Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 10, 2025Proceedings of the Institution of Mechanical Engineers Part G Journal of Aerospace Engineering

Investigation on compressor flow field reconstruction using deep neural networks with a fine-tuned strategy

View Full Paper
Ask AI
Bookmark
Share

Authors

RCRuoyu ChenZLZiliang LiQLQingkuo Li

Discussion

Loading...

Member takes

Overview

Investigative approach shows improved predictions for compressor flow fields, indicating efficient use of computational resources.

Key Points

  • The FTDNN model achieves a maximum average relative error of only 1.29% on extreme flow fields.
  • A deep neural network with two prediction modes was developed using a comprehensive aerodynamic dataset.
  • The research explores the trade-off between generalization and accuracy based on hidden layer configurations.
  • Optimal prediction performance is achieved when equal numbers of frozen and trainable hidden layers are used.

Cite This Study

Chen et al. (2025) studied this question.

synapsesocial.com/papers/68c1d7ee54b1d3bfb60f9e82https://doi.org/10.1177/09544100251358759
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. 1Investigation on Aerodynamic Data Fusion for Low-Reynolds-Number Compressors Based on Multi-Fidelity Deep Neural Networks2025
  2. 2C(NN)FD - Deep Learning Modelling of Multi-Stage Axial Compressors Aerodynamics2025
  3. 3C(NN)FD - A Deep Learning Framework for Turbomachinery CFD Analysis2024 · 5 citations
  4. 4Implicit Neural Representation For Accurate CFD Flow Field Prediction2024
  5. 5Prediction model of the three-dimensional flow field in compressor cascades using shallow neural networks based on sparse pressure data2025 · 1 citations