Railway Track Inspection Research Articles

Rail Detection Research Status of Multi -Sensing Technology

Traditional rail inspection methods, primarily relying on manual inspection and basic equipment, face significant challenges including low efficiency, poor accuracy, and susceptibility to human error. This paper presents a comprehensive review of the current research status and future trends in multi-sensor rail transit inspection vehicles. The focus is on the integrated application of various sensing technologies, particularly inertial systems and visual sensing, to achieve high-precision and efficient measurement of rail geometrical parameters. An in-depth analysis of key technologies and challenges in railway track inspection is provided, exploring how advanced sensing methods can overcome the limitations of traditional approaches. The paper also examines the market prospects for rail transit inspection, highlighting the growing demand for more sophisticated and reliable inspection systems. Furthermore, potential future research directions in this field are outlined, including the development of AI-powered data analysis, real-time defect detection algorithms, and the integration of emerging technologies such as LiDAR and thermal imaging. This review aims to provide valuable insights for researchers, engineers, and industry professionals working on advancing rail inspection technologies.

IoT Based Railway Track Faults Detection and Localization using Acoustic Analysis and Signalling

Ensuring the safety and efficiency of rail transportation is paramount, necessitating timely inspection of railway tracks to prevent potential hazards. This research introduces an innovative approach by implementing an Internet of Things (IoT)-based autonomous railway track fault detection system. Various track components, such as rail surface defects, broken sleepers, missing fasteners, and irregular ballast levels, can lead to hazardous situations if not properly monitored. This master's thesis proposes an efficient method for classifying track components using image processing techniques and deep learning algorithms. Specifically, it focuses on detecting missing fasteners by analyzing images captured by a line camera. Experimental results demonstrate the method's effectiveness and robustness in complex environments. Future work aims to develop a comprehensive model capable of classifying all track components simultaneously. Image processing is utilized to extract individual components such as fasteners, rail, ballast, and sleepers, with the model trained to classify fastener states. This research contributes to advancing railway inspection methods, mitigating operational costs, preventing accidents, and enhancing passenger experience

Development of track component health indices using image-based railway track inspection data

The primary role of the US Department of Transportation (USDOT) Federal Railroad Administration (FRA) is ensuring the safe operation of railway rolling stock and infrastructure by way of regulatory oversight. FRA regulations require US railroads to conduct visual track inspections as often as twice per week depending on a specific track segment’s FRA track class, which also governs maximum train operating speed. Such inspections are often subjective due to the inherent limitations of human visual inspection and cognition. Additionally, human visual inspections require some level of risk given the need for inspectors to be on track while also consuming valuable network capacity. As a result, and the desire to collect objective data to improve both safety and maintenance planning, railroads are pursuing new means and methods to assess track condition and evaluate track component health. This paper presents a numerical method to define track component health using field data collected on the High Tonnage Loop (HTL) at the Transportation Technology Center (TTC) in Pueblo, Colorado, USA. Line scan laser and image data of the track were captured using a 3D Laser Triangulation system and were subsequently processed using Deep Convolutional Neural Networks (DCNNs). The track heath quantification method proposed establishes benchmarks that were developed based on the understanding of railway track mechanics, high axle load (HAL) railroad engineering instructions, and FRA regulations. The novel metrics presented are referred to as Track Component Heath Indices (TCHIs) and are quantitative values that objectively assess track condition and provide a means to monitor condition change with time and tonnage. These data can be used in conjunction with traditional track geometry and other forms of track heath data (e.g. GPR and rail profile) to more holistically assess the condition of the track structure and its components and ultimately predict its future state.

Symmetry-Driven Unsupervised Abnormal Object Detection for Railway Inspection

Vision-based abnormal object detection in railway track inspection images is one of the critical tasks to ensure the safety of railway transportation. Even though many machine learning based methods have been developed, these approaches heavily rely on anomaly supervisions and therefore can not detect unknown anomaly classes. In order to tackle the problem, this paper proposes a novel unsupervised method to detect abnormal objects, which does not require abnormal object training data. Specially, we find that a railway track image is almost symmetrical about the track central line, i.e., normal objects appear repeatedly and symmetrically, while abnormal ones are rare and also significantly different from the corresponding symmetric areas. Motivated by this observation, we propose to train a metric-learning based deep model to learn the similarity between normal objects and the corresponding symmetrical areas. Then for each object proposal in one test image, we measure the distance between the proposal and the corresponding symmetrical regions, and determine whether it is an abnormal object based on the symmetrical metric. Extensive experiments on our collected dataset show that our proposed method achieves competitive performance compared with the state-of-the-art methods.

