sensors-logo

Journal Browser

Journal Browser

Advances in Condition Monitoring of Railway Infrastructures

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Fault Diagnosis & Sensors".

Deadline for manuscript submissions: closed (20 July 2023) | Viewed by 24941

Printed Edition Available!
A printed edition of this Special Issue is available here.

Special Issue Editors


E-Mail Website
Guest Editor
Department of Civil Engineering, University of Porto, Praça de Gomes Teixeira, 4099-002 Porto, Portugal
Interests: railway engineering; condition monitoring (wayside/onboard); damage identification; machine learning
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Civil Engineering, School of Engineering, Polytechnic of Porto, 4200-072 Porto, Portugal
Interests: railway infrastructures; dynamic testing; damage identification; remote inspection; data science
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Civil Engineering, University College Dublin, D04 V1W8 Dublin, Ireland
Interests: structural dynamics and assessments; railway track monitoring; railway bridge monitoring; machine learning for SHM
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Mechanical Engineering and Construction, Universitat Jaume I, Avda. Sos Baynat s/n, ES-12071 Castellón, Spain
Interests: railway induced vibrations; dynamics of railway bridges; moving loads; resonance and cancellation phenomena; dynamic experimental testing; modal identification; model updating; energy harvesting; human induced vibrations; artificial intelligence; control of structures; advanced seismic designrailway induced vibrations; advanced seismic design

Special Issue Information

Dear Colleagues,

In recent years, relevant investments have been made in the construction of new railway lines as well as in the rehabilitation and upgrading of existing lines. Many of these lines include a significant number of critical infrastructures whose operational and safety conditions must be preserved during their life cycle. Recent scientific and technological advances have enabled more efficient structural condition monitoring of railway infrastructures, mainly through the implementation of intelligent strategies for inspection, monitoring, maintenance and risk management. Based on this framework, this Special Issue aims at bringing together the latest research studies, findings and achievements with regard to the condition monitoring of railway infrastructures. Theoretical, experimental and computational investigations (or a combination of these) are welcome. Expected papers will cover several topics related (but not exclusively) to:

  • structural integrity;
  • structural condition assessment;
  • automatic damage detection/identification;
  • wayside and onboard monitoring systems;
  • weigh-in-motion and bridge weigh-in-motion systems;
  • digital twins;
  • model calibration and validation;
  • novel health monitoring;
  • new sensors and technologies (photogrammetry, laser scanning, drones, wireless);
  • computer vision techniques;
  • non-destructive testing (NDT);
  • remote inspection strategies;
  • BIM;
  • Big Data and Internet of Things;
  • artificial intelligence;
  • augmented reality and virtual reality;
  • disaster risk reduction;
  • emergency management;
  • intelligent management systems;
  • condition assessment under extreme load scenarios/climate changes (wind, seismic, flooding, scour).

Dr. Araliya Mosleh
Dr. Diogo Ribeiro
Dr. Abdollah Malekjafarian
Dr. Maria D. Martínez-Rodrigo
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (11 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Editorial

Jump to: Research

4 pages, 178 KiB  
Editorial
Advances in Condition Monitoring of Railway Infrastructure
by Araliya Mosleh, Diogo Ribeiro, Abdollah Malekjafarian and Maria D. Martínez-Rodrigo
Sensors 2024, 24(3), 830; https://doi.org/10.3390/s24030830 - 26 Jan 2024
Viewed by 995
Abstract
In recent years, there has been a notable surge in investments directed towards developing new railway lines and revitalising existing ones, reflecting a global commitment to enhance transportation infrastructure [...] Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)

