Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025MathematicsOpen Access

Research on a Rapid Three-Dimensional Compressor Flow Field Prediction Method Integrating U-Net and Physics-Informed Neural Networks

View Full Paper
Ask AI
Bookmark
Share

Authors

CWChen WangHMHongbing Ma

Discussion

Loading...

Member takes

Overview

This research demonstrates a method for predicting flow fields in compressors, highlighting neural networks integrating physics principles.

Key Points

  • PINN-AeroFlow-U achieves high accuracy with prediction errors of 1.063% for pressure and 2.02% for velocity.
  • The model reconstructs aerodynamic quantities around 3D compressor blades by utilizing structured CFD training data.
  • Employing a U-Net-based architecture, the model captures sharp local transitions induced by fluid acceleration near the blade.
  • Incorporating Euler equations and gradient constraints enhances the physical interpretability of the neural network's predictions.

Cite This Study

Wang et al. (2025) studied this question.

synapsesocial.com/papers/68c1ae7054b1d3bfb60e6618https://doi.org/10.3390/math13152396
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. 1Prediction model of the three-dimensional flow field in compressor cascades using shallow neural networks based on sparse pressure data2025 · 1 citations
  2. 2Implicit Neural Representation For Accurate CFD Flow Field Prediction2024
  3. 3Physics-Informed-Neural-Network-Based Fast Prediction Method for Scramjet Nozzle Flow2026
  4. 4Investigation of Compressor Cascade Flow Using Physics-Informed Neural Networks with Adaptive Learning Strategy2024 · 7 citations
  5. 5Investigation of physics-informed deep learning for the prediction of parametric, three-dimensional flow based on boundary data2024 · 6 citations