Safety Of Railway Systems Research Articles

A comprehensive risk assessment of Chinese high-speed railways affected by multiple meteorological hazards

Meteorological hazards pose a significant risk to the operation and safety of the Chinese railway system. As China Railway High-speed (CRH) has become a vital part of the Chinese transportation infrastructure, an improved understanding of the spatial pattern of multiple hazards across the railway network is urgently needed, especially in the context of accelerated climate change. This study provides a spatial analysis of the dominant meteorological hazards affecting the CRH network (i.e., gales, rainfall, and snow), in terms of both intensity and frequency, and identifies hazard zones according to CRH operating standards. Given that meteorological hazards can lead to speed limitation or disruption of CRH trains, a risk matrix model is developed based on hazard intensity and designated railway speed to comprehensively assess the risk level of CRH lines in China. Risk assessment indicates that CRH lines exposed to hazardous levels of gales, rainfall, and snow account for 6.0%, 29.3%, and 20.0% of the total line length, respectively, while 7.3% of CRH lines are exposed to multiple hazards. Meteorological risk maps for CRH operation reveal hotspot lines that require special adaptive or preventative measures, and emergency protocols to reduce potential losses and disruptions.

Experimental investigation on microstructures and mechanical properties of PG4 flash-butt rail welds

Flash-butt welding (FBW) has recently been employed to construct continuously welded rails. However, the failure mechanisms of FBW joints remain unclear. In this study, the weldability of mobile flash-butt welded joints was investigated in terms of microstructures, mechanical properties, and residual stresses. The microhardness test results indicated that the heat-affected zone (HAZ) of the PG4 welds showed significant reductions in hardness of up to 140 HV, whereas the digital image correlation (DIC) measurements showed high heterogeneous strains of up to 4%. Crystallographic analysis indicated that the grains in the HAZ underwent plastic strain with a lattice reorientation of approximately 80% and 55% in the face- and body-centred cubic phase, respectively. The uniaxial tensile tests established the phenomenological relationship between the bond strength and HAZ width: specifically, the bond strength was relatively high at the foot and head of the rail, progressively decreased at the web, and was inversely correlated with the HAZ width. A fractographic analysis confirmed that the shrinkage cracks, inclusions, and flat spots in the rail web were the main cause of early failure in uniaxial tensile tests. Residual stress measurements also showed that FBW can introduce high residual stresses in the rail web of up to 436.76 ± 18.10 MPa and 225.80 ± 12.94 MPa in the vertical and longitudinal directions, respectively. The results of this study reveal that the bond strength of mobile FBW can be assessed based on their HAZ width and provide reliable guidelines for improving the safety and stability of railway systems.

An intelligent railway surveillance framework based on recognition of object and railway track using deep learning

In high speed railways, the intelligent railway safety system is necessary to avoid the accidents due to collision between trains and obstacles on the railway track. The unceasing research work is being performed to reinforce the railway safety and to diminish the accident rates. The rapid development in the field of deep learning has prompted new research opportunities in this area. In this paper, a novel and efficient approach is proposed to recognize the objects (obstacles) on the railway track ahead the train using deep classifier network. The 2-D Singular Spectrum Analysis (SSA) is utilized as decomposition tool that decomposes the image in useful components. That component is further applied to the deep classifier network. The obstacle recognition performance is enhanced by the combination of 2D-SSA and deep network. This method also presents a novel measure to identify the railway tracks. In addition, the performance of this approach is analyzed under different illumination conditions using OSU thermal pedestrian benchmark database. This system can be a tremendous support to curtail rail accidental rate and monetary loads. The results of proposed approach present good accuracy as well as can effectively recognize the objects (obstacles) on the railway track which helps to the railway safety. It also achieves a better performance with 85.2% accuracy, 84.5% precision and 88.6% recall.

