Expedient hypersonic aerothermal prediction for aerothermoelastic analysis via field inversion and machine learning

The accurate and efficient prediction of aerothermal loads over the hypersonic vehicles during atmospheric flight is critical for the aerothermoelastic design, analysis and optimization of the structures of this class of vehicles. Reduced-order models (ROMs) and surrogates are typical approaches to reducing the computational cost to a tractable level. However, the existing ROMs and surrogates suffer from the curse of dimensionality that roots from the need to parameterize and sample the thermal-structural responses. This work presents a novel physics-informed ROM for the aerothermal load calculation on a deforming structure in high-speed flow, based on the combination of the classical turbulent viscous-inviscid interaction (TVI) model and the field inversion and machine learning technique. It is demonstrated that the new model, termed augmented TVI model, can achieve an accuracy close to that of CFD solvers when predicting the flow solutions over a wide range of complex surface deformations with a limited number of high-fidelity solutions. These results underline its potential to be used as a new generation of ROM for the aerothermal load prediction in hypersonic aerothermoelastic design and analysis.