A Review on the Prospects of Mobile Manipulators for Smart Maintenance of Railway Track

Inspection and repair interventions play vital roles in the asset management of railways. Autonomous mobile manipulators possess considerable potential to replace humans in many hazardous railway track maintenance tasks with high efficiency. This paper investigates the prospects of the use of mobile manipulators in track maintenance tasks. The current state of railway track inspection and repair technologies is initially reviewed, revealing that very few mobile manipulators are in the railways. Of note, the technologies are analytically scrutinized to ascertain advantages, unique capabilities, and potential use in the deployment of mobile manipulators for inspection and repair tasks across various industries. Most mobile manipulators in maintenance use ground robots, while other applications use aerial, underwater, or space robots. Power transmission lines, the nuclear industry, and space are the most extensive application areas. Clearly, the railways infrastructure managers can benefit from the adaptation of best practices from these diversified designs and their broad deployment, leading to enhanced human safety and optimized asset digitalization. A case study is presented to show the potential use of mobile manipulators in railway track maintenance tasks. Moreover, the benefits of the mobile manipulator are discussed based on previous research. Finally, challenges and requirements are reviewed to provide insights into future research.

Dealing with disruptions in railway track inspection using risk-based machine learning

Unplanned track inspections can be a direct consequence of any disruption to the operation of on-board track geometry monitoring activities. A novel response strategy to enhance the value of the information for supplementary track measurements is thus established to construct a data generation model. In this model, artificial (synthetic) data is assigned on each measurement point along the affected track segment over a short period of time. To effectively generate artificial track measurement data, this study proposes a NARX (nonlinear autoregressive with exogenous variables) model, which incorporates short-range memory dependencies in the dependent variable and integrates interdependent effects from external factors. Nonlinearities in the proposed model have been determined using an artificial neural network that allowed fast computation of a mapping function in line with the needs of effective disruption management. The risk of over fitting the data generation model, which reflected its generalisation ability, has been effectively managed through risk aversion concept. For the model evaluation, the deviation of track longitudinal level has been taken as a case study, predicted using its degradation rate and track alignment and gauge as exogenous variables. Simulation results on two datasets that are statistically different showed that the data generation model for disrupted track measurements is reliable, accurate, and easy-to-use. This novel model is an essential breakthrough in railway track integrity prediction and resilient operation management.

Largest Connected-ERFNet for Autonomous Railway Track Detection and Real-time Tracking

Unmanned aerial vehicle (UAV) is expected to have the potential to complete the collection of defect information in track areas with lower labor costs and higher efficiency. In this field, autonomous railway track detection and real-time tracking to guide UAVs are quite essential. However, the limited computation resources of the UAV onboard computer make it difficult to maintain high accuracy in realtime detection and tracking using the deep learning model with a complex structure. Concerning this issue, for the daily detection scene of the track, this paper proposes a novel autonomous railway track detection and real-time tracking algorithm named Largest Connected-ERFNet, which combines ERFNet and the largest connected component labeling to ensure the accuracy of the track area detection and tracking. A comprehensive set of experiments on UAV onboard computer are conducted for verification. Experiments demonstrate the superior performance of the algorithm proposed in this paper. Under the condition of limited training data and computation resources, the detection precision of the algorithm reaches 89.2%, the detection speed reaches 5.5 fps, and the smoothness reaches 99.4%. It is proven that the proposed method can meet the practical needs of using UAVs for railway track inspection.

