Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 28, 2025Proceedings

Investigation on Aerodynamic Data Fusion for Low-Reynolds-Number Compressors Based on Multi-Fidelity Deep Neural Networks

View Full Paper
Ask AI
Bookmark
Share

Authors

RCRuoyu ChenXRXun RenZLZiliang Li

Discussion

Loading...

Member takes

Overview

This research demonstrates improved flow field reconstruction in compressors using a dual-modal deep neural network, highlighting low Reynolds number challenges.

Key Points

  • Accurate reconstruction of flow fields under low Reynolds number conditions is achieved using a Multi-Fidelity Deep Neural Network model, ensuring smooth and consistent results.
  • The MFDNN method improved accuracy in regions like flow separation and wakes, even with limited experimental data.
  • Employing a dual-modal training strategy allows coupling of low-fidelity and high-fidelity models, enhancing the overall flow field reconstruction process.
  • Results indicate reliable accuracy and performance of the model in solving inverse problems related to turbomachinery.

Cite This Study

Chen et al. (2025) studied this question.

synapsesocial.com/papers/68d913b24ddcf71ba560c091https://doi.org/10.33737/gpps25-tc-075
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. 1Aerodynamic data fusion for low-Reynolds-number compressors based on film-Re physics-guided multi-fidelity network2025
  2. 2Investigation on compressor flow field reconstruction using deep neural networks with a fine-tuned strategy2025
  3. 3C(NN)FD - Deep Learning Modelling of Multi-Stage Axial Compressors Aerodynamics2025
  4. 4Multi-fidelity deep learning for aerodynamic shape optimization using convolutional neural network2024 · 18 citations
  5. 5Multi-fidelity aerodynamic data analysis by using composite neural network2024