In this paper, we propose a deep convolutional neural network solution to the analysis of image data for the detection of rail surface defects. The images are obtained from many hours of automated video recordings. This huge amount of data makes it impossible to manually inspect the images and detect rail surface defects. Therefore, automated detection of rail defects can help to save time and costs, and to ensure rail transportation safety. However, one major challenge is that the extraction of suitable features for detection of rail surface defects is a non-trivial and difficult task. Therefore, we propose to use convolutional neural networks as a viable technique for feature learning. Deep convolutional neural networks have recently been applied to a number of similar domains with success. We compare the results of different network architectures characterized by different sizes and activation functions. In this way, we explore the efficiency of the proposed deep convolutional neural network for detection and classification. The experimental results are promising and demonstrate the capability of the proposed approach.

/pdf/deep-convolutional-neural-networks-for-detection-of-rail-32jqr6xkmd.pdf

Deep convolutional neural networks for detection of rail surface defects

This paper presents a view of the current state of monitoring track geometry condition from in-service vehicles. It considers technology used to provide condition monitoring; some issues of processing and the determination of location; how things have evolved over the past decade; and what is being, or could/should be done in future research. Monitoring railway track geometry from an in-service vehicle is an attractive proposition that has become a reality in the past decade. However, this is only the beginning. Seeing the same track over and over again provides an opportunity for observing track geometry degradation that can potentially be used to inform maintenance decisions. Furthermore, it is possible to extend the use of track condition information to identify if maintenance is effective, and to monitor the degradation of individual faults such as dipped joints. There are full unattended track geometry measurement systems running on in-service vehicles in the UK and elsewhere around the world, feedin...

/pdf/perspectives-on-railway-track-geometry-condition-monitoring-24z7xbb52q.pdf

Perspectives on railway track geometry condition monitoring from in-service railway vehicles

This paper presents an automatic method for detecting railway surface defects called “squats” using axle box acceleration (ABA) measurements on trains. The method is based on a series of research results from our group in the field of railway engineering that includes numerical simulations, the design of the ABA prototype, real-life implementation, and extensive field tests.We enhance the ABA signal by identifying the characteristic squat frequencies, using improved instrumentation for making measurements, and using advanced signal processing. The automatic detection algorithm for squats is based on wavelet spectrum analysis and determines the squat locations. The method was validated on the Groningen–Assen track in The Netherlands and accurately detected moderate and severe squats with a hit rate of 100%, with no false alarms. The methodology is also sensitive to small rail surface defects and enables the detection of squats at their earliest stage. The hit rate for small rail surface defects was 78%.

/pdf/automatic-detection-of-squats-in-railway-infrastructure-5e7dvhgcos.pdf

Automatic detection of squats in railway infrastructure

A spatial coupling model to study dynamic performance of pantograph-catenary with vehicle-track excitation

The wind-induced vibration of the high-speed catenary and the dynamic behaviour of the pantograph–catenary under stochastic wind field are firstly analysed. The catenary model is established based on nonlinear cable and truss elements, which can fully describe the nonlinearity of each wire and the initial configuration. The model of the aerodynamic forces acting on the messenger/contact wire is deduced by considering the effect of the vertical and horizontal fluctuating winds. The vertical and horizontal fluctuating winds are simulated by employing the Davenport and Panofsky spectrums, respectively. The aerodynamic coefficients of the contact/messenger wire are calculated through computational fluid dynamics. The wind-induced vibration response of catenary is analysed with different wind speeds and angles. Its frequency-domain characteristics are discussed using Auto Regression model. Finally, a pantograph model is introduced and the contact force of the pantograph–catenary under stochastic wind i...

