No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Possibility analysis of the LiDAR technique utilization to research the wear of rails and turnouts in tram tracks
Abstract
The introduction of the article highlights the importance of measuring the wear of rails and turnouts. The evolution of methods and devices used to measure the profiles of these elements is briefly presented. The principle of conducting research using the LiDAR technique is explained. The problem of geometric and structural differences of tram tracks in relation to classic railways is pointed out, and the resulting concerns about the possibility of adapting typical railway methods of measuring rail and turnouts profiles to tram tracks. The rest of the article describes the construction, basic parameters and method of operation of a precise stationary laser scanner, dedicated to measuring rail profiles and turnouts. Graphical analysis of the results for measurements carried out with the mentioned device on tram tracks are presented – for rails in curves with small radii, turnouts (half-switches and frogs), corrugated wear, and broken welds. The summary presents conclusions from the research conducted.
ResearchGate has not been able to resolve any citations for this publication.
Under sleeper pads (USPs) are resilient elements used in the ballasted track structures to improve dynamic behaviour of the track, reduce vibration and protect the ballast against fast degradation.
As the elements permanently connected to the sleepers or turnout bearers, the pads must have an appropriate level of pull-off strength, so that they do not separate from the rail support (here: sleeper) during their transportation to the construction site or during many years of operation. In this paper, results of pull-off tests performed on four selected USP samples are presented: three samples made of SBR (styrene-butadiene rubber) granulate and one made of polyurethane. Moreover, details of the pad’s
attachment to the rail support are discussed, and the requirements for the USP properties are specified, focusing on the pull-off strength determined after the weather resistance test. It is shown that only two out of four considered USP samples fulfilled the requirements specified by the authors.
This study investigates the possibility of predicting, by means of artificial neural networks (ANNs), the values of static and dynamic bedding moduli of prototypical under sleeper pads (USPs) based on recycled SBR (styrene-butadiene rubber) granulate, in order to adapt their technical parameters (density and thickness) at the production stage to meet the requirements of the railway infrastructure manager or the specifics of a particular investment project. USPs are usually produced from elastomeric materials such as rubber or polyurethane. Here, the authors propose a sustainable approach, where the use of raw materials is reduced and a recycled rubber from end-of-life tires is reused. It is proved that the parameters of a vibration isolator, such as its thickness and density, can be designed using the proposed ANN-based models, which are aimed at the prediction of static and low frequency dynamic bedding moduli of the pad.
The inspection and maintenance of track ballast are fundamental tasks for the preservation of the condition of railway networks. This work presents an application based on a low-cost solid-state LiDAR system, which allows the user to accurately measure the ballast geometry from a mobile inspection trolley or draisine. The solid-state LiDAR system, the LiVOX Avia, was validated on a test track through comparison with a traditional static LiDAR system, the Faro Focus 3D. The results show a standard deviation of around 6 mm for the solid-state LiDAR system. The LiVOX system also provides the capability to measure the ballast digital elevation model and profiles. The LiVOX results are in agreement with those obtained from the Faro Focus. The results demonstrate that the LiVOX system can sufficiently measure even the displacement of a single layer of ballast stones typically between 2.5 cm and 5 cm. The data provided can be easily digitalized using image processing tools and integrated into geographic information systems for infrastructure management.
Railway tracks must be managed appropriately because their conditions significantly affect railway safety. Safety is ensured through inspections by track maintenance staff and maintenance based on measurements using dedicated track geometry cars. However, maintaining regional railway tracks using conventional methods is becoming difficult because of their poor financial condition and lack of manpower. Therefore, a track condition diagnostic system is developed, wherein onboard sensing devices are installed on in-service vehicles, and the vibration acceleration of the car body is measured to monitor the condition of the track. In this study, we conduct long-term measurements using the system and evaluate changes in the track conditions over time using car-body vibration data. Filed test results showed that sections with degraded tracks were identified using car-body vibration data. The track degradation trend can be constructed using the results obtained. Furthermore, this study demonstrated that the track maintenance effect could be confirmed. A method for improving train position using the yaw angular velocity is proposed. The track irregularity position can be shown more clearly by monitoring the track condition using position-corrected data using the proposed method. It is also shown that the time-frequency analysis of measured car-body vertical acceleration is effective for evaluating the track condition more clearly.
