Railway Infrastructure Maintenance Research Articles

Integration of BIM Tools for the Facility Management of Railway Bridges

Current railway infrastructure maintenance work, which is mostly carried out by visual inspection, has a reactive approach, dissociated information, and limited follow-up. On the other hand, railway bridges, being critical infrastructures, require effective monitoring and maintenance to guarantee their safety and operation over time. The designed tool links a parametric BIM model in Revit® with an automated spreadsheet in MS Excel® through visual programming in Dynamo, generating BIM/data automation as an initial step towards a digital twin. This achieves a bidirectional flow to exchange data on the structural condition of elements. The procedure was applied to a railway bridge in use for over 100 years, representing its geometry and damage information according to technical standards. The value lies in laying the foundations for adopting preventive approaches for this key infrastructure. The BIM/data automation allows the BIM model to visually reflect the condition of the elements, depending on their damage, consolidate the inspection information, and generate a visual management tool. In conclusion, the designed BIM/data automation improves the monitoring of railway bridges compared to traditional methods, facilitating the interaction and relationship between the damage records and the actual bridge elements, laying the foundations for the construction of digital twins.

Thermal imaging analysis of ballast fouling: Investigating the effects of parent rock and fouling materials through IRT passive camera

This study explores the use of infrared thermography (IRT) technology for the non-destructive evaluation of ballast fouling in railway tracks, focusing on the influence of parent rock types and fouling materials. Utilizing thermal imaging, the research investigates how variations in ballast conditions affect surface temperature, which serves as an indicator of structural integrity and health. The experimental setup involved ballast samples derived from three different rock types—basalt, limestone, and andesite—fouled with commonly encountered materials like sand and clay at varying percentages. Results demonstrate that fouling level and type significantly influence the thermal signatures captured by IRT passive camera. Notably, ballast derived from darker rocks exhibited higher temperatures, indicating greater emissivity, while fouled ballast showed distinct temperature patterns compared to clean samples, emphasizing the potential of thermal imaging in detecting and quantifying fouling in ballast layers. This research underscores the viability of IRT passive camera in the routine maintenance and monitoring of railway infrastructure, providing a foundation for further development of integrated diagnostic tools for railway management systems.

Railroad missing components detection via cascade region‐based convolutional neural network with predefined proposal templates

AbstractIn the field of railway infrastructure maintenance, timely and accurate detection of component anomalies is crucial for safety and efficiency. This paper presents the Cascade Region‐based convolutional neural network with Predefined Proposal Templates (CR‐PPT), an innovative method for railroad components inspection in complex railway infrastructure using edge‐computing devices. Unlike previous systems, CR‐PPT employs a series of predefined templates that enable it to detect both the presence and missing elements within various fastening systems. Our experimental analysis pinpoints the most effective network configurations for CR‐PPT. Furthermore, the paper examines CR‐PPT's proficiency in zero‐shot learning and fine‐tuning, highlighting its adaptability to new fastening systems. We have developed an optimized inference pipeline on NVIDIA Jetson AGX Orin, significantly enhancing its applicability for railway inspection practices. Field blind tests validate the model's high precision and efficiency, greatly reducing the time and labor required for inspections. The findings highlight CR‐PPT's potential as an efficient and robust tool for track health assessment, marking a notable progression in the integration of AI and computer vision in rail track inspection.

Railway Track Fault Detection and Automation System

The Railway Track Fault Detection and Automation System (RTFDAS) represents a significant leap forward in the realm of railway infrastructure maintenance and management. Traditional methods of track inspection often suffer from limitations such as manual labor, periodic assessments, and the potential for human error, leading to safety hazards and operational disruptions. In response, the RTFDAS leverages cutting-edge technology, sophisticated algorithms, and automation capabilities to enable proactive fault detection and streamlined maintenance processes. This paper presents a comprehensive overview of the RTFDAS, highlighting its key components, functionalities, and benefits. The system comprises a network of sensors strategically deployed along railway tracks to capture data on various parameters. Through advanced data processing and analysis, fault detection algorithms identify anomalies indicative of track faults, such as cracks, misalignments, and wear, enabling prompt intervention and maintenance. Key Words: railway track, automation, fault detection

AI-based technology to prognose and diagnose complex crack characteristics of railway concrete sleepers