An Optimized Deep Neural Network for Overhead Contact System Recognition from LiDAR Point Clouds

As vital infrastructures, high-speed railways support the development of transportation. To maintain the punctuality and safety of railway systems, researchers have employed manual and computer vision methods to monitor overhead contact systems (OCSs), but they have low efficiency. Investigators have also used light detection and ranging (LiDAR) to generate point clouds by emitting laser beams. The point cloud is segmented for automatic OCS recognition, which improves recognition efficiency. However, existing LiDAR point cloud segmentation methods have high computational/model complexity and latency. In addition, they cannot adapt to embedded devices with different architectures. To overcome these issues, this article presents a lightweight neural network EffNet consisting of three modules: ExtractA, AttenA, and AttenB. ExtractA extracts the features from the disordered and irregular point clouds of an OCS. AttenA keeps information flowing in EffNet while extracting useful features. AttenB uses channel and spatialwise statistics to enhance important features and suppress unimportant ones efficiently. To further speed up EffNet and match it with diverse architectures, we optimized it with a generation framework of tensor programs and deployed it on embedded systems with different architectures. Extensive experiments demonstrated that EffNet has at least a 0.57% higher mean accuracy, but with 25.00% and 9.30% lower computational and model complexity for OCS recognition than others, respectively. The optimized EffNet can be adapted to different architectures. Its latency decreased by 51.97%, 56.47%, 63.63%, 82.58%, 85.85%, and 91.97% on the NVIDIA Nano CPU, TX2 CPU, UP Board CPU, Nano GPU, TX2 GPU, and RTX 2,080 Ti GPU, respectively.

Identification of High-Risk Driving Behavior and Sections for Rail Systems

Risk assessment is an important process for railway safety. Current practices for assessing the risks of driving behaviors aim to inspect the driving record generated by automatic train protection systems. This paper proposes an automatic process to access detailed data contained in driving data, and identifies six high-risk driving behaviors. The modules can assess the competency of drivers and evaluate the frequency of high-risk behaviors in each section. Moreover, an integrated risk index for driving behaviors is proposed to compare each driver and section. An empirical study for drivers and sections is performed to demonstrate the feasibility of applying the proposed modules in practice. Results reveal that 20% of high-risk drivers contribute to 74% of the total risk, while 15% of high-risk sections contribute to 80% of the total risk. The proposed modules identify the drivers and sections with high risk. By enabling the operators of railway systems to take countermeasures, this methodology could enable them to improve the safety of railway systems more efficiently.

Development and Validation of a Railway Safety System for Nordic Trains in Isolated Territories of Northern Quebec Based on IEEE 802.15.4 Protocol.

Connected objects are deployed all over the world. Thus, they are contributing to improving communications. In urban areas, technological challenges are gradually being overcome, and advances in this area are exponential. Unfortunately, isolated territories such as northern Quebec do not beneficiate from this technological progress. Yet, northern Quebec relies on abundant natural resources, with notably its huge hydroelectric dams and iron mines, and therefore, the region’s economic life revolves essentially around the exploitation of these resources and is heavily reliant on rail transportation. However, according to Transport Canada, 1246 railroad accidents were reported in 2019 to the Transportation Safety Board (TSB). Thirty-eight people described as trespassers lost their lives, and five railroad employees were fatally injured. In this context, we present the implementation of a security system in an isolated environment for employees intervening on the railroad track to warn them of the imminent arrival of a train. Due to the context of the isolated environment, i.e., without an electrical network, without internet, and without an LTE network, a solution for employees has been developed using a Zigbee telecommunication system and a connected watch. A case study on a train operating in a remote and isolated area in northern Quebec is presented to validate the performance of the proposed system based on an open-source and customizable solution.

Effects of Dynamic Loading under Extreme Conditions on Wear Resistance of T105Mn120 Castings for Railway Safety Systems

Effects of Dynamic Loading under Extreme Conditions on Wear Resistance of T105Mn120 Castings for Railway Safety Systems

A hierarchical method based on improved deep forest and case-based reasoning for railway turnout fault diagnosis