The development of an automated rail line defect classification system is of great benefit, as railway tracks must be periodically monitored and inspected to guarantee the safety of rail transportation. In this paper, an effective multi-scale residual convolutional network (MSRConvNet) model is proposed to classify the different types of railway track defects. The skip connections with residual learning blocks are used to increase the effectiveness of the network. The multi-scale convolutions are connected with parallel and two skip connections in the structure to distribute detailed feature maps with each other. Therefore, different scale feature maps can be extracted. The data augmentation method is performed to ensure a balanced class distribution and to eliminate the negative effect of the imbalanced dataset. The proposed model is compared with both benchmark deep learning models and the different variations of the designed network. The results verify that the proposed model can reach superior classification fulfillment, and the MSRConvNet provides an overall accuracy of 99.83%, precision of 99.83%, sensitivity of 99.83%, specificity of 99.94%, F1-score of 99.83%, and Matthew’s correlation coefficient of 99.78% for four defect classes.
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.
The good condition of railway rails is crucial to ensuring the safe operation of the railway network. At present, the rail flaw detectors are widely used in rail flaw detection, they are typically based on the principle of ultrasonic detection. However, the rail detection results analysis process involves huge manual work and the associated labor costs, with low levels of efficiency. In order to improve the efficiency, accuracy of results analysis and also reduce the labor costs, it is necessary to employ classification of ultrasonic flaw detection B-scan image, based on an artificial intelligence algorithm. Inspired by transformer models, with excellent performance in the field of natural language processing (NLP), some deep learning models differ from traditional convolutional neural networks (CNN), gradually emerge in the field of computer image processing. In order to explore the practicality of this model in the field of computer image processing (vision), in the paper, the Vision Transformer (ViT) is employed to train with rail defect B-scan images data and produce a rail defect classification. The model accuracy is more than 90% with the highest accuracy reaching 98.92%.
The use of rail transport is increasing. Damaged rails interrupt traffic to carry out repairs. In fact, when a conductor or railway operator reports a damaged rail that interrupted the traffic in the affected area. A team of specialized agents dispatch to the site and carries out the repairs. Hence, the importance of automation of railway track faults detection to ensure track safety and reduce maintenance costs. In this work, we propose a method using image processing technologies and deep learning networks. We have studied the correlation effects of MobileNetV2 and optimization algorithms on accuracy and other performance metrics to generate a model that can achieve good performance in classifying railway track faults. The results show that the Rmsprop can improve the effectiveness of feature extraction and classification of MobileNetV2.
Railways speedily transport many people and goods nationwide, so railway accidents can pose immense damage. However, the infrastructure of railways is so complex that its maintenance is challenging and expensive. Therefore, using artificial intelligence for railway safety has attracted many researchers. This paper examines artificial intelligence applications for railway safety, mainly focusing on deep learning approaches. This paper first introduces deep learning methods widely used for railway safety. Then, we investigated and classified earlier studies into four representative application areas: (1) railway infrastructure (catenary, surface, components, and geometry), (2) train body and bogie (door, wheel, suspension, bearing, etc.), (3) operation (railway detection, railroad trespassing, wind risk, train running safety, etc.), and (4) station (air quality control, accident prevention, etc.). We present fundamental problems and popular approaches for each application area. Finally, based on the literature reviews, we discuss the opportunities and challenges of artificial intelligence for railway safety.
Medical imaging is the process of visual representation of different tissues and organs of the human body to monitor the normal and abnormal anatomy and physiology of the body. There are many medical imaging techniques used for this purpose such as X-ray, computed tomography (CT), positron emission tomography (PET), magnetic resonance imaging (MRI), single-photon emission computed tomography (SPECT), digital mammography, and diagnostic sonography. These advanced medical imaging techniques have many applications in the diagnosis of myocardial diseases, cancer of different tissues, neurological disorders, congenital heart disease, abdominal illnesses, complex bone fractures, and other serious medical conditions. There are benefits as well as some risks to every imaging technique. There are some steps for minimizing the radiation exposure risks from imaging techniques. Advance medical imaging modalities such as PET/CT hybrid, three-dimensional ultrasound computed tomography (3D USCT), and simultaneous PET/MRI give high resolution, better reliability, and safety to diagnose, treat, and manage complex patient abnormalities. These techniques ensure the production of new accurate imaging tools with improving resolution, sensitivity, and specificity. In the future, with mounting innovations and advancements in technology systems, the medical diagnostic field will become a field of regular measurement of various complex diseases and will provide healthcare solutions.
Accurate rail location is a crucial part in the railway support driving system for safety monitoring. LiDAR can obtain point clouds that carry 3D information for the railway environment, especially in darkness and terrible weather conditions. In this paper, a real-time rail recognition method based on 3D point clouds is proposed to solve the challenges, such as disorderly, uneven density and large volume of the point clouds. A voxel down-sampling method is first presented for density balanced of railway point clouds, and pyramid partition is designed to divide the 3D scanning area into the voxels with different volumes. Then, a feature encoding module is developed to find the nearest neighbor points and to aggregate their local geometric features for the center point. Finally, a multi-scale neural network is proposed to generate the prediction results of each voxel and the rail location. The experiments are conducted under 9 sequences of 3D point cloud data for the railway. The results show that the method has good performance in detecting straight, curved and other complex topologies rails.