Research

Jump to: Editorial

19 pages, 3885 KiB  
Article
FS-RSDD: Few-Shot Rail Surface Defect Detection with Prototype Learning
by Yongzhi Min, Ziwei Wang, Yang Liu and Zheng Wang
Sensors 2023, 23(18), 7894; https://doi.org/10.3390/s23187894 - 15 Sep 2023
Cited by 2 | Viewed by 1433
Abstract
As an important component of the railway system, the surface damage that occurs on the rails due to daily operations can pose significant safety hazards. This paper proposes a simple yet effective rail surface defect detection model, FS-RSDD, for rail surface condition monitoring, [...] Read more.
As an important component of the railway system, the surface damage that occurs on the rails due to daily operations can pose significant safety hazards. This paper proposes a simple yet effective rail surface defect detection model, FS-RSDD, for rail surface condition monitoring, which also aims to address the issue of insufficient defect samples faced by previous detection models. The model utilizes a pre-trained model to extract deep features of both normal rail samples and defect samples. Subsequently, an unsupervised learning method is employed to learn feature distributions and obtain a feature prototype memory bank. Using prototype learning techniques, FS-RSDD estimates the probability of a test sample belonging to a defect at each pixel based on the prototype memory bank. This approach overcomes the limitations of deep learning algorithms based on supervised learning techniques, which often suffer from insufficient training samples and low credibility in validation. FS-RSDD achieves high accuracy in defect detection and localization with only a small number of defect samples used for training. Surpassing benchmarked few-shot industrial defect detection algorithms, FS-RSDD achieves an ROC of 95.2% and 99.1% on RSDDS Type-I and Type-II rail defect data, respectively, and is on par with state-of-the-art unsupervised anomaly detection algorithms. Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)
Show Figures

Figure 1

21 pages, 7730 KiB  
Article
A Non-Intrusive Monitoring System on Train Pantographs for the Maintenance of Overhead Contact Lines
by Borja Rodríguez-Arana, Pablo Ciáurriz, Nere Gil-Negrete and Unai Alvarado
Sensors 2023, 23(18), 7890; https://doi.org/10.3390/s23187890 - 14 Sep 2023
Viewed by 1555
Abstract
The condition monitoring of an overhead contact line (OCL) is investigated by developing an innovative monitoring system for a pantograph on an electrical multiple unit of a regional line. Kinematic and dynamic modelling of the pantograph is conducted to support the designed monitoring [...] Read more.
The condition monitoring of an overhead contact line (OCL) is investigated by developing an innovative monitoring system for a pantograph on an electrical multiple unit of a regional line. Kinematic and dynamic modelling of the pantograph is conducted to support the designed monitoring system. The modelling is proved through rigorous test-rig experiments, while the proposed methodology is then validated through extensive field tests. The field tests serve a dual purpose: First, to validate the monitoring system using benchmark measurements of the tCat® trolley, and second, to assess the reproducibility of measurements in a realistic case. This paper presents the OCL monitoring system developed in the framework of the H2020 project SIA. The accuracy of our results is not far from that of other commercial systems, with just 12 mm of absolute error in the height measurement. Therefore, they provide reliable information about trends in various key performance indicators (KPIs) that facilitates the early detection of failures and the diagnosis of anomalies. The results highlight the importance of model calibration and validation in enabling novel health monitoring capabilities for the pantograph. By continuously monitoring the parameters and tracking their degradation trends, our approach allows for optimized scheduling of maintenance tasks for the OCL. Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)
Show Figures

Figure 1

15 pages, 24039 KiB  
Article
Seeking a Sufficient Data Volume for Railway Infrastructure Component Detection with Computer Vision Models
by Alicja Gosiewska, Zuzanna Baran, Monika Baran and Tomasz Rutkowski
Sensors 2023, 23(18), 7776; https://doi.org/10.3390/s23187776 - 9 Sep 2023
Cited by 2 | Viewed by 1104
Abstract
Railway infrastructure monitoring is crucial for transportation reliability and travelers’ safety. However, it requires plenty of human resources that generate high costs and is limited to the efficiency of the human eye. Integrating machine learning into the railway monitoring process can overcome these [...] Read more.
Railway infrastructure monitoring is crucial for transportation reliability and travelers’ safety. However, it requires plenty of human resources that generate high costs and is limited to the efficiency of the human eye. Integrating machine learning into the railway monitoring process can overcome these problems. Since advanced algorithms perform equally to humans in many tasks, they can provide a faster, cost-effective, and reproducible evaluation of the infrastructure. The main issue with this approach is that training machine learning models involves acquiring a large amount of labeled data, which is unavailable for rail infrastructure. We trained YOLOv5 and MobileNet architectures to meet this challenge in low-data-volume scenarios. We established that 120 observations are enough to train an accurate model for the object-detection task for railway infrastructure. Moreover, we proposed a novel method for extracting background images from railway images. To test our method, we compared the performance of YOLOv5 and MobileNet on small datasets with and without background extraction. The results of the experiments show that background extraction reduces the sufficient data volume to 90 observations. Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)
Show Figures

