Transition zones in railway tracks often degrade faster than other locations, yet traditional health assessments rely on infrequent track geometry measurements, limiting early detection of dynamic changes. This research presents an approach for more frequent evaluation of transition zone health by integrating data sources from multiple monitoring technologies: track geometry, interferometric synthetic aperture radar (InSAR), and axle box acceleration (ABA). Missing InSAR data are addressed through spatio-temporal interpolation, and track longitudinal levels are predicted using a hybrid neural model that includes a hybrid convolutional neural network (CNN) with gated recurrent units (GRU) network and a hybrid CNN with a long short-term memory (LSTM) network. The models fuse historical and interpolated data from InSAR and ABA, enabling higher-frequency insights. A novel key performance index (KPI) based on predicted longitudinal levels is proposed to quantify track condition. The framework is validated on a transition zone at a railway bridge between Dordrecht and Lage Zwaluwe in the Netherlands. Results show that the hybrid model outperforms standalone methods and offers a good balance between accuracy and computational efficiency. The proposed approach enables earlier detection of irregularities, supporting prescriptive maintenance decisions.

This paper proposes an onboard measurement technology that combines a Laser Doppler Vibrometer (LDV) and an Axle Box Accelerometer (ABA) to approximate the dynamic load-response relationship of railway tracks. Unlike existing track-side and onboard technologies, this paper eliminates the need for load measurement, estimation, or control, enabling continuous measurements under operational conditions. The LDV mounted on the moving vehicle captures the track vibration response contactlessly, while the wheel vibration measured by ABA is used to directly represent the dynamic vehicle load. The LDV and ABA signals are combined to approximate the load-response relationship in the frequency domain. Experimental validation on a vehicle-track test rig demonstrates the effectiveness of the developed system at different speeds. Further comparisons with the hammer test result confirm its ability to capture the local dynamic properties of consecutive track segments along a railway track and also its superiority in measurement efficiency. This paper offers a promising solution for monitoring railway tracks on a large scale and allowing prescriptive maintenance of rail infrastructures.

Axle box acceleration (ABA) measurements can be used for continuously monitoring rail infrastructure and detecting rail surface defects such as squats. However, accurately detecting squats is challenging due to their short-duration responses and low occurrence in ABA signals, particularly for light squats that exhibit subtle ABA responses. To address this challenge, we propose using a spiking neural network (SNN) with time-varying weights to enhance the detection performance of rail squats based on ABA measurements. Our approach employs a simple SNN architecture without hidden layers, trained using a method that combines genetic algorithms, k-fold cross-validation, and multi-start gradient-based approach to optimise hyperparameters and weights. The proposed methodology demonstrates competitive accuracy compared to other state-of-the-art SNN-based methods on UCI benchmarks for both binary and multi-class nonlinear problems. Part of its advantages include higher efficiency with a simpler architecture and training approach that reduces computational times while achieving effective spatiotemporal pattern detection. As shown by real-field measurements from Dutch and Swedish railways in anomaly detection, it effectively captures subtle changes in light squat defect responses in ABA signals and achieves a detection performance of 100% for severe squat defects and over 93% for light squat defects. Furthermore, we show that the spike responses, postsynaptic potentials, and membrane potentials can be used as a new way to explain and analyse the ABA signals. The proposed method using time-varying weights highlights a correspondence with the physical problem and offers an ability to capture sudden and subtle changes in the responses, which is crucial, particularly for detecting defects in their early stages.

Ensuring the safety and longevity of railway bridges requires efficient, non-invasive methods for monitoring their health and detecting structural damage. Drive-by health monitoring (DBHM) has emerged as a promising approach, using vehicle-mounted sensors, such as axle box acceleration (ABA), to assess the structural integrity of bridges. This method offers the advantage of frequent monitoring under operational conditions. However, DBHM faces challenges in real-world applications due to the subtle influence of local damage and disturbances like vehicle dynamics, track irregularities, and noise. This study investigates the feasibility of using ABA to detect structural damage in a real railway bridge. Continuous wavelet transforms and filtering techniques are used to isolate different vibration components within ABA signals. A finite element model of a cracked beam is developed, and simulations reveal that local structural damage introduces a small, local peak in the quasi-static ABA component. Field measurements show the variability of ABA measurements over space and time and the resulting difficulty in directly detecting the local damage. However, probabilistic analysis suggests that reference signals under healthy conditions, combined with frequent monitoring, can enhance the reliability of damage detection using DBHM.

