Researchers have developed two new data-driven models, one using kriging and another employing artificial neural networks (NN), to predict pressure losses in turbulent flows across perforated plates. These models were trained on existing experimental data and demonstrated superior performance compared to traditional empirical formulas. The study also showed that these data-driven approaches can be effectively integrated into computational fluid dynamics simulations, yielding accurate predictions for practical applications. AI
IMPACT These data-driven models offer a more accurate and feasible approach for predicting pressure losses in turbulent flows, potentially improving computational fluid dynamics applications.
RANK_REASON The item describes a research paper proposing new models for predicting pressure losses. [lever_c_demoted from research: ic=1 ai=0.7]
Read on Hugging Face Daily Papers →
- artificial neural network
- kriging
- Perforated plates corresponding to integumental glands on the antennae of adult maleDrilus mauritanicusLucas 1849 (Coleoptera: Elateridae: Agrypninae: Drilini)
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