Railway concrete sleepers are key safety-critical components in ballasted railway tracks. Due to frequent high-intensity impact loadings from train-track interaction over irregularities together with hostile environmental conditions, complicated characteristics of various crack patterns can incur on railway concrete sleepers, which will decrease their durability and service life overtime. Early warning of those cracks can help railway engineers to plan and schedule for renewal and maintenance timely and effectively. This study thus explores the artificial intelligence application of YOLOv5OBB (YOLOv5 with Oriented Bounding Box output) in the identification and classification of cracks in railway sleepers into three distinct types: longitudinal, transverse, and inclined, based on their specific crack angles, which have not been investigated in the past. The identification of crack angles is the novelty of this study. Recognising the various types of cracks is critical, given their varying causes and degrees of severity. Current corrective maintenance methods pose considerable safety risks to workers and exhibit low efficiency, underscoring the need for a more autonomous and efficient solution. This study marks a significant stride towards revolutionising railway maintenance, evidenced by an impressive mAP (Mean Average Precision) of 0.72 for crack detection and a 92% accuracy rate for angle detection. These promising results substantiate our study's potential to pioneer advancements in railway infrastructure maintenance.

Data driven machine learning prognostics of buckling failure modes in ballasted railway track

This study explores the development and application of a machine learning (ML) approach to predict buckling failure modes in ballasted railway tracks. With the growing demand for safer and more reliable railway systems, the ability to foresee and mitigate track failures is of paramount importance. Our study focuses on harnessing advanced ML algorithms to analyse and interpret complex data sets, aiming to identify potential buckling failures before they occur. The methodology employed involves collecting extensive data from previous advanced numerical studies. Faced with the inadequacy of field data collection on track buckling and the limited availability of data related to track conditions, our study has relied on simulation data for insight and analysis. This data is then processed and analysed using sophisticated ML models, trained to recognise patterns and anomalies indicative of potential buckling failures. A novel aspect of our approach is the integration of environmental factors, acknowledging their significant influence on the likelihood of both snap-through and progressive buckling in railway tracks. We compare the effectiveness of various ML algorithms in accurately predicting these failure modes, evaluating their performance in simulated and real-world scenarios. The findings demonstrate the models' proficiency in identifying early signs of both snap-through and progressive buckling, leading to timely interventions. This capability not only improves railway safety but also aids in efficient maintenance scheduling and asset management. Additionally, a case study in Thailand's railway system demonstrates the model's effectiveness in predicting buckling failures under tropical environmental conditions. This paper contributes a novel perspective to the field of railway infrastructure maintenance. By providing a reliable method for predicting specific buckling failure modes, it paves the way for enhanced operational safety and efficiency in railway networks, particularly in the face of dynamic environmental conditions.

Deep learning techniques to detect rail indications from ultrasonic data for automated rail monitoring and maintenance

The increasing number of passengers and services using railways and the corresponding increase in rail use has caused the acceleration of rail wear and surface defects which makes rail defect identification an important issue for rail maintenance and monitoring to ensure safe and efficient operation. Traditional visual inspection methods for identifying rail defects are time-consuming, less accurate, and associated with human errors. Deep learning has been used to improve railway maintenance and monitoring tasks. This study aims to develop a structured model for detecting railway artifacts and defects by comparing different deep-learning models using ultrasonic image data. This research showed whether it is practical to identify rail indications using image classification and object detection techniques from ultrasonic data and which model performs better among the above-mentioned methods. The methodology includes data processing, labeling, and using different conventional neural networks to develop the model for both image classification and object detection. The results of CNNs for image classification, and YOLOv5 for object detection show 98%, and 99% accuracy respectively. These models can identify rail artifacts efficiently and accurately in real-life scenarios, which can improve automated railway infrastructure monitoring and maintenance.

Mobilizing railway track stability with nonionic cement asphalt mortar for floating sleeper mitigation – 2D/3D numerical investigation and full-scale testing verification

This study addresses the mitigation of the floating sleeper phenomenon in ballasted railway tracks through the implementation of Nonionic Cement Asphalt Mortar (CAM). Full-scale testing experiments evaluate track performance with and without CAM stabilization, revealing its efficacy in forming a robust membrane between ballast particles to reinforce the track-bed structure. Wheel load modeling, including static and dynamic, train movement modeling, roadbed pressure analysis, distribution of load, and track rigidity analysis. Life Cycle Cost Analysis (LCCA) establishes CAM's cost-effectiveness by significantly reducing settlement and ensuring long-term durability. Numerical simulations using ABAQUS demonstrate CAM's effectiveness in stabilizing deteriorated ballast. Furthermore, the simulations prove capable of detecting the floating sleeper phenomenon in the full-scale test bed, offering valuable insights into real-world applications. Both 2D and 3D modeling consistently show a more than 30% reduction in initial settlement and a 0.5 mm displacement in CAM-reinforced ballast compared to controls. Plastic displacement in new ballast is consistently 50% less in the initial 50,000 cycles, with ultimate plastic settlement reduced by 40%, indicating the robustness of CAM across different modeling dimensions. The dataset analysis identifies a floating sleeper issue, evidenced by pressure variations in deteriorated ballast. In the control and simulation sections, there is a pressure drop from 65 kPa to 28 kPa, while the reinforced section maintains stable pressures (50 kPa, 36.5 kPa, 10 kPa) with closely aligned predicted values. Despite pressure reduction in simulated zones, the dataset strongly supports concerns about the substantial pressure decrease due to the floating sleeper phenomenon. LCCA substantiates CAM's economic advantage, showcasing a 79.7% cost reduction over 60 years, endorsing CAM as a sustainable maintenance strategy. In conclusion, CAM stabilization effectively mitigates the floating sleeper effect, ensuring long-term track durability, and providing valuable contributions to sustainable railway infrastructure design and maintenance practices.