Frictional heat is generated at the wheel-rail interface during train operations, particularly under high slip ratios during acceleration and braking. Thermal effects can accelerate wear, induce plastic deformation, and contribute to thermal fatigue. Reliable modelling of wheel-rail contact that considers friction-induced thermal effects is desirable for the accurate prediction of wheel-rail interface deterioration. Several analytical and numerical models have been proposed to simulate thermal or thermomechanical wheel-rail loads but have rarely been validated, especially in high slip ratio scenarios where flash temperatures exceed 200 °C. This study develops and experimentally validates a three-dimensional thermomechanical finite element (FE) wheel-rail contact model for high slip ratio conditions, with contact temperatures reaching 360 °C. The model incorporates key mechanical parameters, including wheel loads, coefficients of friction, and slip ratios. Simulated rail surface temperatures across various slip ratios (5 %, 10 %, and 15 %) are compared with the flash temperatures measured with an onboard infrared thermal camera, showing good agreement with a maximum deviation of 9.9 %. This confirms the reliability of the model for simulating wheel-rail contact under thermal effects.

Friction behaviour at the wheel–rail interface is of critical importance for railway operations and maintenance and is generally characterised by creep curves. The V-Track test rig was used in this study to measure both the lateral and longitudinal creep curves with uncontaminated dry interface conditions, utilising contact pressures representative of operational railway wheel–rail systems. The novelties of this study are threefold. 1. With proper representations of train/track components, the V-Track tests revealed the effects of structural dynamics on measuring wheel–rail creep curves in real life. 2. Pure lateral and longitudinal creepage conditions were produced with two distinct experimental principles—displacement- and force-controlled—on the V-Track, i.e., by carefully controlling the angle of attack and the traction/braking torque, respectively, and thus the coefficient of friction from lateral and longitudinal creep curves measured on the same platform could be cross-checked. 3. The uncertainties in the measured creep curves were analysed, which was rarely addressed in previous studies on creep curve measurements. In addition, the measured creep curves were compared against the theoretical creep curves obtained from Kalker’s CONTACT. The influence of wheel rolling speed and torque direction on the creep curve characteristics was then investigated. The measurement results and findings demonstrate the reliability of the V-Track to measure wheel–rail creep curves and study the wheel–rail frictional rolling contact.

Nowadays, rolling stock can be equipped with high-frequency vibration sensors to continuously monitor rail infrastructures and detect defects. These moving sensors measure at high speeds and sampling frequencies, generating a massive amount of data that covers each track position with very short signal durations. These data contain a variety of dynamic and transient responses that vary significantly along the track and are affected by noise. This leads to a large amount of unlabeled and noisy data, complicating the extraction of dynamic responses for effective anomaly detection. To address these challenges, this paper proposes an unsupervised representation learning methodology to automatically capture and extract characteristic features of dynamic responses that reflect the conditions of rail infrastructures. The unsupervised nature allows exploratory analysis of high-frequency vibration signals when prior knowledge or reference information about infrastructure conditions is unavailable or very limited. A collaborative optimization process that synchronizes empirical mode decomposition (EMD) with a convolutional autoencoder (CAE) is presented. The EMD level is tuned to remove noise while preserving effective vibration responses. The CAE is trained using demodulated signals that are considered normal to generate representations that ensure reconstruction quality and differentiate between normal and abnormal conditions. Furthermore, a Gaussian mixture model is used to showcase the effectiveness of the learned representations for rail infrastructures. Applied to validated axle box acceleration data for rail defect detection and train-borne laser Doppler vibrometer data for rail fastener monitoring, our method outperforms other variants of autoencoder-based models and the wavelet-based CAE in accurately identifying the conditions. It achieves an average improvement of 16% with the axle box acceleration data and 21% with the laser Doppler vibrometer data.

