Automatic Detection of Squats in Railway Infrastructure

Molodova, Maria; Li, Zili; Núñez, Alfredo; Dollevoet, Rolf

doi:10.1109/tits.2014.2307955

Cited by 172 publications

(119 citation statements)

References 27 publications

Supporting

Mentioning

118

Contrasting

Unclassified

Order By: Relevance

“…After detection, deterioration state of defects can be assessed so that corrective maintenance measures can be planned according to the damage severity. For example, an ABA system can successfully be used to automatically detect both severe and early stage squats, which are a short wave defect on the rail top (18). In this paper, the ABA system was mounted on a regular Supertram tram with resilient wheels in Sheffield (see Figure 3).…”

Section: Aba Systemmentioning

confidence: 99%

Monitoring bolt tightness of rail joints using axle box acceleration measurements

Oregui

Núñez

et al. 2016

Struct. Control Health Monit.

View full text Add to dashboard Cite

Summary Rail joints are a weak component in railway tracks because of the large impact and wheel‐rail contact forces. Every train passage contributes to the deterioration of rail joints, causing visible (e.g., battered rails) and invisible (e.g., loose bolts) damages. The invisible damage cannot be detected by the commonly performed visual inspection, which is labor intensive, unreliable, intrusive, and unsafe. In this paper, a vehicle‐borne monitoring system is used to automatically detect and assess the tightness condition of bolts at rail joints. The monitoring method is developed based on field axle box acceleration (ABA) measurements using different bolt tightness conditions. The suitability of the method is assessed by bolt tightness prediction and verification of a set of rail joints in the tram network of Sheffield, UK. The results show that ABA system can be employed to monitor bolt tightness conditions at rail joints. With this information, better planning for selective preventive maintenance actions can be taken over rail joints. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Section: Aba Systemmentioning

confidence: 99%

Monitoring bolt tightness of rail joints using axle box acceleration measurements

Oregui

Núñez

et al. 2016

Struct. Control Health Monit.

View full text Add to dashboard Cite

show abstract

“…Furthermore, the comparison between different damaged IRJs suggests that monitoring the prominence of the dominant peak in the frequency range 1000-1150 Hz may help to predict the condition of IRJs. In "Comparison to a Vehicle-Borne Monitoring System" section, it is investigated if the information obtained from the hammer test can be employed for the assessment and monitoring of the condition of IRJs with vehicle-borne monitoring systems which are based on analyzing the dynamic behavior, such as axle box acceleration systems [38][39][40] and strain-gauge-instrumented wheelsets [41].…”

Section: Hammer Measurementmentioning

confidence: 99%

Experimental Investigation Into the Condition of Insulated Rail Joints by Impact Excitation

et al. 2015

View full text Add to dashboard Cite

This paper presents a feasibility study to determine if the health condition of Insulated Rail Joints (IRJs) can be assessed by examining their dynamic response to impact excitation. First, a reference dynamic behavior is defined in the frequency domain of 50-1200 Hz based on field hammer test measurements performed on a IRJ baseline (i.e., a set of IRJ without visible damage). Then, measurements on IRJs with different damage states are compared to the IRJ baseline response via the frequency response function (FRF) based statistical method. Three cases of IRJs are analyzed: a IRJ with a broken fastening, a IRJ with a damaged insulation layer and a IRJ with a rail top with plastic deformation. Combining hammer test measurements, hardness measurements and pictures of the IRJs, two frequency bands were identified as characteristic for damaged IRJs. In the identified high frequency band (1000-1150 Hz), the measured dynamic response with both a vehicle-borne health monitoring system and hammer tests shows a clear difference between the damaged IRJs and the IRJ baseline. Furthermore, different damage types may be able to be identified by examining the dynamic responses in the identified mid-frequency band (420-600 Hz). Further analysis over a larger number of IRJs may complete and support the promising results so that the information can be employed for the condition assessment and monitoring of IRJs.

show abstract

“…The detection and assessment of rail surface defects are normally realized by analyzing frequency-based features. Previously, methods such as the power spectrum density [9], short-time Fourier transform [10] and wavelet transform [11] methods have been adopted for detecting defects in wheels, axle bearings and rails. ABA Pareto-based maintenance decisions for regional railways with uncertain weld conditions using the Hilbert spectrum of axle box acceleration Alfredo Núñez, Senior Member, IEEE, Ali Jamshidi, Hongrui Wang, Student Member, IEEE R Pareto-based maintenance decisions for regional railways with uncertain weld conditions using the Hilbert spectrum of axle box acceleration signals from regional railways are particularly noisy and are affected not only by train speed and wheel conditions but also by a less accurate GPS location.…”

Section: Introductionmentioning

confidence: 99%

Pareto-Based Maintenance Decisions for Regional Railways With Uncertain Weld Conditions Using the Hilbert Spectrum of Axle Box Acceleration

Núñez

Jamshidi

Wang

2019

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

Abstract1 -This paper presents a Pareto-based maintenance decision system for rail welds in a regional railway network. Weld health condition data are collected using a train in operation. A Hilbert spectrum-based approach is used for data processing to detect and assess the weld quality based on multiple registered dynamic responses in the axle box acceleration measurements. The assessment of the welds is stochastic in nature and variant over time, so a set of robust and predictive key performance indicators is defined to capture the weld degradation dynamics during a given maintenance period. Using a scenario-based approach, two objective functions are defined, performance and the number of weld replacements. Evolutionary multi-objective optimization is employed to optimize the objective functions so that the trade-offs between performance and cost support decision-making for railway network maintenance. The results of the proposed methodology show that the infrastructure manager can localize field inspections and maintenance efforts on the area with the most critical welds. To showcase the capability of the proposed methodology, measurements from a regional railway network in Transylvania, Romania are employed.

show abstract

Automatic Detection of Squats in Railway Infrastructure

Cited by 172 publications

References 27 publications

Monitoring bolt tightness of rail joints using axle box acceleration measurements

Monitoring bolt tightness of rail joints using axle box acceleration measurements

Experimental Investigation Into the Condition of Insulated Rail Joints by Impact Excitation

Pareto-Based Maintenance Decisions for Regional Railways With Uncertain Weld Conditions Using the Hilbert Spectrum of Axle Box Acceleration

Contact Info

Product

Resources

About