Search

Track geometry is one of the critical indicators of railway tracks' condition which requires continuous monitoring and maintenance over time. In this paper, a novel artificial intelligence (AI) based framework is proposed for railway track geometry inspection using vibration data collected from a dedicated measuring high-speed train. This AI-based anomaly track detection approach consists of two main stages. Firstly, a subset of features that best characterizes the track condition is defined. Several dynamic features from time domain data are extracted and importance scores are assigned to them, to determine the most effective subset for the purpose of track condition monitoring. Secondly, a data-driven based anomaly detection approach is developed to assess and identify track geometrical defects. In this stage, the acceleration responses collected from an in-service train traversing on a healthy track zone are employed as input into a One-Class Support Vector Machine (OCSVM) algorithm. The proposed algorithm defines the anomalies as relative changes to the historical behaviour. A comprehensive dataset from field measurements using a Société Nationale des Chemins de Fer Français (SNCF) Réseau IRIS320 highspeed train is used in this paper to implement the proposed approach. In addition, the impact of using different features and different locations/directions of the sensors on the accuracy of detecting geometrical defects is investigated. It is also shown that the OCSVM approach outperforms other algorithms based on Isolation Forest (IF), Local Outlier Factor (LOF), and Robust Mahalanobis Distance (RMD) in terms of recall, precision, and F1-score. The proposed anomaly detection approach has demonstrated a 12% increase in defect detection accuracy compared to the direct utilization of the raw acceleration response, which can facilitate track monitoring using in-service trains while providing cost-efficient maintenance in the future. [Display omitted] [ABSTRACT FROM AUTHOR]

Track geometry is one of the critical indicators of railway tracks' condition which requires continuous monitoring and maintenance over time. In this paper, a novel artificial intelligence (AI) based framework is proposed for railway track geometry inspection using vibration data collected from a dedicated measuring high-speed train. This AI-based anomaly track detection approach consists of two main stages. Firstly, a subset of features that best characterizes the track condition is defined. Several dynamic features from time domain data are extracted and importance scores are assigned to them, to determine the most effective subset for the purpose of track condition monitoring. Secondly, a data-driven based anomaly detection approach is developed to assess and identify track geometrical defects. In this stage, the acceleration responses collected from an in-service train traversing on a healthy track zone are employed as input into a One-Class Support Vector Machine (OCSVM) algorithm. The proposed algorithm defines the anomalies as relative changes to the historical behaviour. A comprehensive dataset from field measurements using a Société Nationale des Chemins de Fer Français (SNCF) Réseau IRIS320 highspeed train is used in this paper to implement the proposed approach. In addition, the impact of using different features and different locations/directions of the sensors on the accuracy of detecting geometrical defects is investigated. It is also shown that the OCSVM approach outperforms other algorithms based on Isolation Forest (IF), Local Outlier Factor (LOF), and Robust Mahalanobis Distance (RMD) in terms of recall, precision, and F1-score. The proposed anomaly detection approach has demonstrated a 12% increase in defect detection accuracy compared to the direct utilization of the raw acceleration response, which can facilitate track monitoring using in-service trains while providing cost-efficient maintenance in the future. [Display omitted] [ABSTRACT FROM AUTHOR]

This paper proposes a novel data-driven framework for scour detection around offshore wind turbines (OWTs), where damage features are derived from wind and wave-induced acceleration signals collected along the tower. A numerical model of the NREL 5 MW wind turbine, which considers aerodynamic and hydrodynamic loading with soil-structure interaction (SSI) and servo-dynamics, is developed. The model is used to simulate the acceleration responses along the tower for a healthy structure, and a structure affected by progressive scour. A data segmentation process is initially performed on the collected data, which is followed by a feature selection scheme based on the analysis-of-variance (ANOVA) algorithm, to eliminate irrelevant characteristics from the time domain feature set of responses. The proposed framework consists of two main components: (a) offline training, and (b) real-time classification. The acceleration responses collected from the healthy structure and the structure subjected to three different damage scenarios (different scour depths) and under various load conditions, are used in the offline training mode. The selected feature vector from the feature extraction process is used as input to a Naive Bayes classifier (NBC) algorithm to train the model. In the real-time classification, a prediction of the scour depth affecting the structure is performed using a new dataset simulated from unseen load cases and scour conditions of the OWT. The results show that the model trained in the offline stage can predict the scour depth in the real-time monitoring stage with performance measures over approximately 94%. • A novel data-driven framework is proposed for scour detection around offshore wind turbines. • Damage features are derived from wind and wave-induced acceleration signals collected along the tower. • The data from the healthy structure and the structure subjected to three different damage scenarios and under various load conditions, are used in the offline training mode. • A prediction of the scour depth is performed using a new dataset simulated from unseen load cases and scour conditions of the OWT in the real-time classification. [ABSTRACT FROM AUTHOR]