High-speed Line Research Articles

Classification and extraction method of hidden dangers along railway lines based on semantic segmentation network

ABSTRACT Foreign objects invading high-speed railway lines can cause danger. One existing solution is to use remote sensing images to analyse the dangerous areas along the railway line, thereby providing a certain amount of investigation time. Considering the spatial and temporal resolution characteristics of existing remote sensing technologies in identifying floating objects and the reality of rapid land use changes, this paper identifies areas on the ground where floating objects may be generated by using semantic segmentation techniques oriented to remotely sensed imagery and provides early warnings to staff along the route. However, these regions that need to be analysed have different semantics and scales. To address these challenges, this paper proposes a Dual-branch Parallel Fusion Network (DPFNet) based on Transformer, aimed at enhancing multi-class semantic segmentation in remote sensing images. To leverage global contextual information, we introduce a Swin Transformer-based backbone network, which employs self-attention to capture a comprehensive scene context, facilitating better segmentation by considering the entire scene’s context. For multi-scale semantic features, we propose one approach that involves independent branching feature expression and a Multi-scale Feature Space Fusion Module (MFSFM). The former enriches multi-scale information, while the latter fuses features across different levels to capture diverse semantic features. Experimental results demonstrate that DPFNet can effectively identify the hidden danger area, and the fusion of multi-scale features makes the network more accurately identify and segment the risk area of different sizes, improving the segmentation accuracy and robustness, and is of great significance to the formation of the ‘prevention’ as the core of the railway safety operation.

Estimation of ground vibration emission increase with respect to velocity in high-speed railways

During the design of a new line, it is often necessary to estimate railway vibration emissions at a given future speed from experimental data in similar circumstances, but at a different speed. Future levels are usually estimated according to a logarithmic evolution law with respect to speed, a typical one being that in USA FTA Report nº0123 "Transit Noise and Vibration Impact Assessment Manual", a de facto standard in the sector. Also, it is known that for high-speed lines a drastic increase in vibrations is observed when railway speed is higher than the propagation speed of surface Rayleigh waves. This phenomenon, known as trans-Rayleigh boom, produces a sharp discontinuity in the evolution of vibration emissions. However, vibration levels observed in the vicinity of a high-speed line have shown values well above the prediction rule suggested in FTA Manual, which could not be explained by a trans-Rayleigh boom. A more accurate extrapolation method based on local rail roughness measurements is capable of producing improved predictions compared to FTA rule of thumb. This contribution shows the details of the method suggested, and the improvement in the prediction (with respect to FTA extrapolation law) obtained in the specific case of a high-speed railway.

Results of a pilot study using experience sampling method to assess railway noise annoyance

This article aims to report on the development of a method to study the acoustic factors driving the short-term annoyance experienced by neighbors of high-speed train lines (> 250 km/h). In fact, current indicators (e.g., LDEN) only partially explain annoyance caused by high-speed trains noise. They could potentially be improved by considering some event-related aspects (e.g., the suddenness, spectral content, temporal fluctuations), whose role remains not fully understood. The development of a protocol dedicated to these issues is an essential prerequisite. A review of the different methods used to study transportation noise annoyance highlights the benefits of the experience sampling method (ESM), not yet used for railway noise assessment. This method allows participants to report their annoyance right after a train pass-by with a remote device while noise exposure is simultaneously recorded. We report on the results of a pilot study aiming to test an experimental protocol by proposing an adaptation of the experience sampling method to study annoyance caused by the passage of high-speed trains. Residents were recruited to take part in the study and received two protocols in two different periods. The most efficient ESM parameters were determined, and further possibilities offered by this new methodology are discussed.

