This study developed a rapid method for aerodynamic heating prediction in high-speed lifting bodies. A dataset comprising 540 simulation cases was constructed through parametric modeling, encompassing 15 three-dimensional configurations and 36 flight conditions. To facilitate efficient neural network training, a geometry-aware preprocessing method based on surface slicing and interpolation was proposed, converting complex surface and geometry information into matrix representations. Subsequently, a D-TMU model based on deep learning was introduced. The model employed an encoder–decoder architecture integrating transformer modules, multilayer perceptrons, and UNet structures, with depthwise over-parameterized convolutions replacing standard convolution layers. D-TMU directly predicted surface heat flux distributions without iterative computations from input geometry, pressure distribution, and flight conditions. Validation results demonstrated the predictive performance of the model, with mean prediction errors of 1.21% on the test set, 1.19% in high heat flux regions, and 0.97% at key points. The average inference time per case was 0.03 seconds, representing computational acceleration a speedup of approximately six orders of magnitude compared over traditional CFD methods. These results indicated that D-TMU effectively captured global geometric characteristics and local feature interactions, maintaining achieving high predictive accuracy and computational efficiency. In addition, the model exhibited promising generalization capability for lifting body configurations beyond the training set.

Under non-zero angle of attack, the near-wake flow of a conical shape vehicle loses its axisymmetric nature, and the flow structure significantly differs from that under the condition of zero angle of attack. In the present study, we selected a reference state from the Reentry-F flight experiment of an altitude of 37.5 km and Mach number of 19.13, and conducted a numerical study on the laminar near-wake flow structure of a 5° half-cone angle circular cone. Influences of the angle of attack, Mach number, Reynolds number, etc., on the near-wake flow structures, pressure and heat flux on the base surface were analysed. The results indicated that, in contrast to the conical shape at zero angle of attack, the recirculation region at non-zero angles of attack displayed an irregular shape, and its length decreased significantly, up to 44.6%. As the angle of attack increased, the near-wake vortices and the leeward vortices of the forebody could interact with each other, which results in a trend of decreasing-increasing-decreasing of the recirculation zone length. The non-dimensional pressure and peak values of the Stanton number showed a decreasing-increasing trend with the increase of the angle of attack. As the Mach number increases, the flow compressibility got stronger, leading to a monotonic decrease in the length of small-scale vortex surfaces and wave structures in the recirculation zone, while the dimensionless peak pressure increased monotonically, and the peak Stanton number decreased monotonically. The influence of Reynolds number on the wave structures was relatively small. As the unit Reynolds number increased, the viscous effect weakened, resulting in an increase in the leeward depression of the recirculation zone and a monotonic increase in the length of the recirculation zone, with both the dimensionless peak pressure and Stanton number decreasing monotonically.