During long-duration dynamic loads, such as wind loads or seismic effects, the internal temperature and pressure of a damping cylinder escalate rapidly, which induce shifts in the mechanical attributes of viscous fluid dampers (VFDs). This study investigated the mechanical performance of VFD considering the coupling effects of temperature and pressure under long-duration loads. First, we analyzed the mechanical and energy-dissipation performances of the dampers based on the dynamic mechanical tests considering different loading frequencies, displacement amplitude, and loading cycles. The experimental results indicated that both temperature and pressure influenced the output of the dampers, and in the sealed environment of the damper pip, temperature and pressure exerted mutual influence. Furthermore, the relationship between the damping coefficient and temperature–pressure coupling effects was obtained. Subsequently, an improved mathematical model for the mechanical performance of a gap-type VFD was proposed by considering the macroscopic energy balance of the entire fluid within the damper. Finally, the accuracy of the mathematical model for VFD under long-duration dynamic loads was validated by comparing the computational results with the experimental data.

Reconstructing continuous deflection and stress fields from sparse deflection measurements is challenging because the two responses have different spatial distributions and stress depends on deflection curvature. Limited experimental data further constrain model training and cross-domain adaptation. We present a decoupled spatiotemporal physics-informed neural network (DS-PINN) for reconstructing low-frequency elastic responses. The method combines latent temporal integration, dual-response spatial representation and simulation-to-experiment adaptation. Rather than representing the full spatiotemporal field with a single coordinate network, DS-PINN evolves latent coordinates through a Newmark-β integration operator. A shared sinusoidal representation network (SIREN) backbone extracts continuous spatial features, and two response-specific regression heads produce separate bases for deflection and stress. The model was pretrained on 1800 simulated records and fine-tuned on 16 measured records, while 200 simulated and 5 measured records were used for validation. Only three deflection channels were supplied as inputs. Across four independent 55 s test records, DS-PINN achieved Pearson correlation coefficients of 0.9323 for deflection and 0.9093 for stress. The corresponding normalized root-mean-square error (NRMSE) values were 7.94% and 7.59%. Spatial NRMSE values remained below 6% at all 11 evaluation locations. Compared with the closest end-to-end baseline, a temporal convolutional network, DS-PINN reduced deflection and stress NRMSE by approximately 45.0% and 45.9%, respectively. Ablation tests identified distinct roles for Newmark-based latent dynamics, temporal adaptation, magnitude correction, and spatial-basis consistency. These results support a simulation-assisted approach to multi-location virtual sensing of low-frequency beam responses from sparse deflection measurements and limited experimental data.