Share Email Print
cover

Proceedings Paper • new

Detecting anomalies in longitudinal elevation of track geometry using train dynamic responses via a variational autoencoder
Author(s): Jingxiao Liu; Yujie Wei; Mario Bergés; Jacobo Bielak; James H. Garrett Jr.; HaeYoung Noh
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Track geometry is one of the most important health indices in the maintenance of rail tracks. Visual inspection and inspection using a track-geometry car are two common approaches to inspect track geometry. Presently, using accelerations from in-service trains has become a popular track inspection approach, because it is a low-cost way to monitor the rail tracks more frequently. However, due to the noise presented in the collected accelerations, detecting anomalies using manually designed features often results in many false alarms. In this paper, we propose a learning-based anomaly detection approach for monitoring the longitude elevation of track geometry from the dynamic response of an in-service train. We consider the track geometry with a sudden change as an anomaly, measured by the signal energy of slopes of the track geometry. The proposed approach uses a variational autoencoder (VAE) to detect the anomaly. The VAE takes accelerations as input and learns a mapping from the frequency-domain representation of acceleration signals to a low-dimensional latent space that represents the distribution of the observed data. The reconstruction probability, which measures the variability of the distribution of the input data, is used as an anomaly score for indicating how well the input follows the normal pattern. Compared to distance- and density-based anomaly detection methods, such as K-nearest neighbor and clustering, the VAE-based anomaly detection is robust to measurement noise and prevents overfitting because it captures the underlying distribution of the data in a low-dimensional space. Furthermore, the VAE-based method does not require model-specific thresholds for detecting anomalies because it uses a probabilistic measurement instead of reconstruction error as the anomaly score. We validate the proposed VAE-based approach on the vibration dataset from an in-service train. We show that this approach outperforms a baseline model (an autoencoder-based anomaly detection method) in terms of recall, precision, and F1-score. The proposed method also successfully addresses the overfitting problem presenting in recurrent neural network-based methods. The results make the proposed approach a strong candidate for low-cost and frequent track geometry inspection.

Paper Details

Date Published: 27 March 2019
PDF: 13 pages
Proc. SPIE 10970, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2019, 109701B (27 March 2019); doi: 10.1117/12.2513711
Show Author Affiliations
Jingxiao Liu, Carnegie Mellon Univ. (United States)
Yujie Wei, Carnegie Mellon Univ. (United States)
Mario Bergés, Carnegie Mellon Univ. (United States)
Jacobo Bielak, Carnegie Mellon Univ. (United States)
James H. Garrett Jr., Carnegie Mellon Univ. (United States)
HaeYoung Noh, Carnegie Mellon Univ. (United States)


Published in SPIE Proceedings Vol. 10970:
Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2019
Jerome P. Lynch; Haiying Huang; Hoon Sohn; Kon-Well Wang, Editor(s)

© SPIE. Terms of Use
Back to Top