Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
February 9, 2026ElectronicsOpen Access

ST-GC-GRU: A Hybrid Deep Learning Approach for Shield Attitude Prediction Based on a Spatial–Temporal Graph

View Full Paper
Ask AI
Bookmark
Share

Authors

WLWen LiuJCJia Ao ChenSWShanshan Wang

Discussion

Loading...

Member takes

Overview

A hybrid approach predicts shield attitude deviations in tunnel construction, suggesting enhanced accuracy for adaptive control technology.

Key Points

  • To develop an effective model for predicting shield attitude deviations during tunnel construction.
  • Proposed ST-GC-GRU model utilizing spatial-temporal graphs and GCNs.
  • Applied time decomposition technique for better representation of attitude changes.
  • Compared performance with seven existing prediction models using real data tests.
  • ST-GC-GRU model demonstrates superior prediction performance compared to traditional methods.
  • Achieved improvements in predictions during significant attitude changes.
  • Outperformed seven other models in accuracy across four attitude deviation values.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/698979d9f0ec2af6756e7c8chttps://doi.org/10.3390/electronics15030711
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. 1Shield Machine Attitude Prediction Method Based on Causal Graph Convolutional Network2026
  2. 2Prediction of shield tunneling attitude: A hybrid deep learning approach considering feature temporal attention2024 · 1 citations
  3. 3A Novel Hybrid Deep Learning for Attitude Prediction in Sustainable Application of Shield Machine2025
  4. 4Shield machine pose prediction based on CNN-GRU-Attention2024 · 7 citations
  5. 5Multi-step intelligent prediction of shield machine position attitude on the basis of BWO-CNN-LSTM-GRU2024 · 8 citations