PMSM Speed Sensorless System of Intercity Railway Track Inspection Trolley Based on FOSMO-MRAS Observer

For realizing the speed sensorless control system of the intercity railway track inspection trolley, reducing the manufacturing cost and volume weight of the track inspection trolley, and improving the performance of the three-phase permanent magnet synchronous motor (PMSM) control system inside the track inspection trolley, a new fractional sliding mode variable structure model reference adaptive (FOSMO-MRAS) method is proposed to construct the motor speed observer, and a new sliding mode approach law is constructed by using a hyperbolic tangent function instead of a traditional discontinuous switching function. The simulation results show that the speed sensorless control strategy of PMSM based on the FOSMO-MRAS observer has good dynamic and static performance. And the robustness and reliability of the system are improved.

A Deep-Learning-Powered Near-Real-Time Detection of Railway Track Major Components: A Two-Stage Computer-Vision-Based Method

A deep-learning-powered two-stage method for automating the inspection of railway track major components is developed in this article. Rails and two types of fasteners: 1) bolts and 2) clippers, are considered as major targeted objects in this study. Based on railway images, the developed method realizes the accurate railway track inspection via two stages: 1) the initial detection and 2) the detection calibration. At stage I, a squeeze and excitation participated YOLOv3 model is developed to generate initial detection results. A domain-logic-based hybrid model (DLHM) developed with the domain knowledge is introduced to enhance the detection performance at stage II. The DLHM consists of two modules: 1) a module for the problematic region calibration and 2) another module for the symmetric region calibration. The developed DLHM offers a high probability on inspecting overlooked or misclassified interested objects generated from stage I. The effectiveness of the proposed method for detecting railway tracks is validated with field collected railway images. An overall 95.2% mAP can be achieved via the proposed method. Four state-of-the-art deep-learning-based methods are considered as benchmarks to verify advantages of the proposed method. Via a deep comparative analytics, we show that the proposed method offers a state-of-the-art performance in the railway track major component inspection task.

Scanning Inductive Thermographic Surface Defect Inspection of Long Flat or Curved Work-Pieces Using Rectification Targets

Inductive thermography is an NDT method, which can be excellently used to inspect long metallic specimens (such as railway tracks) to detect surface defects. Aiming at the inspection of railway tracks in service with a movable setup, the method had to be advanced from a stationary application to a scanning setup. This work presents methods for using calibration targets for rectification, in order to improve the quality of the resulting images. Two scanning techniques are presented for detecting different types of rolling contact fatigue (RCF) defects on rail pieces. In the case of the first method, separate stationary inductive pulsed measurements are carried out for the segments of a long sample and the results are stitched together to one panoramic image of the whole specimen (“stop-and-go”). Since the surface of the rail piece is curved, rectification of the surface with a flexible grid is necessary to generate seamless panoramic images. In the case of the second method, a specimen is moved with constant speed underneath the induction coil. For the detection of shallow surface cracks, the infrared camera has to have a view of the surface during the heating; therefore, the camera is placed behind the coil but tilted towards a position below the induction coil. In order to be able to evaluate phase images from the temporal temperature change, a checkerboard grid as a rectification target is used. It is also analyzed how the chosen IR camera frame rate and the motion speed affect the scanning result.

Подходы в планировании планово-предупредительной выправки и оценка состояния пути

Purpose: The research of the matters of planning of planned-preventive setup of a rail way and the analysis of rail track geometry condition before and after the pursing of the setup basing on data of track measuring car passage have shown that existing criteria of the assignment of track planned-preventive setup do not consider exploitation conditions and their reconsideration is demanded. Methods: Statistical methods were used in research pursuing on the matters of planning and evaluation of railway track condition after work fulfillment on planned-preventive setup. Data sampling and analysis of statistical observations have allowed to distinguish applied approaches in the planning of track planned-preventive setup for various exploitation conditions. Grouped in dynamics rows furbished kilometers were evaluated according to the indicators: second degree retreat presence, rail track geometry state estimation before and after repairs and by the end of repairs year. Results: The discrepancies with established criteria were identified at planning on including of kilometers into address plan of track planed-preventive setup, the data on work accomplishment quality and rail way state changes during the first year after repairs were obtained. Practical importance: Research results confirm the necessity to reconsider the criteria for track planed-preventive setup assignment with the distinguishing there separately the main and additional criteria in dependence of exploitation conditions. It’s necessary to pursue railway track inspection in accordance with normative document requirements of federal level and JSC RZD.

Railway Track Inspection Using Deep Learning Based on Audio to Spectrogram Conversion: An on-the-Fly Approach.

