Condition Monitoring of Railway Tracks from Car-Body Vibration Using a Machine Learning Technique

Tsunashima, Hitoshi

doi:10.3390/app9132734

Cited by 65 publications

(56 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The numerical analysis was used for verification of the efficiency and robustness of the Kriging surrogate model. Tsunashima [22] proposed a condition monitoring system for real-time inspection of regional railway lines in Japan. The car body vibration was predicted and used for feature extraction by machine learning algorithm.…”

Section: Sensors Parameter Identification and Signal Processingmentioning

confidence: 99%

Special Feature Vibration-Based Structural Health Monitoring

Park

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

Section: Sensors Parameter Identification and Signal Processingmentioning

confidence: 99%

Special Feature Vibration-Based Structural Health Monitoring

Park

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…For analysing large volume of the measurement data, an algorithm that automatically diagnose track conditions from car-body vibrations using machine learning technique has been developed [2]. In the reference [2], RMS values are used to identify track irregularities for longitudinal level, alignment, cross level. However, it is difficult to classify the track faults by types using RMS values because frequency information is lost in the RMS values.…”

Section: Introductionmentioning

confidence: 99%

Condition monitoring of railway track from car-body vibration using time–frequency analysis

Tsunashima

Hirose

2020

Vehicle System Dynamics

Self Cite

View full text Add to dashboard Cite

Proper maintenance of railway tracks is essential to ensure railway safety. A track condition monitoring system was developed for the preventive maintenance of the track by installing the on-board sensing device in the in-service vehicles and monitoring the track condition by measuring the car-body acceleration. This paper describes the application of time-frequency analysis for the condition monitoring of railway tracks. Car-body acceleration simulated by a 10-DOF vehicle model, with a faulty track, was used to identify the track faults using Hilbert-Huang transform (HHT). Field tests were carried out using the developed track condition monitoring system to show the effectiveness of the time-frequency analysis using HHT. Simulation studies and field test results showed that HHT can yield a good time-frequency resolution and that intrinsic mode functions (IMFs) can provide the detailed information of track faults.

show abstract

“…In order to achieve comprehensive detection and management of all wheels, the only solution is to install sensors on every wheel. Hence, on-board detection methods are usually used to evaluate track structure rather than long-term monitoring of wheel conditions [14].…”

Section: Introductionmentioning

confidence: 99%

Railway Wheel Flat Recognition and Precise Positioning Method Based on Multisensor Arrays

et al. 2020

View full text Add to dashboard Cite

Featured Application: Wheel flats are one of the most threatening defects during the service lifespan of railway vehicle wheels. This study proposes a new long-term monitoring method for wheel flats based on multisensor arrays. The dynamic strain responses of rails are captured by sensor arrays mounted on the rail web, ensuring that all the wheels are assessed during the train passage. Through data fusion among multiple sensors, the method locates the specific position of wheel defects. This study provides potential guidance for the maintenance of vehicles soon after the occurrences of defects.Abstract: Wheel flats have become a major problem affecting the long-term service of railway systems. Wheels with flats create intermittent impact loads to trains and rails. This not only accelerates the deterioration of vehicle and track components but also leads to abnormal wheel-rail contact conditions. An effective method for detecting wheel conditions is urgently needed to ensure the operation of the railway and provide guidance for the repair of wheels. However, most previous researches have used qualitative detection methods, and hence have been unable to achieve accurate positioning of the wheel flats. In addition, the theoretical basis for the layout scheme for wheel flat detection sensors is lacking, making it impossible to meet the needs of field applications. In this study, we simulated the spatial distribution characteristics of rail strain, under different wheel flat conditions, and based on this, a layout scheme of multisensor arrays was proposed which more effectively captured the responses of the wheel flats. A wheel flat recognition and precise positioning method based on multisensor fusion was designed. The algorithm was validated through the combination of experimental and simulation methods. The result shows that the algorithm can ideally detect and locate the wheel flats under complex conditions.

show abstract

Condition Monitoring of Railway Tracks from Car-Body Vibration Using a Machine Learning Technique

Cited by 65 publications

References 13 publications

Special Feature Vibration-Based Structural Health Monitoring

Special Feature Vibration-Based Structural Health Monitoring

Condition monitoring of railway track from car-body vibration using time–frequency analysis

Railway Wheel Flat Recognition and Precise Positioning Method Based on Multisensor Arrays

Contact Info

Product

Resources

About