Lateral Track Buckling in Sweden: Insights from Operators and Infrastructure Managers

Rail transport is expected to become a key component in the development of a long-term sustainable transport system. The planning, construction, operation, and maintenance of railway infrastructure are crucial in this effort. Hence, it is essential to ascertain that the railway infrastructure withstands and is adapted to extreme weather conditions and climate change. This study focuses on evaluating climate adaptation measures for lateral track buckling in Sweden. Through a literature review and interview with an expert at Swedish Transport Administration, it is highlighted that the maintenance status of railway infrastructure plays a significant role in the occurrence of lateral track buckling. According to the expert, inadequate track maintenance is the primary cause of lateral track buckling rather than weather variables like air temperature. The interview also clarifies that the chain of events related to the handling of track buckling is mainly initiated by the observation of a discrete lateral irregularity by a train driver, whereupon the train dispatcher at the traffic management center stops traffic until the location in the track has been inspected by a track entrepreneur. During the inspection, up to half of the observed cases of track buckling turn out to be false.

Improving the technological process of dismantling rail and sleeper grids through the use of a removable catcher

The maintenance and development of railway infrastructure requires a significant amount of repair and construction work. The most labour-intensive and time-consuming type of repair is a major track repair. The development strategy of the track complex sets tasks for planning and organizing track repair work, taking into account the fulfilment of the requirements for highly efficient use of track machines, ensuring their production at the level of passport characteristics. The article discusses the problem of dismantling a rail and sleeper grid using a laying crane, namely the process of lowering the first link of the package onto the crane platform. In a curved section of track, the problem arises that the inverted rail does not reach the platform rollers. Equipping the platforms with additional removable catchers will eliminate the process of rocking the inverted link by track fitters.

The Downside of Upkeep: Analysing Railway Infrastructure Maintenance Impact on Train Operations in Sweden

Efficient and seamless railway operations depend on the systematic and well-coordinated maintenance of both rolling stock and infrastructure. However, track maintenance, or ‘trackwork’, can cause substantial delays if not properly aligned with train schedules. This study comprehensively investigates how trackwork influences train operations in Sweden. It involves an in-depth analysis of an extensive dataset comprising over 225,000 recorded instances of planned trackwork and approximately 32.5 million train passages throughout the year 2017. Multiple logistic and negative binomial regression models showed that train running time delay occurrence is higher in the sections with scheduled trackwork. Trains passing through trackwork are 1.43 times more likely to experience delays compared to trains that do not pass through scheduled trackwork. The likelihood of an opportunity for the train delay recovery passing the section with scheduled trackwork is reduced by 11%. Additionally, the frequency of train delay increase is 16% higher, and delayed recovery is 4% lower in relation to trackwork. With the number of trackwork set to increase over the coming years, these results bring attention to train scheduling and the performance of trackwork.

PLANIMETRIC RAIL POSITIONING USING UAV PHOTOGRAMMETRY: TOWARDS AUTOMATED AND SAFE RAILWAY INFRASTRUCTURE MONITORING

Abstract. The maintenance of railway infrastructure requires detailed inspection of track assets including the rails, sleepers, fasteners, and tie plates. Current methods using total stations and measurement trains are costly and the subsequent data processing is often manual. A potent alternative is the use of Unmanned Aerial Vehicles (UAV) to investigate track asset deviations. However, the potential degree of automation and the overall accuracy is still very much the subject of ongoing research. In this work, a potential pipeline is investigated for the planimetric inspection of rails using UAV photogrammetry. Specifically, state-of-the-art line detectors such as Holistically-Nested Edge Detection, DexiNed, Segment Anything Model, and Mobile Line Segment Detection are combined with logical filtering to assess the localisation and gauge of the rails. The experiments indicate that the accuracy and detection rate are promising. Overall, the proposed method is a promising step towards affordable and safe railway infrastructure inspection.

