundations (PGFs) is crucial for assessing seismic resilience. However, the high computational cost of traditional high-fidelity nonlinear analysis limits the application of probabilistic seismic risk analysis. To address this, an integrated deep learning framework is proposed that employs a unidirectional, multi-layer LSTM network for end-to-end prediction of structural responses directly from ground motions. The proposed model features two innovations. First, its multi-output capability enables simultaneous prediction of complete response time histories and peak values for key engineering demand parameters—bending moment, curvature, and pile cap displacement. Second, the network incorporates sliding time windows and residual connections to capture complex nonlinear soil–structure interaction. These predictions are integrated into a probabilistic seismic demand model to generate fragility curves. The framework is validated using a high-fidelity OpenSees model of a real bridge PGF subjected to 1000 ground motions. Results demonstrate the model’s excellent predictive accuracy: for peak bending moment, the mean predicted-to-actual ratio ranges from 0.97 to 1.03, with standard deviation below 0.12; the derived fragility curves show excellent agreement with benchmarks, achieving an average R2 of 0.985 across four damage states. More importantly, the framework reduces the time for a complete fragility assessment (200 incremental dynamic analyses) from approximately 12 h to about 1 s—a 40,000× speed-up—making data-driven rapid and large-scale seismic risk assessment a reality. The proposed framework provides engineers with a practical design tool for rapidly evaluating alternative foundation configurations and informing seismic design decisions, thereby integrating advanced data-driven methods directly into the engineering design workflow.
Han et al. (Mon,) studied this question.