As a critical factor in the degradation of rails and wheels, wheel-rail contact heat has been investigated with various analytical and numerical methods. However, the predicted temperature distributions and thermal loads have not been directly validated through measurements due to the challenges associated with accurate measurements. This study employs an infrared camera to measure the temperature variation at the wheel-rail contact under various slip ratio conditions in an in-house wheel-rail dynamic contact test rig. Wheel braking is replicated, and a wheel flat is generated. The temperature field of the contact interface is measured and analyzed, revealing the heating and cooling processes before and after the formation of the wheel flat. The results demonstrate that the contact temperature between the wheel and rail progressively increases with increasing slip ratio until a flat is formed. Notably, at a slip ratio of 8.3%, the observed contact temperature reaches 337.2 ℃ and then rises to 432.8 ℃ at a higher slip ratio of 15.9%. When the wheel flat is generated at a slip ratio of 20.4%, the observed contact temperature between the wheel and rail reaches 652.4 ℃. After the formation of the flat, the contact temperature initially decreases due to more wheel material of lower temperature entering into the contact and rises again with the increase of slip ratio. These measurement findings are valuable for calibrating and validating simulation models and investigating thermal damage related to wheel-rail interactions.

This paper presents a methodology for detecting and monitoring short pitch corrugation (SPC) under varying measurement conditions using vertical and longitudinal axle box acceleration (ABA) measurements. The main objective of the detection algorithm is to determine the likelihood and approximate severity of SPC presence, providing insights for maintenance planning. The methodology combines a validated three-dimensional finite element (3D-FE) model of the ABA responses at SPC and signal processing techniques to extract meaningful data from the real-world on-board measurements. First, a 3D-FE vehicle-track model is validated and used to quantify the physical relationships in the time–frequency responses of ABA at SPC under different levels of corrugation severity and measurement speeds. Then, a measurement train is instrumented with multiple accelerometers to capture field data on ABA at SPC, which is validated with field inspections and Railprof measurements. Finally, the ABA responses are analyzed based on the number of signals detecting SPC and an assessment of severity based on impact energy due to SPC. The methodology is demonstrated by analyzing the track between Assen and Groningen on the Dutch rail network. Results show that the methodology accurately detects registered SPC locations. Further, a whole track analysis is conducted, from which the methodology proposes new locations and severities of SPC, providing crucial information for rail maintenance planning.

Short pitch corrugation is a typical rail defect that lacks a thorough understanding and adequate root-cause solutions. This paper aims to identify the damage mechanism of short pitch corrugation through a microstructural analysis of a field rail sample. This sample made of R260Mn pearlitic steel was taken from a straight section of the Dutch railway network, and its geometry and surface hardness variation along the corrugation were measured and analyzed. Eleven specimens, including both corrugated and non-corrugated zones, were sectioned from the rail sample and continuously examined using light optical microscopy, scanning electron microscopy and micro-hardness testing. The results indicate that the corrugation damage mechanism can be categorized into three stages: (1) pre-corrugation, characterized by uniform wear and plastic deformation; (2) corrugation initiation, dominated by differential wear; and (3) corrugation growth, involving both differential wear and plastic deformation accumulation. The initiation and growth of corrugation both contribute to an inhomogeneous distribution of plastic deformation layer (PDL) in the rail subsurface, which follows an approximately sinusoidal pattern, matching the corrugation geometry in both wavelength and phase. Consequently, the hardness also varies in phase with the corrugation geometry, with higher hardness values at corrugation peaks. In the non-corrugation zone, the PDL and hardness show relatively small and irregular fluctuations. This study also provides meaningful insights into rail grinding, suggesting that grinding should account for differential PDL thickness to prevent corrugation reoccurrence due to subsurface material inhomogeneity.