Nowadays it is widely accepted that Artificial Intelligence (AI) is significantly influencing a large number of domains, including railways. In this paper, we present a systematic literature review of the current state-of-the-art of AI in railway transport. In particular, we analysed and discussed papers from a holistic railway perspective, covering sub-domains such as maintenance and inspection, planning and management, safety and security, autonomous driving and control, revenue management, transport policy, and passenger mobility. This review makes an initial step towards shaping the role of AI in future railways and provides a summary of the current focuses of AI research connected to rail transport. We reviewed about 139 scientific papers covering the period from 2010 to December 2020. We found that the major research efforts have been put in AI for rail maintenance and inspection, while very limited or no research has been found on AI for rail transport policy and revenue management. The remaining sub-domains received mild to moderate attention. AI applications are promising and tend to act as a game-changer in tackling multiple railway challenges. However, at the moment, AI research in railways is still mostly at its early stages. Future research can be expected towards developing advanced combined AI applications (e.g. with optimisation), using AI in decision making, dealing with uncertainty and tackling newly rising cybersecurity challenges.
Full text available at:
https://eprints.whiterose.ac.uk/185584/
Rail track is a critical component of rail systems. Accidents or interruptions caused by rail track anomalies usually possess severe outcomes. Therefore, rail track condition monitoring is an important task. Over the past decade, deep learning techniques have been rapidly developed and deployed. In the paper, we review the existing literature on applying deep learning to rail track condition monitoring. Potential challenges and opportunities are discussed for the research community to decide on possible directions. Two application cases are presented to illustrate the implementation of deep learning to rail track condition monitoring in practice before we conclude the paper.
In this paper, we present a global navigation satellite system (GNSS) aided LiDAR-visual-inertial scheme, RailLoMer-V, for accurate and robust rail vehicle localization and mapping. RailLoMer-V is formulated atop a factor graph and consists of two subsystems: an odometer assisted LiDAR-inertial system (OLIS) and an odometer integrated Visual-inertial system (OVIS). Both the subsystem exploits the typical geometry structure on the railroads. The plane constraints from extracted rail tracks are used to complement the rotation and vertical errors in OLIS. Besides, the line features and vanishing points are leveraged to constrain rotation drifts in OVIS. The proposed framework is extensively evaluated on datasets over 800 km, gathered for more than a year on both general-speed and high-speed railways, day and night. Taking advantage of the tightly-coupled integration of all measurements from individual sensors, our framework is accurate to long-during tasks and robust enough to grievously degenerated scenarios (railway tunnels). In addition, the real-time performance can be achieved with an onboard computer.
Complex diagnostics of railway lines involves techniques based on discrete and continual data acquisition. While discrete measurements belong to conventional methods, the modern continual ones use automated robotized instruments with continuous recording. Observations have become more time-efficient, but the processing epoch has become longer to evaluate a large number of data. Railway line diagnostics is realized by relative methods lead to determine relative track parameters as the track gauge, elevation, and track gradients and absolute, geodetic techniques determine directional and height ratios of the track, defined in a global coordinate and height system.
The present paper focuses on the analysis of resistance of several prototypical under sleeper pads (USP) to severe environmental conditions. Taking into account the climate in Poland, evaluation of USP in regard to water and frost resistance should be performed and the influence of high temperatures should be analyzed. In the present paper results of several tests carried out on the selected USP are presented. The tests were performed in accordance with the rules given in PN-EN 16730. Concrete blocks with USP were immersed in water at room temperature for 24 h and then placed in a climatic chamber for resistance testing. The results show that the severe environmental conditions influence the damping-related parameters of USP, which affects the effectiveness of the vibration isolation. The performed analyses allowed the authors to indicate the most resistant pads that will undergo further testing. Additionally, requirements of several railway infrastructure managers as well as authors' recommendations concerning the properties of USP were given.
In the last few years, many works have addressed Predictive Maintenance (PdM) by the use of Machine Learning (ML) and Deep Learning (DL) solutions, especially the latter. The monitoring and logging of industrial equipment events, like temporal behavior and fault events—anomaly detection in time-series—can be obtained from records generated by sensors installed in different parts of an industrial plant. However, such progress is incipient because we still have many challenges, and the performance of applications depends on the appropriate choice of the method. This article presents a survey of existing ML and DL techniques for handling PdM in the railway industry. This survey discusses the main approaches for this specific application within a taxonomy defined by the type of task, employed methods, metrics of evaluation, the specific equipment or process, and datasets. Lastly, we conclude and outline some suggestions for future research.