The periodic inspection of railroad tracks is very important to find structural and geometrical problems that lead to railway accidents. Currently, in Pakistan, rail tracks are inspected by an acoustic-based manual system that requires a railway engineer as a domain expert to differentiate between different rail tracks’ faults, which is cumbersome, laborious, and error-prone. This study proposes the use of traditional acoustic-based systems with deep learning models to increase performance and reduce train accidents. Two convolutional neural networks (CNN) models, convolutional 1D and convolutional 2D, and one recurrent neural network (RNN) model, a long short-term memory (LSTM) model, are used in this regard. Initially, three types of faults are considered, including superelevation, wheel burnt, and normal tracks. Contrary to traditional acoustic-based systems where the spectrogram dataset is generated before the model training, the proposed approach uses on-the-fly feature extraction by generating spectrograms as a deep learning model’s layer. Different lengths of audio samples are used to analyze their performance with each model. Each audio sample of 17 s is split into 3 variations of 1.7, 3.4, and 8.5 s, and all 3 deep learning models are trained and tested against each split time. Various combinations of audio data augmentation are analyzed extensively to investigate models’ performance. The results suggest that the LSTM with 8.5 split time gives the best results with the accuracy of 99.7%, the precision of 99.5%, recall of 99.5%, and F1 score of 99.5%.

Optimal Inspection Scheduling Model for Monitoring Railway Track Grids

The optimization of railway track inspection schedules is of great significance for the monitoring of railway track conditions and reasonable organization of track maintenance tasks. Here, an optimal inspection scheduling model for monitoring railway tracks is proposed. Railway track inspection activities are divided into equal‐length units in the time and spatial location dimensions. The various constraints and objectives on the time and location of different track inspection activities are defined in detail regarding subdivisions of individual management units. The objectives of the model development are to achieve a more optimized equilibrium and robustness of the track inspection schedule. Based on the maximum entropy criterion, entropy is used to measure the distribution equilibrium of the inspection schedule in the time dimension. The proposed model is verified using actual data from the Lanxin railway.

Route planning for capacity restricted agents over railway network, without disrupting train schedules

Deploying mobile instrumentation for railway track inspection is a routing and scheduling problem, that can be benefited from plans which don’t disrupt regular train schedules. In this work, we avoid disrupting train schedules by modeling unavailability of railway tracks, thereby improving reliability without sacrificing on costs. The approach involves a novel mathematical formulation for C apacitated A rc R outing P roblem with T emporal restrictions due to arc U navailabilities (CARP-TU). In addition, we discuss the challenges in CARP-TU w.r.t sibling problems, and propose a suitable column generation algorithm for improving upper and lower bounds. The proposed algorithm is validated over few benchmark datasets, and then two variants of the proposed algorithm are compared to analyse the bound improvements w.r.t problem size.

Design of multifunctional railway track inspection vehicle

With the continuous construction of railway network, it is more and more important to maintain the operating state of railway track. Meanwhile, due to the rising departure density, the time available for maintenance is shortened, and the contradiction between operation and maintenance is becoming increasingly acute. In order to improve the efficiency of track maintenance, this paper proposes a multi-functional railway track comprehensive test platform, which can effectively integrate the existing track maintenance equipment, improve the maintenance kilometers per unit time, and puts forward a set of matching internet data management system, which has important practical value for improving the modernization of track operation.

Railway track availability modelling with opportunistic maintenance practice

The geometry of railway track must be maintained within certain standards in order to provide a highly available network, as well as good ride comfort and safety for all rail users. Modelling is well utilised as part of asset management tools in exploring the effectiveness of different rail geometry maintenance strategies. By considering the rail route as an entire system – in contrast to a track section in isolation – a more effective maintenance strategy can be developed, including the deployment of opportunistic maintenance practice. This study presents a Coloured Petri Net model of railway track degradation, inspection, and maintenance planning and delivery, for an entire route of track sections. Opportunistic maintenance is introduced through a novel search transition function, which groups interventions based on local adjacency. Testing explores the availability and maintenance demands expected when following a series of different management strategies. This is extended to testing under heatwave conditions, a known disrupter to track geometry maintenance delivery. Simulation results show that in following an opportunistic strategy, greater availability can be achieved on the modelled rail line. Further, resilience to the heatwave disruptions can be achieved by selecting the correct maintenance strategy parameters. This asset management tool can provide guidance on management strategies for a full route of track sections as a combined system.