Research and prediction of early-age loads in double-block ballastless track structure

Considering the hydration reaction of cement, a finite element model(FEM) of the coupling of temperature and humidity field and chemical field in the early age of the double-block ballastless track structure was established, and a field monitoring test on the early age of track slab was carried out with the newly constructed Fuzhou-Xiamen high-speed railway line as a case to verify the correctness of the FEM. Based on the official meteorological data from China Meteorological Administration (CMA) and the FEM, the dataset of vertical temperature and humidity gradients in the early age of the track slab was constructed, and five machine learning training models, namely, machine learning (MLR), multivariate polynomial regression (MPR), support vector regression (SVR), random forest (RF), and gradient boosted regression (GBR), were adopted to train the temperature gradient model and humidity gradient model for the early age of the track slab. The research results show that: (1) under the combined effect of solar radiation, convective heat transfer, radiative heat exchange and the cement hydration reaction, the temperature loading leads to the susceptibility of the sleepers to diagonal cracking; the humidity loading leads to transverse cracking in the center region of the surface of the track slab; (2) the finite element model with a higher accuracy provided the training dataset for the machine learning model. According to the Spearman correlation coefficient, the input features of the temperature gradient model and the humidity gradient model are determined, respectively; (3) Five ML methods were used to train the temperature gradient model and humidity gradient model, both of which demonstrated good generalization ability with a coefficient of determination(R2) greater than 0.85. Among these methods, GBR and SVR exhibited the best performance; From the perspective of MAPE value, the prediction effect of the temperature gradient training model was better than that of the humidity gradient training model; (4) The curing method and the average value of the relative humidity were the important input features influencing the training models for the temperature and humidity gradient loads, respectively. This finding provided an important guideline for the construction of ballastless track structures.

Last-train timetable synchronization for service compatibility maximization in urban rail transit networks with arrival uncertainties

The last train services of urban rail transit offer all passengers the final chance to reach their destinations. In the context of multimodal transport, considering the random delayed arrivals of late-night vehicles of other transport modes at urban hub stations and their adverse effects on multimodal passengers transferring to urban rail transit, a probabilistic scenario set is established to determine the arrival uncertainties of multimodal passengers. In each scenario, the timetable synchronization problem is formulated as a mixed-integer nonlinear programming model that requires a performance trade-off between destination reachability and the remaining path distance of both non-multimodal and multimodal passengers, integrally termed last train service compatibility. Through linearization techniques, the model is transformed into an equivalent mixed-integer linear programming form, which can be efficiently solved using the Gurobi solver to obtain the optimal last train timetable for each scenario and form an alternative scheme set. An improved probabilistic scenario set-based regret value theory is then developed, in which a novel regret value calculation method is proposed. The scheme with the minimum total weighted opportunity loss in all scenarios is selected as the optimal robust. Real case experiments based on the Chengdu–Chongqing high-speed railway line and Chengdu metro network are conducted to test the performance of our model. The results show that compared with the original timetable, the optimized timetable reduces the number of unreachable passengers by 34.29% and the sum of the average remaining path distance of non-multimodal and multimodal passengers by 57.43% with the help of path planning for all passengers. The proposed approach is proven not only to balance the demands of both reachable and unreachable passengers, but also to significantly improve the robustness of the last train timetable to arrival uncertainties of multimodal passengers and reduce their service inequity.

Effect of pier bearing construction on nearby high-speed rail line bridges

Effect of pier bearing construction on nearby high-speed rail line bridges

SCS-YOLO: A Defect Detection Model for Cigarette Appearance

Appearance defects significantly impact cigarette quality. However, in the current high-speed production lines, manual inspection and traditional methods are unable to satisfy the actual demands of inspection. Therefore, a real-time and high-precision defect detection model for cigarette appearance, SCS-YOLO, is presented. The model integrates space-to-depth convolution (SPD-Conv), a convolutional block attention module (CBAM), and a self-calibrated convolutional module (SCConv). SPD-Conv replaces the pooling structure to enhance the granularity of feature information. CBAM improves the ability to pay attention to defect locations. Improved self-calibrated convolution broadens the network’s receptive field and feature fusion capability. Additionally, Complete IoU loss (CIoU) is replaced with Efficient IoU Loss (EIoU) to enhance model localization and mitigate sample imbalance. The experimental results show that the accuracy of SCS-YOLO is 95.5% and the mAP (mean average precision) value is 95.2%. Compared with the original model, the accuracy and mAP value of the SCS-YOLO model are improved by 4.0%. Furthermore, the model achieves a detection speed of 216 FPS, meeting cigarette production lines’ accuracy and speed demands. Our research will positively impact the real-time detection of appearance defects in cigarette production lines.