As a result of long-term pressure from train operations and direct exposure to the natural environment, rails, fasteners, and other components of railway track lines inevitably produce defects, which have a direct impact on the safety of train operations. In this study, a multiobject detection method based on deep convolutional neural network that can achieve nondestructive detection of rail surface and fastener defects is proposed. First, rails and fasteners on the railway track image are localized by the improved YOLOv5 framework. Then, the defect detection model based on Mask R-CNN is utilized to detect the surface defects of the rail and segment the defect area. Finally, the model based on ResNet framework is used to classify the state of the fasteners. To verify the robustness and effectiveness of our proposed method, we conduct experimental tests using the ballast and ballastless railway track images collected from Shijiazhuang-Taiyuan high-speed railway line. Through a variety of evaluation indexes to compare with other methods using deep learning algorithms, experimental results show that our method outperforms others in all stages and enables effective detection of rail surface and fasteners.
Various techniques have been developed to detect railway defects. One of the popular techniques is machine learning. This unprecedented study applies deep learning, which is a branch of machine learning techniques, to detect and evaluate the severity of rail combined defects. The combined defects in the study are settlement and dipped joint. Features used to detect and evaluate the severity of combined defects are axle box accelerations simulated using a verified rolling stock dynamic behavior simulation called D-Track. A total of 1650 simulations are run to generate numerical data. Deep learning techniques used in the study are deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN). Simulated data are used in two ways: simplified data and raw data. Simplified data are used to develop the DNN model, while raw data are used to develop the CNN and RNN model. For simplified data, features are extracted from raw data, which are the weight of rolling stock, the speed of rolling stock, and three peak and bottom accelerations from two wheels of rolling stock. In total, there are 14 features used as simplified data for developing the DNN model. For raw data, time-domain accelerations are used directly to develop the CNN and RNN models without processing and data extraction. Hyperparameter tuning is performed to ensure that the performance of each model is optimized. Grid search is used for performing hyperparameter tuning. To detect the combined defects, the study proposes two approaches. The first approach uses one model to detect settlement and dipped joint, and the second approach uses two models to detect settlement and dipped joint separately. The results show that the CNN models of both approaches provide the same accuracy of 99%, so one model is good enough to detect settlement and dipped joint. To evaluate the severity of the combined defects, the study applies classification and regression concepts. Classification is used to evaluate the severity by categorizing defects into light, medium, and severe classes, and regression is used to estimate the size of defects. From the study, the CNN model is suitable for evaluating dipped joint severity with an accuracy of 84% and mean absolute error (MAE) of 1.25 mm, and the RNN model is suitable for evaluating settlement severity with an accuracy of 99% and mean absolute error (MAE) of 1.58 mm.
Determining the requirement and location and deciding on the time and sources of repair action is a difficult process, influenced by requirements on cost minimization and operational constraints. The particular sections of the railway track react differently to traffic and non-traffic loads, which implies the need to determine the format of development of structural quality indicators and decision-making is based on a large amount of technical and economic information, the interconnection of which is determined by the infrastructure manager. The decision-making process on repair work in the railway infrastructure management system is therefore based on the analysis of diagnostic data, technical, technological, environmental, and economic information, or the personal professional experience of the staff of the infrastructure manager. Understanding the causes of the structure’s behaviour in this process leads to the identification of its weaknesses and the ability to predict its behaviour, which allows for timely planning and accurate targeting of adequate repair work to minimize the occurrence of structural faults.
Smart railway maintenance is crucial to the safety and efficiency of railway operations. Successful deployment of technologies such as condition-based monitoring and predictive maintenance will enable railway companies to conduct proactive maintenance before defects and failures take place to improve operation safety and efficiency. In this paper, we first propose to develop a classification-based method to detect rail defects such as localized surface collapse, rail end batter, or rail components—such as joints, turning points, crossings, etc.—by using acceleration data. In order to improve the performance of the classification-based models and enhance their applicability in practice, we further propose a deep learning-based approach for the detection of rail joints or defects by deploying convolutional neural networks (CNN). CNN-based models can work directly with raw data to reduce the heavy preprocessing of feature engineering and directly detect joints located on either the left or the right rail. Two convolutional networks, ResNet and fully convolutional networks (FCN), are investigated and evaluated with the collected acceleration data. The experimental results show both deep neural networks obtain good performance, which demonstrate that the deep learning-based methods are effective for detecting rail joints or defects with the expected performance.
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.
