August 16, 2025Applied SciencesOpen Access

Research on ATT-BiLSTM-Based Restoration Method for Deflection Monitoring Data of a Steel Truss Bridge

View Full Paper

Ask AI

Bookmark

Authors

YCYongjian ChenFuzhou University RLR. LiuYunnan University JWJianlin WangFuzhou University

Discussion

Member takes

Implication

This analysis shows enhanced repair of anomalous monitoring data in steel truss bridges, indicating ATT-BiLSTM's effectiveness over Support Vector Machine models.

Key Points

The repair rate for anomalous data reached 93.88%, showcasing high effectiveness in maintaining data integrity.
The mean square error for the actual complete data was only 0.0226, indicating great accuracy in the repair process.
Anomaly detection utilized correlation heat maps and Gray correlation for key measurement points monitoring.
ATT-BiLSTM model outperformed the Support Vector Machine, preserving important data characteristics while correcting anomalies.

Cite This Study

Chen et al. (2025) studied this question.

synapsesocial.com/papers/68c235fdb210217d647730bd https://doi.org/10.3390/app15158622

View Full Paper

Ask AI

Bookmark

Implication

This analysis shows enhanced repair of anomalous monitoring data in steel truss bridges, indicating ATT-BiLSTM's effectiveness over Support Vector Machine models.

Research on ATT-BiLSTM-Based Restoration Method for Deflection Monitoring Data of a Steel Truss Bridge

Discussion

Member takes

Implication

Key Points

Cite This Study

Research on ATT-BiLSTM-Based Restoration Method for Deflection Monitoring Data of a Steel Truss Bridge

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider