Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 6, 2026Physics of Fluids

Predicting distribution of adiabatic film cooling effectiveness using generative adversarial networks with mist/air mixture as coolant

View Full Paper
Ask AI
Bookmark
Share

Authors

XHXin HuangZHZetao HanDDDan Deng

Discussion

Loading...

Member takes

Overview

Randomized trial predicts cooling effectiveness in mist/air mixtures, suggesting efficient design optimization.

Key Points

  • The aim is to develop a deep-learning framework using CGAN to accurately predict adiabatic film cooling effectiveness in aero-engines.
  • Proposed a Conditional Generative Adversarial Network model to analyze cooling effectiveness.
  • Input parameters include blowing ratio, mist concentration, and droplet diameter.
  • Employs dataset expansion, transfer learning, and regularization for improved generalization.
  • Achieved a computational speedup of several thousand times compared to CFD with maximum absolute errors below 0.07.
  • Generalization-enhancement strategy reduced mean absolute error from 0.048 to 0.012 in extreme conditions.
  • Model accurately reflects how physical factors impact film cooling effectiveness.

Cite This Study

Huang et al. (2026) studied this question.

synapsesocial.com/papers/6a23bc0571a5da9775e77733https://doi.org/10.1063/5.0316011
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Data-driven framework for prediction and optimization of gas turbine blade film cooling2024 · 20 citations
  2. 2Deep learning-aided active subspace exploration of free-stream effects for fan-shaped film cooling2024 · 3 citations
  3. 3Deep Learning-Aided Active Subspace Exploration for Free Stream Optimization in Fan-Shaped Film Cooling2024
  4. 4Quick Prediction of Complex Temperature Fields Using Conditional Generative Adversarial Networks2024 · 3 citations
  5. 5Generative Design of Liquid-Cooled Cold Plates via Enhanced Cross-Attention Conditional Diffusion Model2026