The Design and Implementation of an Inertial GNSS Odometer Integrated Navigation System Based on a Federated Kalman Filter for High-Speed Railway Track Inspection

The detection of track geometry parameters is essential for the safety of high-speed railway operation. To improve the accuracy and efficiency of the state detector of track geometry parameters, in this study we propose an inertial GNSS odometer integrated navigation system based on the federated Kalman, and a corresponding inertial track measurement system was also developed. This paper systematically introduces the construction process for the Kalman filter and data smoothing algorithm based on forward filtering and reverse smoothing. The engineering results show that the measurement accuracy of the track geometry parameters was better than 0.2 mm, and the detection speed was about 3 km/h. Thus, compared with the traditional Kalman filter method, the proposed design improved the measurement accuracy and met the requirements for the detection of geometric parameters of high-speed railway tracks.

Research on application of deep convolutional network in high-speed railway track inspection based on distributed fiber acoustic sensing

The shortcomings of the commonly used track inspection methods in high-speed railway are the high cost and the safety risks. Distributed optical fiber acoustic sensors (DAS) technology owns lots of performance benefits (e.g. anti-interference and real-time performance) and its potential to be a great help in the field of track inspection has been proved by various empirical certifications under its accuracy and practicability. In this paper, we first take a part of tracks in some high-speed rail track as the experimental object, and describe the deployment of DAS and the process of data collection. Then we propose a new scheme for the rail track state inspection with a deep convolutional network as the core. The selection and processing of data and the innovation of network structure have been experimentally verified.

Rail corrugation inspection by a self-contained triple-repellent electromagnetic energy harvesting system

Rail corrugation, a widely distributed periodic wear pattern of the railway track, is a severe rail defect that could cause high-pitched noises and vibrations of the ground and nearby buildings. The current rail corrugation inspection trolley can only be employed offline, whereas online monitoring devices require external batteries that depend heavily on manual maintenance. This paper presents a novel approach by monitoring the rail corrugation online using a self-contained energy harvesting system. The mechanics of the magnetic-floating energy harvester was improved by a triple-magnet configuration, and differences between repellent and attractive configurations were investigated. Comprehensive broad-band (5–2000 Hz) sinusoidal sweeping vibration tests and stochastic vibration tests were conducted based on the measured railway track spectra. The wavelet theory was used to carry out time–frequency analysis and identify the defects of the rail corrugation. The results indicate that the proposed system could collect the rail vibration energy across a wider frequency range as well as identify the rail corrugation by the induced voltage of the energy harvesters. This study offers a new sustainable approach toward rail corrugation monitoring by the self-contained energy harvesting system that could eliminate environmentally-unfriendly batteries and reduce manual involvement for railway track inspection.

Study of loaded versus unloaded measurements in railway track inspection

To ensure railway operations safe, track geometry parameters, e.g., track gauge, are usually inspected using track geometry cars. The measurement frequency of track geometry cars is low (twice per year) due to high operational costs and track possession. An innovative way to perform track inspection at high frequency and affordable cost is using mobile track inspection systems, which can be easily mounted on passenger or freight trains. Besides track geometry, it also creates a digital copy of railway corridors providing asset managers with the ability to make fully informed decisions on track assets. Differently, the collectors of mobile systems are further away from the axle than track geometry cars, which are regarded as unloaded and loaded measurement respectively. This difference may lead to a discrepancy in measurement results. This paper studies the difference between loaded and unloaded measurements, using experimental and numerical methods. In the experimental research, a section of track was measured using both systems. The track longitudinal level measured using unloaded and loaded methods were compared, and the discrepancy reported. It was found that although the measuring distance can cause discrepancies, the unloaded measurement method still meets the measurement requirement. The largest discrepancies are in track transition zones, which is explained using the numerical method. After that, a case study using the unloaded measurement method is presented, wherein a section of track has been measured every month. The results show the advantages of frequent measurements in track inspections and the potential applications of unloaded track inspections.