Adaptive stepsize forward–backward pursuit and acoustic emission-based health state assessment of high-speed train bearings

Compressed sensing (CS) is a promising tool for data compression reconstruction. However, fault diagnosis methods for high-speed train bearings based on CS and acoustic emission (AE) technologies have not been reported yet. Notably, the accuracy and speed of CS two-stage reconstruction methods are affected and restricted by prior initial conditions. Therefore, this article proposes adaptive dynamic thresholds applicable to adaptive stepsize forward–backward pursuit (ASFBP), and bearing health state assessment method. First, the adaptive dynamic thresholds for atom selection and deletion are constructed based on the residual feedback mechanism and the atom quality distribution law, which enables ASFBP to realize high-precision rapid reconstruction of signal without any atom priori initial conditions. Second, the initial dictionary length is improved based on the AE hit characteristics. Furthermore, a damage state comprehensive evaluation index (DSCEI) is established using principal component analysis based on AE time-domain hit parameters and compression-domain energy parameter. Compared with the kurtosis index and permutation entropy index, the DSCEI demonstrates better monotonicity and stability in the quantitative evaluation of high-speed train bearing condition. Finally, the validity and stability of the method are verified by testing under complex test conditions resembling actual high-speed train lines, providing valuable insights for the CS-based data-driven bearing fault diagnosis.

An efficient dynamic reliability method for maglev vehicle-bridge systems and its application in random controller parameters analysis

This article presents an efficient method for analyzing the dynamic reliability of maglev vehicle-bridge coupled systems by combining a theoretical model with an adaptive surrogate model and the probability density evolution method (PDEM). First, a refined theoretical model of a maglev vehicle-bridge coupling system is established. Next, an adaptive surrogate model of the equivalent extreme value of the system dynamic response is established by combining an adaptive sampling method with radial basis functions. Finally, the adaptive surrogate model and PDEM are combined to further improve the efficiency of the dynamic reliability analysis. In the numerical example, the theoretical model of the maglev vehicle-guideway system was first validated by comparing with the measured data from the Shanghai high-speed maglev line. Then, by treating the controller parameters as normally distributed random variables, the accuracy and efficiency of the proposed reliability method were verified through comparison with the Monte Carlo method and the one-stage sampling surrogate model. Additionally, the impact of the randomness of each controller parameter and the coefficient of variation of the controller parameters on the system’s dynamic reliability was discussed.

Application of PS-InSAR and Diagnostic Train Measurement Techniques for Monitoring Subsidence in High-Speed Railway in Konya, Türkiye

Large-scale man-made linear structures like high-speed railway lines have become increasingly important in modern life as a faster and more comfortable transportation option. Subsidence or longitudinal levelling deformation problems along these railway lines can prevent the line from operating effectively and, in some cases, require speed reduction, continuous maintenance or repairs. In this study, the longitudinal levelling deformation of the high-speed railway line passing through Konya province (Central Turkey) was analyzed for the first time using the Persistent Scatter Synthetic Aperture Radar Interferometry (PS-InSAR) technique in conjunction with diagnostic train measurements, and the correlation values between them were found. In order to monitor potential levelling deformation along the railway line, medium-resolution, free-of-charge C-band Sentinel-1 (S-1) data and high-resolution, but paid, X-band Cosmo-SkyMed (CSK) Synthetic Aperture Radar (SAR) data were analyzed from the diagnostic train and reports received from the relevant maintenance department. Comparison analyses of the results obtained from the diagnostic train and radar measurements were carried out for three regions with different deformation scenarios, selected from a 30 km railway line within the whole analysis area. PS-InSAR measurements indicated subsidence events of up to 40 mm/year along the railway through the alluvial sediments of the Konya basin, which showed good agreement with the diagnostic train. This indicates that the levelling deformation of the railway and its surroundings can be monitored efficiently, rapidly and cost-effectively using the InSAR technique.

