Researchers have developed a novel physics-guided multi-fidelity surrogate framework called Extended Hierarchical Kriging (PG-EHK) to predict the natural supercavity geometry of axisymmetric conical cavitators. This approach fuses multiple analytical cavity formulas as low-fidelity trend functions, corrected by a limited number of high-fidelity computational fluid dynamics (CFD) simulations. The PG-EHK framework uses Bayesian-estimated scaling factors to incorporate these analytical models, enabling accurate cavity geometry predictions with fewer than 20 high-fidelity CFD evaluations. Cross-validation shows a 61% reduction in prediction error compared to individual analytical methods. AI
RANK_REASON The cluster contains an academic paper detailing a new modeling framework. [lever_c_demoted from research: ic=1 ai=0.4]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