Recently, with the emergence of Industry 4.0 (I4.0), smart systems, machine learning (ML) within artificial intelligence (AI), predictive maintenance (PdM) approaches have been extensively applied in industries for handling the health status of industrial equipment. Due to digital transformation towards I4.0, information techniques, computerized control, and communication networks, it is possible to collect massive amounts of operational and processes conditions data generated form several pieces of equipment and harvest data for making an automated fault detection and diagnosis with the aim to minimize downtime and increase utilization rate of the components and increase their remaining useful lives. PdM is inevitable for sustainable smart manufacturing in I4.0. Machine learning (ML) techniques have emerged as a promising tool in PdM applications for smart manufacturing in I4.0, thus it has increased attraction of authors during recent years. This paper aims to provide a comprehensive review of the recent advancements of ML techniques widely applied to PdM for smart manufacturing in I4.0 by classifying the research according to the ML algorithms, ML category, machinery, and equipment used, device used in data acquisition, classification of data, size and type, and highlight the key contributions of the researchers, and thus offers guidelines and foundation for further research.
A cab-based track monitoring system has been developed which makes use of the existing on-board GSM-R cab radio present in the majority of trains operating in the UK. With the addition of a low-cost sensor, type, location and severity of the track defects are reported using the system. The system improves safety and network performance by efficiently directing maintenance crews to the location of defects, minimising time spent on maintenance and inspection. Initially, vehicle dynamic simulation was used to test the feasibility of the system for defect monitoring and to develop compensation factors for vehicle type and operating speed. Novel on-board signal processing techniques are also presented through comparison of vibration response from sites with known defects and outputs from Network Rail’s (NR) New Measurement Train (NMT). Good agreement was reported for track faults in relation to vertical and lateral alignment and dip faults. Statistically, good agreement has been demonstrated, suggesting that the data acquired could be used to provide an indication of track quality thereby improving network performance, reducing rough ride and leading to improved passenger comfort. Improvements in the measured and statistical correlation are anticipated through the use, of multi-train / multi-journey and machine learning methods..
A coordinate-based 3D model of a railroad rail is essential for the maintenance of railway services. However, automated processing to reconstruct objects from light detection and ranging (LiDAR) data in areas where such facilities are installed in a complex manner is still a
challenge. In this study, our objective is to develop a method for the automated reconstruction of rails from LiDAR data in a complex area. Unlike the running sections of a train where one or two rails are present, many rails are installed by joining or branching in a railway
station. Three factors, namely, height difference, spatial relationship with other objects, and point density difference, were considered in detecting the rails in this complicated area. For tracking and modeling rails, an iterative random sample consensus (RANSAC) and singular
value decomposition (SVD) algorithms were used. The results showed that about 90% of the rail tracks were extracted, and the precision rate was about 99%. All processes were fully automated, and the method proposed in this study was developed to be applicable to various
line-type facilities as well as rails.
The railway structures need constant monitoring and maintenance to ensure the train circulation safety. Quality information concerning the infrastructure geometry, namely the three-dimensional linear elements, are crucial for that processes. Along with this work, a method to automated extract three-dimensional linear elements from point clouds collected by terrestrial mobile LiDAR systems along railways is presented. The proposed method takes advantage of the stored cloud point’s attributes as an alternative to complex geometric methods applied over the point’s cloud coordinates. Based on the assumption that the linear elements to extract are roughly parallel to the rail tracks and therefore to the system trajectory, the stored scan angle value was used to restrict the number of cloud points that represents the linear elements. A simple algorithm is then applied to that restricted number of points to get the three-dimensional polylines geometry. The obtained values of completeness, correctness and quality, validate the use of the methodology for linear elements extraction from mobile LiDAR data gathered along railway environments.
The paper presents results of the laboratory tests made for the prototype resilient under sleeper pads in the Warsaw University of Technology laboratory unit. These pads are dedicated to reduce vibrations transmitted to the vicinity of the railroad and to improve the resistance of the railroad structure. The laboratory testing program was carried out for elastomeric materials (polyurethane and rubber based) due to the PN-EN 16730 standard. The obtained values of the key parameters were used in order to determine the insertion loss vibration level by applying analytical method. The paper presents the influence of selected parameters i.e. static and dynamic moduli on the reduction of vibration and structure-borne sound level.
Railway transportation demands more efficient and accurate rail wear inspection systems to ensure the train operation safety. To obtain continuous three-dimensional data, a structured light rail wear inspection system is developed in this article, and the data processing method for aligning the point cloud from structured light scanning to the nominal computer-aided design model of the rail is investigated. For further data registration, the point cloud of the computer-aided design model is generated and the normal vectors of these points are calculated. In the coarse registration, conformal geometric algebra is applied to align the segmented point clouds by intuitive geometric calculations to those from the computer-aided design model. In the fine registration, the accurate alignment of the point clouds is implemented by the iterative closest point algorithm. The vertical and lateral wear amounts are obtained on the cross section by slicing the aligned three-dimensional point clouds data. Finally, the proposed system and method are validated by comparing the vertical wear amounts with the two-dimensional laser scanning and contact measurement results.