Integrated train timetable with supply–demand interactions at the Chinese high-speed railway

In traditional Chinese railway operations, train timetable and unit assignment are usually separated from pricing and seat allocation, resulting in a decrease in revenue and an increase in operating costs. In this paper, we study the integrated problem of train timetable, unit assignment, pricing, and seat allocation, where passenger choice behavior is modeled by the multinomial logit (MNL) model. This integration enables us to explicitly capture supply–demand interactions. The problem is formulated as a mixed integer nonlinear programming model with the objective of maximizing total profit. By converting the MNL model into its equivalent convex form, we recast the model as a tractable reformulation, allowing the use of a general-purpose solver to solve practical-sized instances. Based on real data from high-speed railway lines in China, three sets of case studies are conducted to validate the effectiveness and efficiency of the proposed approach.

Study on damage of CRTS II slab tracks in coated-uncoated transition zones subjected to temperature and train loads

The CRTS II ballastless track is sensitive to temperature due to its longitudinal continuity. The application of reflective insulation coating can efficiently lower the temperature of the track slab, thereby decelerating track deterioration. Given the considerable length of high-speed railway lines, the application of reflective insulation coatings leads to numerous transitions between coated and uncoated sections. This study investigates the influence of reflective insulation coatings on the structural damage of coated-uncoated transition zones in railways. To this end, a CRTS II slab track model involving the bilinear cohesive zone model and the concrete plastic damage model is established. The model examines the combined impact of high temperature and train loading, aiming to investigate the damage patterns within the coated-uncoated transition zone of the track. The results indicate: (1) During high temperature loading, the center of the track slab layer is predisposed to warping compared to the sides. (2) If the cohesion parameter falls below 0.04 MPa, augmenting the cohesion model parameter effectively alleviates track slab arching. (3) In instances where the track slab lacks complete coverage of reflective insulation coatings, train loading may shift the location of the maximum vertical displacement and interface failure mode.

Fatigue life assessment of thermite welded rails based on laboratory tests and field measurement data

This in-depth study assesses the fatigue life of thermite-welded 60E1 rails by combining fatigue experimental tests with field measurement data. Material characterization, conducted using X-ray Diffraction (XRD), X-ray Fluorescence (XRF), and Scanning Electron Microscopy (SEM), aimed to understand the fatigue behavior of these materials. The research was particularly focused on high-speed rail lines in South Korea, targeting areas with influence of track condition to collect strain data. By combining dynamic modulus calculations from high-speed tensile tests with the rain flow counting method for determining wheel loads, and employing the Linear Cumulative Damage method for estimating rail fatigue life, this study provides novel insights into the maintenance and durability of thermite welded rails. The integration of detailed laboratory experiments with field stress data offers a significant contribution to the predictive maintenance and lifecycle management of high-speed railway infrastructure.

