Unsteady carrier airwake under complex sea states flow characteristics and time-conditioned prediction
Abstract
Carrier motion under complex sea states continuously changes the relative inflow in the landing glide-path region and produces an unsteady airwake. High-fidelity computational fluid dynamics (CFD) can resolve this coupled wind–wave–carrier problem, but long-sequence and multi-condition calculations remain expensive. Here, a coupled CFD framework is used to examine the temporal and downstream evolution of the airwake. Wave-induced heave and pitch produce a clear phase-related modulation of the sectional velocity fields. The angled-deck landing region contains separated velocity-deficit branches that are transported, deformed, and redistributed downstream rather than forming a single uniform wake. A time-conditioned one-shot residual network (TCO-ResNet) is then developed for rapid flow-field prediction. The initial flow field and target time are mapped directly to the specified future state, avoiding recursive time marching. Wake region-of-interest weighting, physics-guided constraints, and texture loss are used to retain wake boundaries and velocity-transition regions. Compared with an autoregressive ResNet, TCO-ResNet avoids the error growth associated with recursive prediction. Tests on unseen longitudinal sections retain both the phase-related evolution and the main multi-branch wake pattern. Integral wake measures further show that the strong low-velocity cores contract downstream, while the total streamwise velocity deficit changes much less, indicating redistribution rather than uniform wake attenuation. After transfer from Sea State 6 to Sea State 4, the phase-related evolution is still recovered, whereas the weaker wind–wave forcing produces less downstream reorganization. The method therefore provides a rapid reconstruction of the main temporal and spatial characteristics of carrier airwakes across the two sea states considered.