Figure 1

17 pages, 4969 KiB  
Article
A Machine-Learning-Based Approach for Railway Track Monitoring Using Acceleration Measured on an In-Service Train
by Abdollah Malekjafarian, Chalres-Antoine Sarrabezolles, Muhammad Arslan Khan and Fatemeh Golpayegani
Sensors 2023, 23(17), 7568; https://doi.org/10.3390/s23177568 - 31 Aug 2023
Cited by 7 | Viewed by 2954
Abstract
In this paper, a novel railway track monitoring approach is proposed that employs acceleration responses measured on an in-service train to detect the loss of stiffness in the track sub-layers. An Artificial Neural Network (ANN) algorithm is developed that works with the energies [...] Read more.
In this paper, a novel railway track monitoring approach is proposed that employs acceleration responses measured on an in-service train to detect the loss of stiffness in the track sub-layers. An Artificial Neural Network (ANN) algorithm is developed that works with the energies of the train acceleration responses. A numerical model of a half-car train coupled with a track profile is employed to simulate the train vertical acceleration. The energy of acceleration signals measured from 100 traversing trains is used to train the ANN for healthy track conditions. The energy is calculated every 15 m along the track, each of which is called a slice. In the monitoring phase, the trained ANN is used to predict the energies of a set of train crossings. The predicted energies are compared with the simulated ones and represented as the prediction error. The damage is modeled by reducing the soil stiffness at the sub-ballast layer that represents hanging sleepers. A damage indicator (DI) based on the prediction error is proposed to visualize the differences in the predicted energies for different damage cases. In addition, a sensitivity analysis is performed where the impact of signal noise, slice sizes, and the presence of multiple damaged locations on the performance of the DI is assessed. Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)
Show Figures

Figure 1

19 pages, 7925 KiB  
Article
Freight Wagon Digitalization for Condition Monitoring and Advanced Operation
by Iker Moya, Alejandro Perez, Paul Zabalegui, Gorka de Miguel, Markos Losada, Jon Amengual, Iñigo Adin and Jaizki Mendizabal
Sensors 2023, 23(17), 7448; https://doi.org/10.3390/s23177448 - 27 Aug 2023
Viewed by 1887
Abstract
Traditionally, freight wagon technology has lacked digitalization and advanced monitoring capabilities. This article presents recent advancements in freight wagon digitalization, covering the system’s definition, development, and field tests on a commercial line in Sweden. A number of components and systems were installed on [...] Read more.
Traditionally, freight wagon technology has lacked digitalization and advanced monitoring capabilities. This article presents recent advancements in freight wagon digitalization, covering the system’s definition, development, and field tests on a commercial line in Sweden. A number of components and systems were installed on board on the freight wagon, leading to the intelligent freight wagon. The digitalization includes the integration of sensors for different functions such as train composition, train integrity, asset monitoring and continuous wagon positioning. Communication capabilities enable data exchange between components, securely stored and transferred to a remote server for access and visualization. Three digitalized freight wagons operated on the Nässjo–Falköping line, equipped with strategically placed monitoring sensors to collect valuable data on wagon performance and railway infrastructure. The field tests showcase the system’s potential for detecting faults and anomalies, signifying a significant advancement in freight wagon technology, and contributing to an improvement in freight wagon digitalization and monitoring. The gathered insights demonstrate the system’s effectiveness, setting the stage for a comprehensive monitoring solution for railway infrastructures. These advancements promise real-time analysis, anomaly detection, and proactive maintenance, fostering improved efficiency and safety in the domain of freight transportation, while contributing to the enhancement of freight wagon digitalization and supervision. Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)
Show Figures

