Winterization of polar ships requires an engineering link between whole-ship airflow and local thermal boundaries. This study develops a one-way, whole-ship airflow-to-convective-boundary mapping framework for exposed superstructure components. Reynolds-averaged Navier–Stokes simulations using the RNG k–ε model were conducted for MV Xue Long 2 at seven wind directions and inflow velocities of 5–20 m/s. Representative surface-pressure trends were compared with measurements from a 1:400 wind-tunnel model. Source-reported monitoring-point results cover all seven directions from 0° to 180°. Velocities at 18 locations were converted to effective convective heat-transfer coefficients using a project-specific correlation and then supplied to an energy-conservation heat-loss framework. Representative dimensionless local velocities of 0.3–1.6 illustrate shielding and acceleration; they are not the extrema over all cases. For a representative comparison at 10 m/s inflow, local velocities of 3–16 m/s corresponded to correlation-derived coefficients of 31.53–86.35 W/(m²·K), compared with 63.55 W/(m²·K) for a uniform boundary. The resulting velocity and flow-topology information was used to define case-specific, mechanism-based screening zones. A 3.0 m bow fairing reduced the mean deck velocity from 10 to 3.9 m/s and the calculated coefficient by 42.9%. The study therefore demonstrates aerodynamic-to-convective-boundary screening rather than a fully validated bidirectional fluid–thermal or phase-change model; phase-change loads and transferable zoning thresholds require further validation.

In polar environments, icing on ship deck surfaces severely compromises navigation safety. Conventional electric trace heating systems operate in continuous heating mode, resulting in high energy consumption. This study proposes an intelligent periodic heating control method that integrates physics-informed neural networks (PINNs) and deep reinforcement learning (DRL) for energy-efficient anti-icing of circular pipe components on polar vessels. Using a polar coupled environment simulation platform, experiments were conducted on electric heating anti-icing for circular pipe components. Temperature data under various heating modes were collected, and a physically constrained PINN temperature prediction model was constructed, achieving high prediction accuracy with limited samples (test set R² = 0.9091; 5-fold cross-validation R² = 0.8877 ± 0.0312). The DRL agent trained in this virtual environment autonomously optimized the heating strategy, yielding optimal cycle parameters: heating ratio D = 0.722 and cycle duration τ = 88 s. While maintaining surface temperatures above 0 °C against a −10 °C ambient baseline, this strategy achieved a unit energy consumption of 0.27 kJ/°C, representing a 63% reduction compared to conventional continuous heating. This study provides a data-physics fusion control approach for polar vessel anti-icing systems, demonstrating strong potential for engineering applications.