Railroads companies conduct regular inspections of their tracks to maintain and update the geographic data for railway management. Traditional railroad inspection methods, such as onsite inspections and semi-automated analysis of imagery and video data, are time consuming and ineffective. This study presents an automated effective method to detect tracks on the basis of their physical shape, geometrical properties, and reflection intensity feature. This study aims to investigate the feasibility of fast extraction of railroad using onboard Velodyne puck data collected by mobile laser scanning (MLS) system. Results show that the proposed method can be executed rapidly on an i5 computer with at least 10 Hz. The MLS system used in this study comprises a Velodyne puck/onboard GNSS receiver/inertial measurement unit. The range accuracy of Velodyne puck equipment is 2 cm, which fulfills the need of precise mapping. Notably, positioning STD is lower than 4 cm in most areas. Experiments are also undertaken to evaluate the timing of the proposed method. Experimental results indicate that the proposed method can extract 3D tracks in real-time and correctly recognize pairs of tracks. Accuracy, precision, and sensitivity of total test area are 99.68%, 97.55%, and 66.55%, respectively. Results suggest that in a multi-track area, close collaboration between MLS platforms mounted on several trains is required.
Track detection and gauge measurement are considered as crucial aspects of railway inspection systems. Traditionally, monitoring by human inspectors was done. Nowadays, computer vision-based systems are used due to their flexibility and ease of use. In recent years, various prototypes of vision based inspection system have been proposed, most have a camera mounted on carts or trains. Employing drones for such monitoring systems provides a cost effective and accurate means for monitoring tracks. This paper explores the possibilities of computer vision based monitoring through drone imagery. The experimental results ensure that the proposed method provides high reliability and accuracy.
The Mobile LiDAR Mapping System StreetMapper from IGI and 3D Laser Mapping (Bingham Nottingham, UK) is mounted on a large variety of road vehicles to cover different mission specifications. In addition to the operation on the road, the system finds its applications on other kinds of vehicles, like boats or trains. The modular and flexible system concept even allows utilizing the same LiDAR Mapping system for Mobile Mapping on the ground and for airborne missions on helicopters, respectively.
Besides this general flexibility, each application has its own special requirements. Special hardware and software components are needed to complete the core components, like the laser scanner and the GNSS/IMU systems, to build a dedicated system for the chosen task.
Compared to the typical dynamics of a road vehicle mounted Mobile Mapping system, a dedicated rail mapping system operates under conditions that are much more challenging for a high accuracy GNSS/IMU trajectory determination. Furthermore, the typical rail mapping tasks, like the exact measurement of the rail track geometry, require the operation of the most accurate laser scanners and of specialized post-processing software.
In this paper, the RailMapper, a specialized Mobile Mapping system for railway surveys is presented. The system is described with focus on the railway specific requirements and results of practical surveys are given.
Railroad tracks need to be periodically inspected and monitored to ensure safe transportation. Automated track inspection using computer vision and pattern recognition methods have recently shown the potential to improve safety by allowing for more frequent inspections while reducing human errors. Achieving full automation is still very challenging due to the number of different possible failure modes as well as the broad range of image variations that can potentially trigger false alarms. Also, the number of defective components is very small, so not many training examples are available for the machine to learn a robust anomaly detector. In this paper, we show that detection performance can be improved by combining multiple detectors within a multi-task learning framework. We show that this approach results in better accuracy in detecting defects on railway ties and fasteners.
Predicting track degradation is extremely important due to its beneficial effects on increasing track safety and scheduling preventive maintenance. Logistic regression and Gradient Boosting Machine (GBM) were employed in this paper for predicting Yellow-tag Defect in the Next Inspection (YDNI), which is an indicator of maintenance requirement in the track. The geometry data of this paper were collected from passenger tracks with a length of 155 miles from 2011 to 2020. In addition to geometry data, Ground Penetrating Radar (GPR) data were used as additional explanatory variables to improve the performance of models. As there are a limited number of YDNI observations, Synthetic Minority Oversampling Technique (SMOTE) is employed to resolve the issue of imbalance dataset. Results indicate that the GBM outperforms logistic regression and can successfully predict YDNI with a very high sensitivity of 0.94. Parametric analysis indicated the direct correlation between the Ballast Fouling Index (BFI) and the probability of defect occurrence. Finally, the model can be integrated into a decision-making framework which generates predictions based on a given probability threshold for classification. Thus, the railway companies can select a specific threshold according to their maintenance budget and desired level of track safety for scheduling preventive maintenance interventions.
