September 10, 2025PolymersOpen Access

Fatigue Life Prediction of CFRP-FBG Sensor-Reinforced RC Beams Enabled by LSTM-Based Deep Learning

View Full Paper

Ask AI

Bookmark

Authors

Discussion

This approach utilizes LSTM networks for precise fatigue life predictions in structures, suggesting enhanced monitoring capabilities.

The LSTM model reduced mean squared error by 61.62%, significantly improving predictions.
Principal Component Analysis helped isolate critical features for robust fatigue life assessment.
The method proved effective for capturing nonlinear dynamics in sensor data.
Results demonstrate substantial improvements in prediction stability and accuracy for structural health monitoring.

Jia et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark