Regular inspection of railway track health is crucial for maintaining safe and reliable train operations. Factors, such as cracks, ballast issues, rail discontinuity, loose nuts and bolts, burnt wheels, superelevation, and misalignment developed on the rails due to non-maintenance, pre-emptive investigations and delayed detection, pose a grave danger and threats to the safe operation of rail transport. The traditional procedure of manually inspecting the rail track using a railway cart is both inefficient and prone to human error and biases. In a country like Pakistan where train accidents have taken many lives, it is not unusual to automate such approaches to avoid such accidents and save countless lives. This study aims at enhancing the traditional railway cart system to address these issues by introducing an automatic railway track fault detection system using acoustic analysis. In this regard, this study makes two important contributions: data collection on Pakistan railway tracks using acoustic signals and the application of various classification techniques to the collected data. Initially, three types of tracks are considered, including normal track, wheel burnt and superelevation, due to their common occurrence. Several well-known machine learning algorithms are applied such as support vector machines, logistic regression, random forest and decision tree classifier, in addition to deep learning models like multilayer perceptron and convolutional neural networks. Results suggest that acoustic data can help determine the track faults successfully. Results indicate that the best results are obtained by RF and DT with an accuracy of 97%.
Regular inspection of railway track health is crucial for maintaining safe and reliable train operations. Factors, such as cracks, ballast issues, rail discontinuity, loose nuts and bolts, burnt wheels, superelevation, and misalignment developed on the rails due to non-maintenance, pre-emptive investigations and delayed detection, pose a grave danger and threats to the safe operation of rail transport. The traditional procedure of manually inspecting the rail track using a railway cart is both inefficient and prone to human error and biases. In a country like Pakistan where train accidents have taken many lives, it is not unusual to automate such approaches to avoid such accidents and save countless lives. This study aims at enhancing the traditional railway cart system to address these issues by introducing an automatic railway track fault detection system using acoustic analysis. In this regard, this study makes two important contributions: data collection on Pakistan railway tracks using acoustic signals and the application of various classification techniques to the collected data. Initially, three types of tracks are considered, including normal track, wheel burnt and superelevation, due to their common occurrence. Several well-known machine learning algorithms are applied such as support vector machines, logistic regression, random forest and decision tree classifier, in addition to deep learning models like multilayer perceptron and convolutional neural networks. Results suggest that acoustic data can help determine the track faults successfully. Results indicate that the best results are obtained by RF and DT with an accuracy of 97%.
“…18. Generally, RCF defects observed at high rails in heavy haul operations, such as gauge corner checking, shelling and flaking, are originated from the rail surface or 2-8 mm underneath the gauge corner of the rail head [6]. The difference may be attributed to the consideration of only one combination of wheel and rail profiles in this study.…”
Section: Discussionmentioning
confidence: 87%
“…Initiation of rail degradation, such as rolling contact fatigue (RCF) or wear, will primarily occur where the ratcheting strain reaches the limiting ductility of the rail material [4,5]. Wear at curved tracks has been found in many cases [6,7] and it is proportional to contact pressure, number of loading cycles [8,9], friction level and creepage level [10]. Throughout the past few decades, the introduction of higher axle loads and annual haulage rates has placed more emphasis on the performance of of rails in curved track.…”
“…6 According to current knowledge, squats start to evolve from either surface or sub-surface defects. 5,7 In combination with unfavourable contact conditions, such as a high contact pressure or microslip, squats can propagate below the running surface up to a depth of a few millimetres.…”
Section: Introductionmentioning
confidence: 99%
“…In literature, the shape is often described “as if a heavy gnome sat or squatted on the rail leaving two similarly sized lobes behind.” 6 According to current knowledge, squats start to evolve from either surface or sub-surface defects. 5,7 In combination with unfavourable contact conditions, such as a high contact pressure or micro-slip, squats can propagate below the running surface up to a depth of a few millimetres.Figure 1.Top view of a rail with a severe squat. The typical V shape of the initiating cracks on the surface is visible with the dark depression due to the crack network below the surface.…”
Squats are rather complex failure mechanisms in rails and challenge railway operators all over the world, thus calling for a detailed investigation of squats by means of finite element analysis to locate the initiation and propagating mechanisms. In this work, a cyclic three-dimensional (3D) finite element model of a wheel-rail contact including an initial penny-shaped defect is used. This work presents the implementation of the starting penny-shaped crack in the rail for a wheel-rail simulation by utilising a submodel strategy. Moreover, viable evaluation options are shown. In the future, this set-up will help to assess multiple crack positions and possible squat growth mechanisms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