Nonlinear analysis of wind-induced vibration of high-speed railway catenary and its influence on pantograph–catenary interaction

This paper describes a method of estimating irregularities in railway tracks using acceleration data measured from high-speed trains. Track irregularities are the main causes of the vibration of high-speed trains and thus should be carefully monitored to maintain the stability and ride quality of the trains. A mixed filtering approach is proposed for stable displacement estimation and waveband classification of the irregularities in the measured acceleration. Accelerometers are mounted on the axle box and the bogie of a high-speed train to measure the acceleration in the lateral and vertical directions. The estimated results are compared with those of a commercial track geometry measurement system. Finally, the performance of the proposed approach and the relationship between the mounted location of the accelerometers and the estimated track irregularities are discussed.

A Mixed Filtering Approach for Track Condition Monitoring Using Accelerometers on the Axle Box and Bogie

Understanding the dynamic interaction between the catenary and pantograph of a high-speed train is the one of the most important technical issues in the railway industry. This is because the catenary–pantograph system plays a crucial role in providing electric power to the railway vehicle for stable operation. The aim of the present paper is to estimate the current-collection performance of this system by using numerical analysis, in particular, the flexible multibody dynamic analysis technique. To implement large deformable catenary wires, an absolute nodal coordinate formulation is used for the cable element. Additionally, an efficient contact element and an interactive model for the catenary–pantograph system are introduced. Each developed model is then used for analytical and experimental verification. Actual on-line test results of existing high-speed railway vehicles are presented and used to verify the analysis model. Finally, the performance characteristics of a new 400 km/h-class high-speed line ...

Analysis of dynamic interaction between catenary and pantograph with experimental verification and performance evaluation in new high-speed line

This paper is focused on waveband analysis of the lateral and vertical track irregularities from the on-board acceleration measurement of in-service high-speed trains. The track irregularities play important roles to determine dynamic stability of vehicles and ride quality of passengers, so that their amplitude and wavelength should be monitored continuously and carefully. Measuring acceleration at the axle-box or bogie of the trains has been under consideration for low-cost implementation and robust to a harsh railway environment. To estimate the track irregularities, lateral and vertical vibration caused by the wheel/track interaction is measured by the axle-box and bogie mounted accelerometers of an in-service high-speed train. A Kalman filter is used to prevent unrealistic drifts in the estimation. By applying the waveband-pass and compensation filters to the estimated displacement, it is possible to estimate the track irregularities. A distance-wavelength representation is used to identify their waveband in an intuitive way. It is verified by comparing with a commercial track geometry measurement system. From their comparison, it confirms that the representation can produce a satisfactory result.

Waveband Analysis of Track Irregularities in High-Speed Railway from On-Board Acceleration Measurement

Evaluation of the ride comfort for railway vehicles can be divided into two classes; the long-term evaluation of ride comfort and the momentary evaluation of ride comfort. In the present paper, the ride comfort of railway vehicles are investigated for high speed trains in Korea. The long-term ride comfort has been analyzed by a statistical method and the momentary ride comfort has been analyzed by using the longitudinal acceleration, the jerk and the stationary lateral acceleration.

Evaluation of the Ride Comfort for High Speed Trains in Korea

The vibration characteristics of railway vehicles are very complex because they are not only dependent on vehicle and track conditions but also on operating conditions. Vibration can cause the failure of rolling stock equipment. To verify that the quality of rolling stock equipment is acceptable, it should be able to withstand vibration tests of reasonable magnitude and duration. There are many standards for vibration and shock tests of equipment in Korea. In this paper, we have reviewed and compared the standards (KS R 9144, R 9146 and IEC 61373) for vibration and shock tests.

Young Guk Kim

Papers

A Mixed Filtering Approach for Track Condition Monitoring Using Accelerometers on the Axle Box and Bogie

Analysis of dynamic interaction between catenary and pantograph with experimental verification and performance evaluation in new high-speed line

Waveband Analysis of Track Irregularities in High-Speed Railway from On-Board Acceleration Measurement

Evaluation of the Ride Comfort for High Speed Trains in Korea

Comparison and Analysis of Vibration and Shock Test Methods for Rolling Stock Equipment