Figure 1

27 pages, 8636 KiB  
Article
An Unsupervised Learning Approach for Wayside Train Wheel Flat Detection
by Mohammadreza Mohammadi, Araliya Mosleh, Cecilia Vale, Diogo Ribeiro, Pedro Montenegro and Andreia Meixedo
Sensors 2023, 23(4), 1910; https://doi.org/10.3390/s23041910 - 8 Feb 2023
Cited by 14 | Viewed by 2292
Abstract
One of the most common types of wheel damage is flats which can cause high maintenance costs and enhance the probability of failure and damage to the track components. This study aims to compare the performance of four feature extraction methods, namely, auto-regressive [...] Read more.
One of the most common types of wheel damage is flats which can cause high maintenance costs and enhance the probability of failure and damage to the track components. This study aims to compare the performance of four feature extraction methods, namely, auto-regressive (AR), auto-regressive exogenous (ARX), principal component analysis (PCA), and continuous wavelet transform (CWT) capable of automatically distinguishing a defective wheel from a healthy one. The rail acceleration for the passage of freight vehicles is used as a reference measurement to perform this study which comprises four steps: (i) feature extraction from acquired responses using the specific feature extraction methods; (ii) feature normalization based on a latent variable method; (iii) data fusion to enhance the sensitivity to recognize defective wheels; and (iv) damage detection by performing an outlier analysis. The results of this research show that AR and ARX extraction methods are more efficient techniques than CWT and PCA for wheel flat damage detection. Furthermore, in almost every feature, a single sensor on the rail is sufficient to identify a defective wheel. Additionally, AR and ARX methods demonstrated the potential to distinguish a defective wheel on the left and right sides. Lastly, the ARX method demonstrated robustness to detect the wheel flat with accelerometers placed only in the sleepers. Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)
Show Figures

Figure 1

14 pages, 2703 KiB  
Article
Semantic Segmentation of Terrestrial Laser Scans of Railway Catenary Arches: A Use Case Perspective
by Bram Ton, Faizan Ahmed and Jeroen Linssen
Sensors 2023, 23(1), 222; https://doi.org/10.3390/s23010222 - 26 Dec 2022
Cited by 7 | Viewed by 2902
Abstract
Having access to accurate and recent digital twins of infrastructure assets benefits the renovation, maintenance, condition monitoring, and construction planning of infrastructural projects. There are many cases where such a digital twin does not yet exist, such as for legacy structures. In order [...] Read more.
Having access to accurate and recent digital twins of infrastructure assets benefits the renovation, maintenance, condition monitoring, and construction planning of infrastructural projects. There are many cases where such a digital twin does not yet exist, such as for legacy structures. In order to create such a digital twin, a mobile laser scanner can be used to capture the geometric representation of the structure. With the aid of semantic segmentation, the scene can be decomposed into different object classes. This decomposition can then be used to retrieve cad models from a cad library to create an accurate digital twin. This study explores three deep-learning-based models for semantic segmentation of point clouds in a practical real-world setting: PointNet++, SuperPoint Graph, and Point Transformer. This study focuses on the use case of catenary arches of the Dutch railway system in collaboration with Strukton Rail, a major contractor for rail projects. A challenging, varied, high-resolution, and annotated dataset for evaluating point cloud segmentation models in railway settings is presented. The dataset contains 14 individually labelled classes and is the first of its kind to be made publicly available. A modified PointNet++ model achieved the best mean class Intersection over Union (IoU) of 71% for the semantic segmentation task on this new, diverse, and challenging dataset. Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)
Show Figures

Figure 1

15 pages, 4081 KiB  
Article
An Ensemble Learning Aided Computer Vision Method with Advanced Color Enhancement for Corroded Bolt Detection in Tunnels
by Lei Tan, Tao Tang and Dajun Yuan
Sensors 2022, 22(24), 9715; https://doi.org/10.3390/s22249715 - 11 Dec 2022
Cited by 10 | Viewed by 2194
Abstract
Bolts, as the basic units of tunnel linings, are crucial to safe tunnel service. Caused by the moist and complex environment in the tunnel, corrosion becomes a significant defect of bolts. Computer vision technology is adopted because manual patrol inspection is inefficient and [...] Read more.
Bolts, as the basic units of tunnel linings, are crucial to safe tunnel service. Caused by the moist and complex environment in the tunnel, corrosion becomes a significant defect of bolts. Computer vision technology is adopted because manual patrol inspection is inefficient and often misses the corroded bolts. However, most current studies are conducted in a laboratory with good lighting conditions, while their effects in actual practice have yet to be considered, and the accuracy also needs to be improved. In this paper, we put forward an Ensemble Learning approach combining our Improved MultiScale Retinex with Color Restoration (IMSRCR) and You Only Look Once (YOLO) based on truly acquired tunnel image data to detect corroded bolts in the lining. The IMSRCR sharpens and strengthens the features of the lining pictures, weakening the bad effect of a dim environment compared with the existing MSRCR. Furthermore, we combine models with different parameters that show different performance using the ensemble learning method, greatly improving the accuracy. Sufficient comparisons and ablation experiments based on a dataset collected from the tunnel in service are conducted to prove the superiority of our proposed algorithm. Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)
Show Figures