INTERACTION OF IRREGULARITIES IN THE STANDARD OF SURVEYING AND CARTOGRAPHIC DOCUMENTATION WITH RAIL TRANSPORT PROBLEMS: A CASE STUDY

Surveying (geodesy) and cartographic documentation, their types, and their flow (circulation) are the basis for the uniformity of the work carried out in the pre-design, design, and execution of construction works, ultimately having a representation in the operational (exploitation) and maintenance of railway infrastructure. The type and circulation of surveying and cartographic documentation constitute an important element for the transport sector. The aim of the present scientific research work was to define the state of irregularity of the standard of uniform surveying-cartographic documentation, their type, and their circulation (Ig-1) in interaction with rail transport problems. A case study method was used corresponding to a factual description, which aimed to analyze and evaluate the existing standard. This is important from a theoretical and, above all, a practical point of view. The results show an extensive space of irregularities occurring, violating legal regulations and professional ethics. At the same time, good practice solutions have been implemented to optimize the negative impact when interacting with rail transport problems. The authors’ position on the irregularities was forwarded to an infrastructure manager. The irregularities that occur significantly contribute to the limitations of surveying and cartographic documentation harmonization, and these have an impact on fully functional rail transport.

An autonomous rail-road amphibious robotic system for railway maintenance using sensor fusion and mobile manipulator

The current maintenance of railway infrastructure replies heavily on human involvement, requiring possession of the track section during maintenance, resulting in high costs and inefficient execution. This paper proposes an autonomous rail-road amphibious robotic system for railway inspection and maintenance tasks. By virtue of its road and rail-autonomous mobility, it is able to execute the complete maintenance execution flow in multiple phases. The system provides flexible track job location access, low-cost maintenance execution, and reduced track network possession. The payload mobile manipulator and sensor fusion enhance the system's capabilities for multiple types of inspection and repair. The design of a command and control system was guided by a rule-based expert system strategy to enable remote operation of the whole system. The developed demonstrator of a track wheel accompanied unmanned ground vehicle was integrated and demonstrated in both operational and realistic track environments with multiple testing activities of remote operation, navigation, accurate job detection, inspection, and repair, confirming effective job completion and logical human interaction. The proposed method produces an outstanding hardware-software integrated robotic inspection and repair system with a high level of technological readiness for autonomous railway maintenance and intelligent railway asset management.

Analysis Of Modern Railway Power Quality Conditions With Inspection Methods To Mitigate Operating System Failures Referring To Regulations And Standard References

Elevated stations or commonly called elevated stations have an electric power system with a main power supply of 20KiloVolt with a nominal voltage of 750volt and a station operating facility voltage of 380volt laying station. This research uses the inspection method by making observations by work instructions and instruction manuals for railway infrastructure maintenance studies. Some were identified as related to power quality issues with progression-appropriate inspections and appropriate instruction manuals. The main objective of this study is to prevent overvoltage interference problems by recommending risk mitigation through investigative and simulation analysis methods using Electric Transient and Analysis Program (ETAP) software that can help evaluate and estimate strategic steps by paying attention to regulations and standard references and detecting losses in operating pattern disturbances due to disruption of power quality conditions caused by overvoltage surges in the station traction substation system by investigation and simulation methods using Electric Transient and Analysis Program (ETAP) software. This overvoltage is carried out in the context of research on maintaining services to the public and preventing system failures by using risk mitigation and investigation and simulation methods using Electric Transient and Analysis Program (ETAP) software that pays attention to environmental, safety, technical, and economic aspects with regulations and standard references. This research is in the form of mitigation analysis and describes the losses that have an impact by looking at a power quality condition and the follow-up provided to prevent overvoltage and components of modern railway electric facilities.

Interactive reinforcement learning innovation to reduce carbon emissions in railway infrastructure maintenance

Carbon emission is one of the primary contributors to global warming. The global community is paying great attention to this negative impact. The goal of this study is to reduce the negative impact of railway maintenance by applying reinforcement learning (RL) by optimizing maintenance activities. Railway maintenance is a complex process that may not be efficient in terms of environmental aspect. This study is the world's first to use the potential of RL to reduce carbon emission from railway maintenance. The data used to create the RL model are gathered from the field data between 2016–019. The study section is 30 km long. Proximal Policy Optimization (PPO) is applied in the study to develop the RL model. The results demonstrate that using RL reduces carbon emission from railway maintenance by 48%, which generates a considerable amount of carbon emission reduction and reduces railway defects by 68%, which also improves maintenance efficiency significantly.

