Railway Point-Operating Machine Fault Detection Using Unlabeled Signaling Sensor Data

Mistry, Pritesh; Lane, Phil; Allen, Paul

doi:10.3390/s20092692

Cited by 14 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Effective protection assures good turnout function and contributes to rail traffic efficiency and safety [ 23 , 24 , 25 , 26 ]. Some researchers have also proposed different incremental methods for classification problems [ 27 ].…”

Section: Resultsmentioning

confidence: 99%

The Fundamental Approach of the Digital Twin Application in Railway Turnouts with Innovative Monitoring of Weather Conditions

Kampczyk

Dybeł

2021

Sensors

View full text Add to dashboard Cite

Improving railway safety depends heavily on the reliability of railway turnouts. The realization of effective, reliable and continuous observations for the spatial analysis and evaluation of the technical condition of railway turnouts is one of the factors affecting safety in railway traffic. The mode and scope of monitoring changes in geometric parameters of railway turnouts with associated indicators needs improvement. The application of digital twins to railway turnouts requires the inclusion of fundamental data indicating their condition along with innovative monitoring of weather conditions. This paper presents an innovative solution for monitoring the status of temperature and other atmospheric conditions. A UbiBot WS1 WIFI wireless temperature logger was used, with an external DS18B20 temperature sensor integrated into an S49 (49E1)-type rail as Tszyn WS1 WIFI. Measurements were made between January and May (winter/spring) at fixed time intervals and at the same measurement point. The aim of the research is to present elements of a fundamental approach of applying digital twins to railway turnouts requiring the consideration and demonstration of rail temperature conditions as a component in the data acquisition of railway turnout condition data and other constituent atmospheric conditions through an innovative solution. The research showed that the presented innovative solution is an effective support for the application of digital twins to railway turnouts and ongoing surveying and diagnostic work of other elements of rail transport infrastructure. The applicability of the TgCWRII second temperature difference indicator in the monitoring of railway turnouts was also confirmed.

show abstract

Section: Resultsmentioning

confidence: 99%

The Fundamental Approach of the Digital Twin Application in Railway Turnouts with Innovative Monitoring of Weather Conditions

Kampczyk

Dybeł

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…The statistical data on derailments confirm the claim in [83] that derailments are common. Mistry et al in [84] concluded that railway point-operating machine (POM) failures are considered to be critical failures of a rail network system. Signaling equipment and turnout failures account for 55% of all railway infrastructure component failures, leading to delays, costly repairs, and potentially hazardous situations.…”

Section: Structure Of the Number Of Derailments And Safety Statusmentioning

confidence: 99%

Measurement of the Geometric Center of a Turnout for the Safety of Railway Infrastructure Using MMS and Total Station

Kampczyk

2020

Sensors

View full text Add to dashboard Cite

The turnouts in railway infrastructure constitute bottlenecks, limiting the capacity of the entire railway network. Due to their design and geometry, these turnouts force speed limits. The need to ensure the proper technical condition of turnouts has prompted ongoing scientific research and the use of modern technological solutions. Until now, there have been no tests for the correct location of the geometric center of a double and outside slip turnout with the related geometric relationships. Therefore, the main objective of this research was to demonstrate the position of the geometric centre of a double slip turnout and the geometric conditions of the curves of circular diverted tracks by measuring the horizontal versines and geometric irregularities of turnouts. The application of this surveying method, with reference to obtuse crossings and arising from geometric dependencies in the double and outside slip turnout, is defined and implemented (also known as a method for checking the correct location of the geometric center of a turnout—Surveying and Monitoring of the Geometric Center of a Double and Outside Slip Turnout (SMDOST)) via the Magnetic-Measuring Square (MMS) and electronic Total Station. This method also recommends measuring the horizontal versines of the diverted tracks. This paper presents the results of field measurements using the SMDOST and MMS methods, which were applied to carry out an analysis and evaluation of the turnout geometry conditions, thereby presenting the irregularities that cause turnout deformations. The validity of the SMDOST method using MMS and Total Station was thus confirmed. The observations from the conducted research indicate that neglecting measurements of the geometry of the turnouts resulted in additional irregularities in their conditions.

show abstract

“…For instance, in the example of engine wear, it is feasible to obtain degradation data through sensor technology, then employ data mining and machine learning algorithms to determine life span and maintenance decisions [6,7,10]. Several reports in the literature discuss using machine learning and statistical modelling to predict wear and failure [11], although work specifically on engine failure rates is not so common, the reports discovered are briefly discussed herein.…”

Section: Introductionmentioning

confidence: 99%

Using Event Data to Build Predictive Engine Failure Models

Mistry

Hughes²,

Gunasekaran

et al. 2023

Machines

Self Cite

View full text Add to dashboard Cite

Diesel engine failures are one reason for delays and breakdowns on the UK rail network, resulting in significant fines and related financial penalties for a train operating company. Preventing such failures is the ultimate goal, but forecasting or predicting future failures before they occur would be highly desirable. In this study, we take real world Diesel Multiple Unit sensor data, recorded in the form of event data, and repurpose it for the remote condition monitoring of critical diesel engine operations. A methodology based on windowing of data is proposed that demonstrates the effective processing of event data for predictive modelling. This study specifically looks at predicting engine failures, and through this methodology, models trained on the processed data resulted in accuracies of 88%. Explainable AI methods are then utilised to provide feature importance explanations for the model’s performance. This information helps the end user understand specifically which sensor data from the larger dataset is most relevant for predicting engine failures. The work presented is useful to the railway industry, but more specifically to train operator companies who ideally want to foresee failures before they occur to avoid significant financial costs. The methodology proposed is applicable for the predictive maintenance of many systems, not just railway diesel engines.

show abstract

Railway Point-Operating Machine Fault Detection Using Unlabeled Signaling Sensor Data

Cited by 14 publications

References 14 publications

The Fundamental Approach of the Digital Twin Application in Railway Turnouts with Innovative Monitoring of Weather Conditions

The Fundamental Approach of the Digital Twin Application in Railway Turnouts with Innovative Monitoring of Weather Conditions

Measurement of the Geometric Center of a Turnout for the Safety of Railway Infrastructure Using MMS and Total Station

Using Event Data to Build Predictive Engine Failure Models

Contact Info

Product

Resources

About