Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 2, 2026BiomimeticsOpen Access

Compressor Flow Perception via Deep Learning Modeling with Multi-Source Dynamic Fusion of Temporal Features by Bio-Inspired Optimization

View Full Paper
Ask AI
Bookmark
Share

Authors

MZMingming ZhangYZYuying ZhaoHLHui Li

Discussion

Loading...

Member takes

Overview

Randomized trial identifies aerodynamic instability in aeroengines, suggesting improved operation stability and reliability.

Key Points

  • The aim is to enhance the stability and reliability of aeroengine operation through advanced flow perception.
  • Developed a deep learning model based on cross-attention and bidirectional long short-term memory (CA_BiLSTM).
  • Integrated variational mode decomposition and Dung Beetle Optimizer into a coupled prediction model.
  • Constructed a dual-channel fusion model to capture complex flow characteristics.
  • Achieved advanced instability detection at 1580 r, overcoming limitations of single-point monitoring.
  • Demonstrated superior anti-interference capability compared to traditional methods.
  • Successfully integrated inlet and outlet signals for collated flow characterization.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/6a4600a29ed1343031310aechttps://doi.org/10.3390/biomimetics11070452
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. 1C(NN)FD - Deep Learning Modelling of Multi-Stage Axial Compressors Aerodynamics2025
  2. 2A multimodal attention fusion-based model for velocity field prediction of supersonic isolators2026 · 3 citations
  3. 3A dual-module deep learning approach for flow field prediction in supersonic isolators from noisy signals2026 · 1 citations
  4. 4The improved CNN_BILSTM hybrid model for predicting compressor stall2025
  5. 5Global stability prediction of compression ramp flow based on deep neural networks2025