Research on the Calculation Method and Influence Law of High-speed Railway Line Sound Source Propagation Attenuation Caused by Building Sheltering

Abstract In recent years, China’s rail transit system, particularly the high-speed railway network, has experienced rapid development. However, the issue of noise pollution along these railways has become increasingly severe. The accurate prediction of sound levels at specific points near buildings is challenging due to complex factors such as differences in line height, distance, and angle relative to the building. To address this challenge and improve predictions of sound propagation attenuation caused by building shelter from high-speed railway line sources, this study derives an integral expression for diffraction attenuation based on Curze and Meakawa’s point source acoustic diffraction theory. Numerical calculations are conducted to investigate the sound propagation attenuation patterns under different position relationships between buildings and railway lines. Field tests are also carried out along a high-speed railway in China. The findings are as follows: (1) The calculated results show a difference of less than 0.5 dB compared to measured values, indicating that they accurately reflect sound attenuation caused by building shelter. (2) The angle between the building and the railway as well as the distance between the sound point and the edge of the building significantly influence building shelter attenuation; with angle being most prominent among them within a frequency band of 500~2000 Hz resulting in an attenuation range of 0.6~15 dB variation should be considered when predicting noise levels at sensitive points or designing vibration and noise reduction measures accordingly. (3) Different distances between buildings and railway lines result in additional effects on attenuations.

Machine vision-based detection of forbidden elements in the high-speed automatic scrap sorting line

Highly efficient industrial sorting lines require fast and reliable classification methods. Various types of sensors are used to measure the features of an object to determine which output class it belongs to. One technique involves the use of an RGB camera and a machine learning classifier. The paper is focused on protecting the sorting process against prohibited and dangerous items potentially present in the sorted material that pose a threat to the sorting process or the subsequent metallurgical process. To achieve this, a convolutional neural network classifier was applied under real-life conditions to detect forbidden elements in copper-based metal scrap. A laboratory stand simulating the working conditions in a high-speed scrap sorting line was prepared. Using this custom stand, training and test sets for machine learning were gathered and labeled. An image preprocessing algorithm was designed to increase the robustness of the resulting forbidden element detector system. The performance of multiple neural network architectures and data set augmentations was analyzed. The highest accuracy of 98.03% and F1-score of 97.16% were achieved with a DenseNet-based classifier. The results of this paper show the feasibility of using the presented solution on a high-speed industrial line.

Prediction model for icing growth characteristics of high-speed railway contact lines

The sliding electrical contact is the only means by which high-speed trains obtain energy. When icing occurs on the contact lines, the impact vibrations of the pantograph-catenary system are further exacerbated, electrical arcing becomes more frequent, and abnormal wear is caused, seriously threatening the safety of the energy supply for high-speed railways. To address the unclear mechanisms, unpredictable patterns, and challenging characterization of contact lines icing, this paper proposes a dynamic simulation method for the first time. Furthermore, a surrogate model for predicting contact line icing is developed using deep learning algorithms. First, based on grid updating, flow field analysis, and icing calculations, key icing parameters are obtained to establish a numerical model of contact lines icing under time-varying meteorological parameters. Then, the effects of factors such as wind speed, temperature, and liquid water content on the dynamic evolution characteristics of contact line icing are analyzed. Finally, using the CNN-GRU algorithm, a prediction model for contact line icing is constructed to predict the icing mass and contours. This research clarifies the evolution patterns of contact lines icing, addresses challenges in monitoring and predicting icing states, and lays a theoretical foundation for high-speed railways' safe and stable operation under icing conditions.

Non-linear critical speed in high-speed ballasted railways with ground reinforcement

When constructing or upgrading high-speed railway lines on soft soils, reinforcing the soil foundation becomes crucial. This not only involves small track displacements but also increases the critical speed, thereby ensuring safe and efficient regular operations. Nevertheless, existing studies on the critical speed phenomenon in high-speed railway tracks with ground reinforcement are limited, and they all assume a linear elastic behavior for both the soils and reinforcement materials. The main novelty of this research is that it presents the first study on the effect of non-linear soil behavior on the critical speed of high-speed railway ballasted tracks with soil reinforcement and introduces a novel simplified approach based on an equivalent homogeneous soil layer by replacing the soil layer containing inclusions/columns. To accomplish this, a full 3D non-linear numerical model was developed and experimentally validated. The findings from a detailed and comprehensive parametric analysis demonstrate a significant influence of non-linear behavior on the critical speed, resulting in reductions of up to 30% compared to the linear elastic scenario. Furthermore, it is found that the soil-reinforcement stiffness contrast, the area replacement ratio, and the plasticity index of the soil foundation play a crucial role in the critical speed. Other aspects such as the installation pattern and the thickness of soft soil have a relatively lower impact on the critical speed.