Parkinson's Disease (PD) is a pervasive, chronic, progressively debilitating neurodegenerative disorder that commonly presents with a series of motor-related symptoms, including resting tremor, stiffness, bradykinesia, and issues with balance and reflexes leading to postural instability and an impaired gait. Since it's official classification, much has been studied regarding the clinical features, etiology, and neuropathophysiology of PD. An array of similar conditions, known as Parkinsonian syndromes, have also been identified. In addition to the clinical presentation of motor and non-motor related symptoms, histological analyses have revealed the presence of protein clusters and cellular changes in the brain that are indicative of PD. Since histology is necessarily performed post-mortem on the patients sectioned brain, it is not of use in diagnostic purposes. However, with the use of medical imaging technologies, particularly magnetic resonance imaging (MRI) and nuclear medicine imaging techniques, characteristic morphological and metabolic changes in the brain, which occur in the earlier stages of the disease, have been uncovered. Despite these technological advancements, PD is still typically diagnosed via clinical analysis. With the uncertainty associated with this technique, and the development of observable motor-related symptoms occurring after a significant amount of neurodegeneration, diagnosis of PD in its early stages is not possible. A review of the diagnostic imaging approaches to assessing PD could spread awareness of their efficacy and their potential for earlier diagnosis. Not only could this information inform public health policy in a similar manner to the recommendations for mammographic scans, the early diagnosis of PD is necessary for the implementation of any potential interventions.
The paper discusses the application areas of UAVs and their regulations. Particular attention is paid to the inspection and maintenance of railway infrastructure. The use of UAVs in many railway networks around the world is reviewed. The implementation of autonomous solutions is highlighted. The safety of UAVs on railways is analysed and directions for their implementation at PKP PLK S.A. are indicated. Keywords: UAVs, inspection, infrastructure, railway, security
Turnout systems on railways are crucial for safety protection and improvements in efficiency. The statistics show that the most common faults in railway system are turnout system faults. Therefore, many railway systems have adopted the microcomputer monitoring system (MMS) to monitor their health and performance in real time. However, in practice, existing turnout fault diagnosis methods depend largely on human experience. In this paper, we propose a data-driven fault diagnosis method that monitors data from point machines collected using MMS. First, based on a derivative method, data features are extracted by segmenting the original sample. Then, we apply two methods for feature reduction: principal component analysis (PCA) and linear discriminant analysis (LDA). The results show that LDA gave a better performance in the cases studied. A problem that cannot be overlooked is that the imbalanced quantity of rare fault samples and abundant normal samples will reduce the accuracy of classic fault diagnosis models. To deal with this problem of imbalanced data, we propose a modified support vector machine (SVM) method. Finally, an experiment using real data collected from the Guangzhou Railway Line is presented, which demonstrates that our method is reliable and feasible in fault diagnosis. It can further assist engineers to perform timely repairs and maintenance work in the future.
Track engineers face increasing cost pressure and budget restrictions in their work today. This leads to growing difficulty in legitimizing crucial maintenance and renewal measures. As a result, infrastructure managers must ensure they invest all available financial resources as sustainably and efficiently as possible. These boundary conditions require an objective tool enabling both a component-specific condition evaluation and preventive maintenance with renewal planning. The present research introduces such a tool for railway tracks based on innovative track data analyses. This tool includes time-series analyses for predicting future quality behavior. Consequently, the technical necessity of maintenance actions can be derived for every specific track section. In addition, these technical evaluations are combined with economic and operational considerations to plan reasonable maintenance lengths for different track components in the next few years. In a further step, business evaluations by means of annuity monitoring are executed to determine whether ongoing track maintenance or complete track renewal is the most economical solution. This methodology also allows calculating the economic damage caused by neglecting the ideal point in time for reinvestment. On the basis of this economic damage, it is possible to rank projects by priority in the case of insufficient budgets and to ensure that all available resources are invested in the most reasonable manner possible. Furthermore, such analyses clearly show that when a specific degradation level of railway track is reached track renewal is more economic in relation to life-cycle costs than ongoing maintenance.
Facility managers usually conduct reactive maintenance or preventive maintenance strategies in building maintenance management. However, there are some limitations that reactive maintenance cannot prevent failure, and preventive maintenance cannot predict the future condition of MEP components and repair in advance to extend the lifetime of facilities. Therefore, this study aims to apply a predictive maintenance strategy with advanced technologies to overcome these limitations. Building information modeling (BIM) and Internet of Things (IoT) have the potential to improve the efficiency of facility maintenance management (FMM). Despite the significant efforts that have been made to apply BIM and IoT to the architecture, engineering, construction, and facility management (AEC/FM) industry, BIM and IoT integration for FMM is still at an initial stage. In order to provide a better maintenance strategy for building facilities, a data-driven predictive maintenance planning framework based on BIM and IoT technologies for FMM was developed, consisting of an information layer and an application layer. Data collection and data integration among the BIM models, FM system, and IoT network are undertaken in the information layer, while the application layer contains four modules to achieve predictive maintenance, namely: (1) condition monitoring and fault alarming module, (2) condition assessment module, (3) condition prediction module, and (4) maintenance planning module. Machine learning algorithms, ANN and SVM, are used to predict the future condition of MEP components. Furthermore, the developed framework was applied in an illustrative example to validate the feasibility of the approach. The results show that the constantly updated data obtained from the information layer together with the machine learning algorithms in the application layer can efficiently predict the future condition of MEP components for maintenance planning.