Indirect Assessment of Railway Infrastructure Anomalies Based on Passenger Comfort Criteria

Railways are among the most efficient and widely used mass transportation systems for mid-range distances. To enhance the attractiveness of this type of transport, it is necessary to improve the level of comfort, which is much influenced by the vibration derived from the train motion and wheel-track interaction; thus, railway track infrastructure conditions and maintenance are a major concern. Based on discomfort levels, a methodology capable of detecting railway track infrastructure failures is proposed. During regular passenger service, acceleration and GPS measurements were taken on Alfa Pendular and Intercity trains between Porto (Campanhã) and Lisbon (Oriente) stations. ISO 2631 methodology was used to calculate instantaneous floor discomfort levels. By matching the results for both trains, using GPS coordinates, 12 track section locations were found to require preventive maintenance actions. The methodology was validated by comparing these results with those obtained by the EM 120 track inspection vehicle, for which similar locations were found. The developed system is a complementary condition-based maintenance tool that presents the advantage of being low-cost while not disturbing regular train operations.

Совершенствование аналитического метода расчета наличной пропускной способности с применением имитационного моделирования

Purpose: To develop method for calculating actual capacity on railway line on the basis of the improvement of analytical formulas and the use of simulation tools. Correction of mathematical apparatus and calculation of simulation modeling coefficient. Methods: Analytical method, simulation and dynamic modeling, mathematical modeling, AnyLogic Software Package tools were applied. Research results: New calculation approach that allows to raise railway line throughput precision. In its turn, the new approach will allow to optimize operating costs for the maintenance and current repair of railway infrastructure and rolling stock. Practical significance: The results obtained can be used in the analytics, prediction and modeling of transportation processes in the dispatch centers of JSC "Russian Railways" transportation management.

Railway infrastructure maintenance efficiency improvement using deep reinforcement learning integrated with digital twin based on track geometry and component defects

Railway maintenance is a complex and complicated task in the railway industry due to the number of its components and relationships. Ineffective railway maintenance results in excess cost, defective railway structure and components, longer possession time, poorer safety, and lower passenger comfort. Of the three main maintenance approaches, predictive maintenance is the trendy one, and is proven that it provides the highest efficiency. However, the implementation of predictive maintenance for the railway industry cannot be done without an efficient tool. Normally, railway maintenance is corrective when some things fail or preventive when maintenance is routine. A novel approach using an integration between deep reinforcement learning and digital twin is proposed in this study to improve the efficiency of railway maintenance which other techniques such as supervised and unsupervised learning cannot provide. In the study, Advantage Actor Critic (A2C) is used to develop a reinforcement learning model and agent to fulfill the need of the study. Real-world field data over four years and 30 km. is obtained and applied for developing the reinforcement learning model. Track geometry parameters, railway component defects, and maintenance activities are used as parameters to develop the reinforcement learning model. Rewards (or penalties) are calculated based on maintenance costs and occurring defects. The new breakthrough exhibits that using reinforcement learning integrated with digital twin can reduce maintenance activities by 21% and reduce the occurring defects by 68%. Novelties of the study are the use of A2C which is faster and provides better results than other traditional techniques such as Deep Q-learning (DQN), each track geometry parameter is considered without combining into a track quality index, filed data are used to develop the reinforcement learning model, and seven independent actions are included in the reinforcement learning model. This study is the world’s first to contribute a new guideline for applying reinforcement learning and digital twins to improve the efficiency of railway maintenance, reduce the number of defects, reduce the maintenance cost, reduce the possession time for railway maintenance, improve the overall safety of the railway operation, and improve the passenger comfort which can be seen from its results.

A Digital Twin System for Railway Infrastructure

This paper presents a concept and case study implementation for a system of digital twins (DTs) aimed at supporting the management of railway infrastructure maintenance. The system of DTs includes DTs and software services. The case study uses, as physical asset, a subset of the railway infrastructure managed by the Passenger Rail Agency of South Africa (PRASA). The DT system concept is evaluated, using a case study, to assess its ability to meet users' information requirements and contextual requirements. The paper also evaluates the generality of the case study results. The case study illustrates that the DT system can acquire and integrate data from diverse data sources and be adapted to a changing context (in terms of user requirements, infrastructural elements, and data sources). Even though the case study considers only a subset of infrastructure, the scalability of the DT system is illustrated, indicating its potential for larger implementations, within and beyond PRASA. The paper, therefore, shows that the DT system concept can provide an integrated view of the data on the railway infrastructure, thereby supporting data-led decision-making by infrastructure maintenance managers.