Active faults along Indonesia’s first high-speed rail line

Abstract The cities of Jakarta and Bandung, two vital hubs in the western part of Java, are now connected by a high-speed rail line. However, potential earthquake hazards arise as the line intersects two active faults in West Java. To address this concern, we conducted a detailed geomorphological analysis using high-resolution DEM data (8-meter resolution) combine with 30-m resolution data to locate fault lines along the rail infrastructure. In the north, the line intersects the West Java back-arc thrust, while in the south, it crosses the junction of the Lembang Fault and Cimandiri Fault in Padalarang. However, young deposits and vegetation still could obscure fault traces in specific areas observed from high-resolution DEM data. To overcome this challenge, we employed UAV drone mapping to capture finer geomorphology details. This information then combined with paleoseismology trenching to uncover the active structural features. The aim is to enhance the railway’s resilience; and build monitoring and early warning systems for the high-speed train operation system to seismic events.

Dynamic amplification of rail tracks in high-speed lines: Exploring train effects and impact of ground treatment

When the train circulation speed is much lower than the critical speed of the track-ground system, problems with dynamic amplification effects are purely theoretical. However, the situation can change if a new high-speed line, with a higher operation speed, is planned for a site with soft soils. In such cases, it may be necessary to assess the importance and consequences of the critical speed phenomenon on safety and operational costs of the railway track. A practical measure involving the ground treatment may contribute to an improvement of the system behaviour. This measure is based on replacing a portion of the natural soil with stiffer materials or by employing grouting. The current paper provides numerical evidence as the soil reinforcement significantly improves the dynamic behaviour of the ground-track system. It is also possible to conclude that localized ground reinforcement below the track yields a response similar to extending the reinforcement over a larger area. This conclusion is particularly interesting for engineering practice and for numerical/semi-analytical analysis. The study of the effect of the train geometry on the critical speeds of the train-track system is also carried out. However, the main conclusion is that the definition of the critical speed as the value that induces larger amplification due to the passage of a single load is a conservative approach. Finally, it was observed that an approach based on the calculation of the dispersion curves enhances an adequate estimation of the system’s critical speed.

Robots for Interventions: Proof-of-Concept Method for High-Speed Filling Line Interventions Towards the Removal of Gloves

PurposeAlthough pharmaceutical high-speed filling lines are fully automated, interventions are still performed by hand via glove ports. Bringing robots into the high-speed production lines for the handling of interventions could increase both the thoughput and the sterility of the system. The work presented in this manuscript proposes a semi-autonomous intervention strategy for the removal of erroneous plungers.MethodsA YOLOv8-based computer vision algorithm continuously monitors the state of the plunger feed. Autonomous motion planning is used for large, general movements, while human-operated teleoperation with system guidance allows for small, precise motions. The combination of both creates a intuitive, gloveless intervention method.ResultsA user test with a group of 22 volunteers shows that an untrained operator can perform the teleoperated intervention via this system in an average of ±30\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm 30$$\\end{document}s and ±21\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\pm 21$$\\end{document}s when the plungers are static and dynamic respectively. Via a Likert-scale based questionnaire, it was found that the test group experienced the haptic system as very intuitive. Additionally, the system is capable of running completely remotely via a two-laptop setup, which has been tested at distances up to 100km.ConclusionAn intuitive, haptic semi-autonomous teleoperation system is created for the execution of a plunger removal intervention. Both in a static and dynamic scenario, an improvement of the operating time is observed compared to the current glove-based method (2 to 3 min). The system can run fully remotely and was found to be very intuitive by the user group.