This paper presents the concept of a simple system for the identification of the technical condition of tracks based on a trained learning system in the form of three independent neural networks. The studies conducted showed that basic measurements based on the root mean square of vibration acceleration allow for monitoring the track condition provided that the rail type has been included in the information system. Also, it is necessary to select data based on the threshold value of the vehicle velocity. In higher velocity ranges (above 40 km/h), it is possible to distinguish technical conditions with a permissible error of 5%. Such selection also enables to ignore the impact of rides through switches and crossings. Technical condition monitoring is also possible at lower ride velocities; however, this comes at the cost of reduced accuracy of the analysis.
In recent decades, 3D reconstruction techniques have been applied in an increasing number of areas such as virtual reality, robot navigation, medical imaging and architectural restoration of cultural relics. Most of the inspection techniques used in railway systems are, however, still implemented on a 2D basis. This is particularly true of track inspection due to its linear nature. Benefiting from the development of sensor technology and constantly improving processors, higher quality 3D model reconstructions are becoming possible which push the technology into more challenging areas. One such advancement is the use of 3D perceptual techniques in railway systems. This paper presents a novel 3D perceptual system, based on a low-cost 2D laser sensor, which has been developed for the detection and characterisation of physical surface defects in railway tracks. An innovative prototype system has been developed to capture and correlate the laser scan data; dedicated 3D data processing procedures have then been developed in the form of three specific defect-detection algorithms (depth gradient, face normal and face-normal gradient) which are applied to the 3D model. The system has been tested with rail samples in the laboratory and at the Long Marston Railway Test Track. The 3D models developed represent the external surface of the samples both laterally (2D slices) and longitudinally (3D model), and common surface defects can be detected and represented in 3D. The results demonstrate the feasibility of applying 3D reconstruction-based inspection techniques to railway systems.
This article investigates in which way a lidar sensor can be used in a train-borne localization system. The idea is to sense infrastructure elements like rails and turnouts with the lidar sensor and to recognize those objects with a template-matching approach. A requirement analysis for the lidar sensor is presented and a market review based on these requirements is performed. Furthermore, an approach for template matching on lidar scans to recognize infrastructure objects is introduced and its empirical performance is demonstrated based on measurements taken in a light rail environment. The overall goal of the integration of lidar sensors is to fill the sensory gap of existing train localization approaches, which are able to determine the exact, track-selective train position only if highly accurate position measurements from satellite navigation systems are available, which is often not the case. By integrating a lidar sensor, the localization system becomes more diverse, more robust, and can tolerate missing or faulty measurements from the satellite navigation system.
The goal of this paper is to share experience about the degradation assessment of railway track point machines. A real scale point machine test bench was used to perform several thousands of maneuvers. Recorded data consisted in the measurements of the shaft speed and the torque during a maneuver. Some faulty conditions were introduced to obtain degraded signals. Relevant indicators were computed to quantify the health state of the point machine and to detect faulty behaviours. The analysis also highlighted the in
uence of the temperature on the point machine performance. A degradation model is then built from the indicator to compute the reliability and the remaining useful life. The conclusions of this analysis will be
useful to properly de�ne an experimental design to be applied on a real turnout.
The railroad track substructure and specifically its ballast and sub-ballast layers play a key role in the maintenance of the stability and geometry of the track structure. However, because it traditionally has not been readily accessible below the surface of the ballast, very limited information about its conditions was available, without extensive and disruptive excavation techniques. New-generation inspection technology now allows for the access to significant additional information about the ballast and sub-ballast to include its extent, condition, depth, degree of fouling, and any inadequacies in the substructure layer that can lead to loss of track stability or accelerated degradation of the track structure. This paper discusses several of the key track substructure inspection technologies, to include the traditional monitoring of the track geometry and then addresses the new inspection technologies now available to more accurately define the ballast condition. This includes such newly introduced inspection technologies as LIDAR for measurement of the ballast profile, ground penetrating radar inspection for ballast depth deficiency, and other related inspection technologies. These new technologies allow for more accurate ballast deficit and condition analysis.