Physics-Guided Multi-Fidelity Surrogate Modeling for Natural Supercavity Geometry of an Axisymmetric Conical Cavitator
The study developed a Physics-Guided Multi-Fidelity Surrogate (PG-EHK) framework to accurately predict the geometry of natural supercavities behind conical cavitators. By fusing multiple analytical models with sparse high-fidelity CFD data, the method achieves a 61% reduction in prediction error compared to single analytical approaches, enabling rapid design and shape management without extensive CFD sweeps.