Monitoring the Condition of Railway Tracks Using a Convolutional Neural Network

Tsunashima, Hitoshi; Takikawa, Masashi

doi:10.5772/intechopen.102672

Cited by 5 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tsunashima et al developed a system to identify track faults by using accelerometers and GNSS placed on the car-body of in-service vehicles [1][2][3][4][5].…”

Section: Car-body-mounted Sensorsmentioning

confidence: 99%

“…A new method for automatically classifying the type and degradation level of track faults using a convolutional neural network (CNN) by imaging car-body acceleration on a time-frequency plane by continuous wavelet transform [5].…”

Section: Signal Processingmentioning

confidence: 99%

“…In this study, the Morlet wavelet, which has a good performance between localization of time and frequency, was used [5,28].…”

Section: Continuous Wavelet Transform (Cwt)mentioning

confidence: 99%

“…However, these methods are labor-intensive and costly, and many operators cannot carry out sufficient track inspections of regional railways due to limited financial resources. To address this problem, a track diagnosis system using an exclusive onboard sensing device has been developed [1][2][3][4][5].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Track Condition Monitoring Based on In-Service Train Vibration Data Using Smartphones

Tsunashima¹,

Honda²,

Matsumoto³

2024

Civil Engineering

Self Cite

View full text Add to dashboard Cite

Although track maintenance is important, many operators of regional railway with limited financial resources are unable to conduct sufficient track inspections. In response to this problem, a track condition diagnosis system using car-body vibration sensors has been developed. In this study, a track condition monitoring system using a smartphone for general use has been developed. A technique for identifying train location using global navigation satellite system (GNSS) speed is proposed. The results of field testing shows that track condition diagnosis is possible using a smartphone-based monitoring system.

show abstract

“…Tsunashima et al developed a system to identify track faults by using accelerometers and GNSS placed on the car-body of in-service vehicles [1][2][3][4][5].…”

Section: Car-body-mounted Sensorsmentioning

confidence: 99%

Section: Signal Processingmentioning

confidence: 99%

“…In this study, the Morlet wavelet, which has a good performance between localization of time and frequency, was used [5,28].…”

Section: Continuous Wavelet Transform (Cwt)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Track Condition Monitoring Based on In-Service Train Vibration Data Using Smartphones

Tsunashima¹,

Honda²,

Matsumoto³

2024

Civil Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…The longitudinal level degradation was shown to be associated with frequencies below 5 Hz, making it distinguishable from localized defects, which are more related to a higher frequency range. In an investigation involving similar track faults, Tsunashima & Takikawa [41] demonstrated the feasibility of applying Convolutional Neural Networks directly to the time-frequency color map representation to automatically identify and distinguish between these defects.…”

Section: Track Irregularities Assessmentmentioning

confidence: 99%

Drive-by Methodologies Applied to Railway Infrastructure Subsystems: A Literature Review—Part II: Track and Vehicle

et al. 2023

View full text Add to dashboard Cite

Railways are one of the most important means of transportation, allowing people and goods to move quickly, environmentally beneficially, and efficiently over long distances. To ensure safe and reliable operations, regular condition-based assessments of trains and track are of paramount importance. Drive-by methodologies, which utilize data collected by onboard monitoring systems as the vehicle travels over the track, have gained popularity as an economically viable strategy for monitoring extensive track networks as well as vehicles traveling on them. This paper presents a critical review of these methodologies applied to railway tracks and vehicles. It assesses research on track irregularities, rail conditions, and the condition of rail supporting elements, highlighting important early developments and recent papers that provide insights into future practical applications. Additionally, the paper explores works related to global vehicle condition evaluation, focusing on the identification of suspension and wheelset element damage and also discussing challenges towards commercial application. The findings suggest that drive-by methodologies have several promising future applications. These include track maintenance optimization, proactive fault detection, predictive maintenance, track performance evaluation, vehicle health monitoring, and data-driven decision-making. By leveraging drive-by assessments, railway operators can optimize maintenance efforts, detect faults early, predict remaining component life, evaluate track performance, monitor vehicle health, and make informed decisions based on data analysis. Finally, a comprehensive conclusion summarizes the achievements thus far and provides perspectives for forthcoming developments. The future practical applications of drive-by methodologies discussed in this review have the potential to revolutionize railway track and vehicle assessments, leading to safer and more efficient railway operations in the days to come.

show abstract

Multiclass Classification of Rail Track Defects Using Deep Learning Techniques

Bhat,

Karegowda,

2023

2023 International Conference on Smart Systems for Applications in Electrical Sciences (ICSSES)

View full text Add to dashboard Cite

Monitoring the Condition of Railway Tracks Using a Convolutional Neural Network

Cited by 5 publications

References 18 publications

Track Condition Monitoring Based on In-Service Train Vibration Data Using Smartphones

Track Condition Monitoring Based on In-Service Train Vibration Data Using Smartphones

Drive-by Methodologies Applied to Railway Infrastructure Subsystems: A Literature Review—Part II: Track and Vehicle

Multiclass Classification of Rail Track Defects Using Deep Learning Techniques

Contact Info

Product

Resources

About