Intelligent detection of loose fasteners in railway tracks using distributed acoustic sensing and machine learning

Abstract

Loose fasteners in railway tracks present a potential safety concern for train operations, especially when fasteners at sharp curves become loosened or when multiple consecutive fasteners are loosened. Traditional inspection methods are inefficient due to the large number of fasteners along the rail. This study introduces Fiber-optic based Distributed Acoustic Sensing (DAS) technology for real-time health monitoring of rail track, and proposes a DAS-based framework including both supervised and unsupervised learning methods for detecting loosened fasteners. In the supervised approach, a DAS signal anomaly detection (DSAD) model is proposed to directly predict the torque applied to the fasteners. Conversely, the unsupervised method employs a DAS signal anomaly detection Variational Autoencoder (DSAD-VAE) model, which evaluates the difference between the reconstructed and input signals to quantitatively assess the extent of loosening of rail fasteners. In the laboratory track tests, the DSAD model achieves an average prediction accuracy of about 1 N m per bolt, while the DSAD-VAE model attains an impressive F1-score of 0.9 for classification. Furthermore, during field tests conducted on a subway track, the DSAD model achieves a F1-score of 0.9917 for fastener loosening classification, while the DSAD-VAE model achieves 100% accuracy in unsupervised monitoring of fastener anomalies.