Figure 1

17 pages, 7926 KiB  
Article
Virtual Axle Detector Based on Analysis of Bridge Acceleration Measurements by Fully Convolutional Network
by Steven Robert Lorenzen, Henrik Riedel, Maximilian Michael Rupp, Leon Schmeiser, Hagen Berthold, Andrei Firus and Jens Schneider
Sensors 2022, 22(22), 8963; https://doi.org/10.3390/s22228963 - 19 Nov 2022
Cited by 6 | Viewed by 1782
Abstract
In the practical application of the Bridge Weigh-In-Motion (BWIM) methods, the position of the wheels or axles during the passage of a vehicle is a prerequisite in most cases. To avoid the use of conventional axle detectors and bridge type-specific methods, we propose [...] Read more.
In the practical application of the Bridge Weigh-In-Motion (BWIM) methods, the position of the wheels or axles during the passage of a vehicle is a prerequisite in most cases. To avoid the use of conventional axle detectors and bridge type-specific methods, we propose a novel method for axle detection using accelerometers placed arbitrarily on a bridge. In order to develop a model that is as simple and comprehensible as possible, the axle detection task is implemented as a binary classification problem instead of a regression problem. The model is implemented as a Fully Convolutional Network to process signals in the form of Continuous Wavelet Transforms. This allows passages of any length to be processed in a single step with maximum efficiency while utilising multiple scales in a single evaluation. This allows our method to use acceleration signals from any location on the bridge structure and act as Virtual Axle Detectors (VADs) without being limited to specific structural types of bridges. To test the proposed method, we analysed 3787 train passages recorded on a steel trough railway bridge of a long-distance traffic line. Results of the measurement data show that our model detects 95% of the axles, which means that 128,599 out of 134,800 previously unseen axles were correctly detected. In total, 90% of the axles were detected with a maximum spatial error of 20 cm, at a maximum velocity of vmax=56.3m/s. The analysis shows that our developed model can use accelerometers as VADs even under real operating conditions. Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)
Show Figures

Figure 1

18 pages, 5897 KiB  
Article
Characteristic Differences of Wind-Blown Sand Flow Field of Expressway Bridge and Subgrade and Their Implications on Expressway Design
by Shengbo Xie, Xian Zhang and Yingjun Pang
Sensors 2022, 22(11), 3988; https://doi.org/10.3390/s22113988 - 24 May 2022
Cited by 1 | Viewed by 1750
Abstract
Bridges and subgrades are the main route forms for expressways. The ideal form for passing through sandy areas remains unclear. This study aims to understand the differences in the influence of expressway bridges and subgrades on the near-surface blown sand environment and movement [...] Read more.
Bridges and subgrades are the main route forms for expressways. The ideal form for passing through sandy areas remains unclear. This study aims to understand the differences in the influence of expressway bridges and subgrades on the near-surface blown sand environment and movement laws, such as the difference in wind speed and profile around the bridge and subgrade, the difference in wind flow-field characteristics, and the difference in sand transport rate, to provide a scientific basis for the selection of expressway route forms in sandy areas. Therefore, a wind tunnel test was carried out by making models of a highway bridge and subgrade and comparing the environmental effects of wind sand on them. The disturbance in the bridge to near-surface blown sand activities was less than that of the subgrade. The variation ranges of the wind speed of the bridge and its upwind and downwind directions were lower than those of the subgrade. However, the required distance to recover the wind speed downwind of the bridge was greater than that of the subgrade, resulting in the sand transport rate of the bridge being lower than that of the subgrade. The variation in the wind field of the subgrade was more drastic than that of the bridge, but the required distance to recover the wind field downwind of the bridge was greater than that of the subgrade. In the wind speed-weakening area upwind, the wind speed-weakening range and intensity of the bridge were smaller than those of the subgrade. In the wind speed-increasing area on the top of the model, the wind speed-increasing range and intensity of the bridge were smaller than those of the subgrade. In the wind-speed-weakening area downwind, the wind speed weakening range of the bridge was greater than that of the subgrade, and the wind speed-weakening intensity was smaller than that of the subgrade. This investigation has theoretical and practical significance for the selection of expressway route forms in sandy areas. Full article
(This article belongs to the Special Issue Advances in Condition Monitoring of Railway Infrastructures)
Show Figures

Figure 1

Back to TopTop