What question did this study set out to answer?

The study aims to enhance the prediction accuracy and interpretability of concrete fatigue life in high-speed railway track slabs by integrating physical mechanisms with machine learning.

February 2, 2026Open Access

Physics-guided GNN-transformer model for multi-scale fatigue life prediction of concrete track slabs in high-speed railways

Key Points

The study aims to enhance the prediction accuracy and interpretability of concrete fatigue life in high-speed railway track slabs by integrating physical mechanisms with machine learning.
Developed a multi-task learning framework combining Graph Neural Network (GNN) and Transformer architectures.
Abstracted concrete microstructure as topological graphs to analyze spatial damage propagation.
Analyzed random load spectra to identify critical temporal patterns influencing fatigue damage.
Evaluated model performance through metrics like Mean Squared Error and Coefficient of Determination.
The model achieved a Mean Squared Error of 0.224 and a Coefficient of Determination of 0.939 after 150 training epochs.
Demonstrated an average prediction latency of 0.86 seconds per sample with 48.3% GPU utilization.
Outperformed existing models across all evaluated indicators.

Abstract

This study establishes a novel machine learning paradigm integrating physical mechanisms. It aims to address the limitations of traditional methods in predicting the concrete fatigue life of high-speed railway (HSR) track slab, particularly their insufficient accuracy and poor interpretability due to overlooking microstructure characteristics and load randomness. The research method innovatively develops a multi-task learning framework combining the Graph Neural Network (GNN) and Transformer architectures. GNN abstracts concrete microstructure as topological graphs to capture spatial damage propagation paths, while Transformer analyzes random load spectra to identify critical temporal patterns determining fatigue damage. The multi-task framework simultaneously predicts fatigue life, damage evolution rate, and residual strength. Experimental results demonstrate the outstanding performance of the proposed GNN-Transformer model. After 150 training epochs, the proposed model achieves a Mean Squared Error of 0.224, Root Mean Square Error of 0.332, and Coefficient of Determination reaching 0.939. Meanwhile, based on the computational architecture used in the experiments, the model achieves an average single-sample prediction latency of 0.86 s and a GPU utilization rate of 48.3%, demonstrating its strong potential for online deployment. All indicators significantly outperform existing models. The study concludes that this framework successfully constructs a high-accuracy, efficient, and physically interpretable prediction model by effectively integrating microstructure topology with macroscopic load sequence features. This study provides robust algorithmic support for predictive maintenance and intelligent health management of HSR infrastructure.

Read Full Paperexternally

KI fragen

Bookmark

View Full Paper