Railway turnout system (RTS), which is widely laid along the railway tracks, is one of the most crucial devices in the whole railway infrastructures. Unpredictable outdoor weather, complex site conditions, and mechanical wear make the RTS the most vulnerable asset. Scientific and practical fault diagnosis is of great significance for reducing railway failures, improving operation efficiency, and ensuring transportation safety. In this paper, a hierarchical fault diagnosis method is proposed to realize accurate fault diagnosis of railway turnouts and improve the reliability and safety of railway systems. At the first level, an improved deep forest that embeds priori knowledge is adopted to distinguish the first-class fault sets. The embedded priori knowledge can help to outperform the traditional gcForest with fewer features produced at each level of the cascade forest. At the second level, a Case-based Reasoning component is utilized to classify the sub-class fault sets, which are difficult to be distinguished by the first level fault diagnosis due to their similar features. The hierarchical fault diagnosis method has been validated by using a real-world railway maintenance dataset. Extensive experiments show that the proposed method achieves superior performance compared to the state-of-the-art approaches in diagnostic precision under the constraint of limited data.

Sponge-Supported Triboelectric Nanogenerator for Energy Harvesting from Rail Vibration

Smart health monitoring based on a wireless sensor network plays a crucial role in maintaining the efficiency and safety of railway systems during operation, while the power source of the railway monitoring system remains a problem. Considering the mechanical energy produced by the rail vibration to be a sustainable and environment friendly power source, we propose a sponge-supported triboelectric nanogenerator (S-TENG) device as an energy harvester for the railway monitoring system. A high-density sponge is utilized under the tribo-pair as an innovative flexible buffer structure. The initial gap between the tribo-pair is properly designed according to the rail vibration amplitude to guarantee that the two dielectric materials can get into contact, while the rail with displacement beyond the initial gap will compress the sponge instead of squashing the tribo-pair, so as not to break the tribo-pair and to improve the output performance by enhancing the contact force between the tribo-pair. The feasibility of the sponge base is proved through a mechanical test, and a series of well-designed experimental tests are carried out to study the output performance of S-TENG with various loading conditions. To further investigate the applicability of S-TENG in railway monitoring, we establish a theoretical model for S-TENG output performance combined with a metro train-floating slab track model and simulate the output characteristics of S-TENG under train operation.

Wavelet Scattering and Neural Networks for Railhead Defect Identification.

Accurate and automatic railhead inspection is crucial for the operational safety of railway systems. Deep learning on visual images is effective in the automatic detection of railhead defects, but either intensive data requirements or ignoring defect sizes reduce its applicability. This paper developed a machine learning framework based on wavelet scattering networks (WSNs) and neural networks (NNs) for identifying railhead defects. WSNs are functionally equivalent to deep convolutional neural networks while containing no parameters, thus suitable for non-intensive datasets. NNs can restore location and size information. The publicly available rail surface discrete defects (RSDD) datasets were analyzed, including 67 Type-I railhead images acquired from express tracks and 128 Type-II images captured from ordinary/heavy haul tracks. The ultimate validation accuracy reached 99.80% and 99.44%, respectively. WSNs can extract implicit signal features, and the support vector machine classifier can improve the learning accuracy of NNs by over 6%. Three criteria, namely the precision, recall, and F-measure, were calculated for comparison with the literature. At the pixel level, the developed approach achieved three criteria of around 90%, outperforming former methods. At the defect level, the recall rates reached 100%, indicating all labeled defects were identified. The precision rates were around 75%, affected by the insignificant misidentified speckles (smaller than 20 pixels). Nonetheless, the developed learning framework was effective in identifying railhead defects.

Research on risk assessment of high-speed railway operation based on network ANP

Purpose The causes of high-speed railway failures are complex, and it is difficult to quantitatively and accurately describe safety evaluation. The purpose of this paper is to construct a model to ensure the safety of high-speed railway operations. Design/methodology/approach The authors construct a high-speed railway operation safety evaluation index system from four aspects: personnel, equipment, environment and management and analyze the inter-coupling relationship of various safety factors. Based on the evaluation index system, the use of network analytic hierarchy process (ANP) and fuzzy comprehensive evaluation will be used to establish a high-speed railway operation safety evaluation model. Findings Through the literature investigation and field investigation, combined with high-speed railway safety key points and system composition, 4 first-level indicators and 17 second-level indicators were selected to construct a high-speed railway operation safety evaluation index system. It can be seen from the results that the personnel management system and the signal and control system have the largest weight. Originality/value On the basis of establishing an evaluation index system, comprehensively considering the internal coupling relationship between evaluation indexes and the fuzziness of high-speed railway operation safety evaluation, high-speed railway uses ANP fuzzy network analysis method to construct high-speed railway operation, and the safety evaluation model has certain advantages and practicability in the case of the relative lack of high-speed railway operation data and fault data.

