Back to Search
Start Over
Intelligent Detection of Surface Defects in High-Speed Railway Ballastless Track Based on Self-Attention and Transfer Learning.
- Source :
-
Structural Control & Health Monitoring . 5/18/2024, Vol. 2024, p1-22. 22p. - Publication Year :
- 2024
-
Abstract
- The detection of ballastless track surface (BTS) defects is a prerequisite for ensuring the safe operation of high-speed railways. Traditional convolutional neural networks fail to fully exploit contextual information and lack global pixel representations. The extensive stacking of convolutions leads deep learning models to play a black-box detection role, lacking interpretability. Due to the current lack of sufficient high-quality surface data for ballastless tracks, it is a severe constraint on the accurate identification of the substructure state in high-speed railways. This paper proposes an intelligent detection method for BTS defects named TrackNet based on self-attention and transfer learning. The method enhances the fusion ability of global features of BTS defects using multihead self-attention. The model's dependence on extensive defect data is reduced by transferring knowledge from large-scale publicly available datasets. Experimental results demonstrate that compared to advanced Swin Transformer model results, the TrackNet model achieves improvements in average accuracy and F1-score by 5.15% and 5.16%, respectively, on limited test data. The TrackNet model visualizes the decision regions of the model in identifying BTS defects, revealing the black-box recognition mechanism of deep learning models. This research performs engineering applications and provides valuable insights for the multiclass recognition of BTS defects in high-speed railways. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 15452255
- Volume :
- 2024
- Database :
- Academic Search Index
- Journal :
- Structural Control & Health Monitoring
- Publication Type :
- Academic Journal
- Accession number :
- 177355988
- Full Text :
- https://doi.org/10.1155/2024/2967927