New method maps transonic flutter boundary with active learning

Researchers have developed a new method for mapping the transonic flutter boundary of airfoils, specifically focusing on Isogai's case A. This method utilizes coupled unsteady Euler simulations and a Gaussian-process surrogate trained with active learning, combined with split conformal prediction for stability calls. The approach accurately labels flutter boundaries and provides distribution-free error rates, with a documented 2.8% increase in flutter speed at the dip due to a slight mean incidence. AI

IMPACT Introduces novel active learning and conformal prediction techniques applicable to complex simulation problems.

RANK_REASON The item is an academic paper detailing a new computational method for fluid dynamics research. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv cs.LG →

• elastic axis
• Euler simulations
• flutter speed index
• Gaussian process
• Isogai's case A
• Mach number
• split conformal prediction
• The Leading Edge
• trailing edge

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →