Shear panel dampers (SPDs) are critical passive energy dissipation devices used in earthquake-resistant structures. They are designed to yield in shear before other structural members, thereby reducing seismic damage. The hysteretic behavior of SPDs is significantly influenced by the stiffeners attached to their webs, which mitigate web shear buckling. This study investigates SPDs with three distinct stiffener orientations—transverse, longitudinal, and diagonal—to identify the optimal configuration that enhances ductility and energy dissipation. A three-dimensional (3D) finite element model was developed in ANSYS Workbench to analyze SPDs under lateral cyclic loading, incorporating geometric imperfections and material nonlinearity. The model was validated against experimental data, demonstrating its accuracy in predicting hysteretic behavior. Subsequently, 18 SPD specimens fabricated from cold-formed steel and stainless steel were numerically analyzed to evaluate their hysteretic performance. Results revealed that transversely stiffened shear panel dampers (TSPDs) and longitudinally stiffened shear panel dampers (LSPDs) exhibited more stable responses compared to diagonally stiffened shear panel dampers (DSPDs). While DSPDs demonstrated higher shear capacity, they exhibited lower ductility and energy dissipation due to rapid strength deterioration. Among the configurations, LSPDs outperformed TSPDs in terms of buckling resistance, deformation capacity, ductility, and energy dissipation. Based on these findings, preliminary predictive design formulae for LSPDs made of cold-formed stainless steel were derived, providing valuable insights for optimizing their design.

Conventional structural design frameworks assess natural hazards as statistically independent phenomena, a practice that can lead to significant underestimation of risk for structures subjected to sequential or concurrent hazards. The generation of probabilistic fragility functions under such cascading loads, particularly for post-fire seismic events, presents a computational barrier for standard non-linear dynamic analysis. To address this barrier, this study introduces a comprehensive computational framework centered on a physics-constrained neural network (PCNN) to serve as a high-fidelity surrogate model. The framework first uses a non-linear 12-degree-of-freedom structural model to generate a baseline dataset of collapse times under post-fire, concurrent wind-earthquake loading via the computationally efficient endurance time (ET) method, confirming that wind effects are negligible under ambient conditions and that the framework correctly identifies this hazard hierarchy without prior labeling, while fire and seismic parameters dominate. This dataset is subsequently used to train the PCNN, which is validated to achieve exceptional predictive accuracy ($R^2=$ 0.991), performing on par with a state-of-the-art Random Forest model while enforcing physical constraints. A feature importance analysis confirmed that structural collapse is dominated by fire intensity (≈55%) and initial structural period (≈45%). The validated PCNN is then applied to demonstrate the framework’s capability, rapidly generating fragility curves that quantify the catastrophic effect of fire on seismic resilience. This analysis reveals that a severe 800 °C localized fire reduces the structure’s median collapse capacity by 94.7%, thereby establishing the proposed framework as a successful template for tackling complex, non-linear problems in multi-hazard engineering.