Characteristics and Mitigation Measures of Floor Heave in Operational High-Speed Railway Tunnels

The rapid development of high-speed railway tunnels has resulted in the increased application of ballastless track slabs. However, floor heave induces ballastless track slab deformation as a result of surrounding rock pressure, imposing serious challenges to the safety of railway systems. In this study, the characteristic of floor heave was analyzed based on field monitoring data. A new tunnel lining structure was then proposed to reduce the effect of floor heave on the slab track. The stress and deformation characteristics of the lining structure under different floor heave loads were analyzed through three-dimensional load structure numerical simulation, and the adaptability of the new tunnel lining structure was numerically studied. The results show that the floor heave typically occurred in the deep-buried sections of tunnel and the maximum floor heave was less than 50 mm during the operation of high-speed railway tunnels. When the new type of tunnel lining was adopted, the influence of the floor heave on the slab track was very small due to the reserved groove of the upper part of the invert and the high rigidity of the steel-reinforced concrete slab, thus effectively reducing the deformation of the tunnel floor heave. This research can be beneficial in the structural design of high-speed railway tunnels and the prevention of tunnel floor heave.

Impact of rail impedance intrinsic variability on railway system operation, EMC and safety

Running rails in electrified transportation systems are the interface element for several phenomena related to system performance, electromagnetic compatibility and safety: useful voltage at rolling stock, short circuit current, induced voltage, stray current, and track circuit operation. This work presents the physical and mathematical groundings of rail electrical parameters (dc and ac resistance, ac internal and external inductance) and experimental results available in the literature, discussing variability and reliability for each interface. The results consist thus of the identification of the relevant rails longitudinal electrical parameters, the presentation of a set of reliable experimental values, and the discussion of the best approach to manage their variability and uncertainty.

Possibilities of Railway Safety Improvement on Regional Lines

Level of railway safety is influenced by railway safety system, what is a complex of technical equipment and administrative arrangements. Current and previous accidents that happened show the necessity of solving these issues. The paper is focused on deep analysis, description and comparison of specific railway safety systems usage, which are suitable for regional railway lines. Content of the paper is applied on conditions in the Czech Republic. The main output of the paper is comparative evaluation of different railway safety systems on regional lines from safety and technology point of view.

A method of railway system safety analysis based on cusp catastrophe model

For rail transit systems, safety is one of the most important goals that need to be guaranteed. We build a method of railway system safety analysis based on the cusp catastrophe model. This method describes the continuous changing process of railway system safety and considers the emergent property of safety. This method solves the problem that the outputs of most static analysis methods of railway system safety do not have continuity and avoids the complex analysis process and heavy computation burden brought by using some dynamic models such as state transition models. The quantitative case study of the continuous changing process of system safety in the evolution process of the Yong-Wen railway accident shows that the visualized outputs obtained by using this method are consistent with the actual situation. This method has the potential to be applied in the real-time monitoring of railway system safety and the early warning of train accidents.

A novel method for simultaneous-fault diagnosis based on between-class learning

Condition monitoring and fault diagnosis are crucial to ensure the safety and efficiency of modern railway systems. The simultaneous fault may lead to catastrophic consequences and can be difficult to accurately detect when components are tightly coupled, which poses particular challenges to the automatic diagnosis. This paper proposes a novel method for simultaneous-fault diagnosis based on the combination of between-class learning and Bayesian deep learning. A modified between-class learning strategy with the multi-label approach is developed for model training. The detection results are obtained through an enhanced estimation method based on Bayesian deep learning, which can capture suspicious samples and identify simultaneous faults. The proposed method can distinguish simultaneous faults from regular faults and identify corresponding fault classes without using simultaneous-fault samples in the training phase. The experiments are conducted for the case of fault detection of high-speed trains, which demonstrates the accuracy and validity of the proposed method.

An Improved Faster R-CNN for UAV-Based Catenary Support Device Inspection

The catenary support device inspection is of crucial importance for ensuring safety and reliability of railway systems. At present, visual detection tasks of catenary support devices defect are performed by trained personnel based on the images taken periodically by industrial cameras installed on inspection vehicle in a limited period of time at midnight. However, the inspection mean is inappropriate for low efficiency and high cost. This paper presents a novel network based on unmanned aerial vehicle (UAV) images for catenary support device inspection and focuses on small object detection and the imbalanced dataset. With regards to the first aspect, based on a pyramid network structure, the improved Faster R-CNN consists of a top-down-top feature pyramid fusion structure, which heavily fuses high-level semantic information and low-level detail information. The feature map fusions of three different pooling scales are employed for improving detection accuracy of predicted bounding boxes. With regards to the second, we copy and paste the small proportion objects of dataset for avoiding category imbalance. Finally, quantitative and qualitative evaluations illustrate that the improved Faster-RCNN achieves better performance over the classic methods, yet remains convenient and efficient.

Development and validation of a new code for longitudinal train dynamics simulation

Longitudinal train dynamics have a significant impact on both safety and performance of railway systems. Numerical simulation of long heavy haul trains can thus provide essential information for the development of diagnostic and signaling systems as well as coupling elements and braking systems. Long trains are usually modeled by considering only the longitudinal degree of freedom and by adding extra resistant forces to represent the track curvature and gradients. The prediction of in-train forces represents the most critical aspect in modeling the longitudinal dynamics of long trains made up of several vehicles. In fact, coupling elements have non-linear force–deflection characteristics, with different behavior in loading and unloading states, thus featuring a hysteretic loop. Look-up tables storing data from experimental tests are generally used to model these elements; however, other strategies, such as fitting curves and white-box models are witnessed in the literature. Recently, an international benchmarking of longitudinal train dynamics simulator was established in order to compare the output results obtained by different models with the same input data. The research group from Politecnico di Torino performed the simulations using the multibody software Simpack, but computational inefficiencies and numerical divergences occurred. To overcome these issues, a new dedicated in-house code was developed in the MATLAB environment. The paper focuses on the description of this new code and its validation, which was carried out by performing the simulations according to the benchmark inputs and comparing the results with the outputs from the other participants.

Changes in maintenance of railway vehicles as the sources of threats in the railway system

Proper operation of railway vehicles is the basis for the functioning of a safe railway system. At the same time, it is not possible to talk about the safe use of a vehicle without adequately carried out maintenance processes. Due to legislative changes in August 2017, the maintenance system of railway vehicles has changed significantly. In most cases, it is the entities responsible for maintenance that are fully liable for the shape of the maintenance documentation, not the national security authority (in Poland the President of the Rail Transport Office) as has been the case so far. That is a big challenge for everyone involved in maintaining railway vehicles. The article presents the system of maintenance of railway vehicles as critical for the railway system safety, with the division into those registered in the National Railway Register and the unregistered ones. National and EU requirements for maintenance systems as well as the conditions for the implementation of “changes” in these systems have been presented, based, among others, on the results of the risk assessment of the threats they generate.

Supervision system for emergency brake and traction-system isolation on train formations

In the event of an emergency, railway safety systems typically work by isolating the traction-system and applying the emergency brake, causing logistic problems on the railway line where the train formation remains stopped. This paper presents the design of a supervision system that enables the train formation to be moved in a limited and controlled way to a repair workshop or to a safe place for dropping off passengers (in the case of passenger trains). This supervision system is considered critical, because it operates on the emergency brake and the traction-system. Thus, recommendations of the UNE-EN 50126 standard were followed during its design. In particular, hardware design techniques commonly used in other industries like automotive, aeronautics and aerospace, have been adopted.