Short pitch corrugation is a major rail defect worldwide, and its development mechanism remains not fully understood. This work aims to better understand corrugation and validate some numerical predictions through extensive field monitoring. 105 corrugations on four sections of mainline tracks were continually monitored for five years. Comprehensive field data were collected, including photos, geometry, and vehicle-track dynamic responses. Numerical results of corrugation development agree with the field observations. It confirms that corrugation initiates with necessary initial excitation, consistently grows at fixed locations due to differential wear, and eventually reaches a limiting amplitude. Moreover, vehicle-track longitudinal vibrations are crucial to corrugation initiation, while vertical vibration plays an increasingly important role in corrugation growth.

The ratcheting phenomenon remains a persistent concern in modern railways due to its close association with head checks, a typical type of rolling contact fatigue. This study presents experimental research focussing on elucidating the mechanical, hardening, and material ratcheting properties of one bainitic (B320) and two pearlitic (R220 and R260MN) rail steels. The experiment consisted of monotonic tension, uniaxial cyclic strain range, and uniaxial cyclic stress range tests. Two load cases representing the equivalent stresses experienced by rails under real-life wheel-rail contacts were used in the cyclic stress range tests to assess the rail ratcheting behaviour in railway operating conditions. The test results highlighted that the two pearlitic steels showed similar mechanical strength and ratcheting behaviour; and by contrast, the bainitic steel exhibited superior mechanical strengths and yielded significantly weaker ratcheting responses for both load cases. The study then characterised the three rail steels by calibrating for them the hardening parameters of two classical constitutive models: Chaboche and Ohno-Wang II (OWII) based on the monotonic and cyclic strain range tests. The hardening parameters of the constitutive models were then optimied based on the cyclic stress range tests to represent the material ratcheting behaviours of rail steels for each load case. Notably, the OWII model demonstrated higher precision in reproducing ratcheting strains and rates than the Chaboche model, which faced limitations in simulating relatively low ratcheting rates. This study enhanced the understanding of the mechanical and ratcheting properties of the investigated rail steels and provided insights into the applicability of constitutive models for predicting and mitigating rail ratcheting effects.

This study experimentally and numerically investigated wheel–rail rolling contact fatigue (RCF), focusing on the initiation mechanisms of head check (HC). The experimental study was conducted using V-Track, a scaled test rig developed at TU Delft that is able to simulate real-life wheel–rail contact with controllable contact geometries and loading conditions. Ratcheting and HCs were generated on the V-Track rails with wheel–rail frictional rolling contact loading for up to 60,000 cycles. Rail samples with HCs were then examined with a microscopic analysis focusing on the R260MN steel grade. The boundary element method (BEM) and finite element method (FEM) were then applied to calculate wheel–rail contact-induced stress states in and below the rail surface under the same contact conditions as the experiment. The rail surface shear stresses calculated with BEM exhibited a strong correlation to the ratcheting observed within the rail running band in the microscopic analysis. Moreover, the plastic flows and cracks outside the running band identified by the microscopic analysis were correlated to the rail surface stresses, especially outside the contact patch, and subsurface stresses calculated with FEM: the results suggested that the accumulation of residual stresses could also contribute to plastic flow and the consequent initiation of cracks outside the running band.

This paper investigates the growth and treatment of a major type of rail rolling contact fatigue (RCF) known as head checks (HCs). The analysis is based on extensive field data of 212 curved tracks made of R260 steel across the entire Belgian railway network. The HC crack depth was mainly measured by eddy current testing. The growth rates of HCs are analysed in relation to the curve radius, annual traffic load, and rail wear. The key findings are as follows: 1) Tracks with radii between 750 and 1000 m exhibit the highest HC growth rate of about 1.5 mm per 100 million gross tons (MGT) and the largest occurrence probability of about 25 %. 2) A counterintuitive result is that the HC growth per MGT is higher on lines with lower annual traffic loads, consistent with the trend observed in rail wear rates. 3) The artificial wear methods to control RCF, such as preventive grinding, should consider annual traffic load and service time, rather than solely accumulated tonnage, as is the current practice. Based on these findings, a new method is proposed to estimate the magic wear rate for the Belgian railways, which can serve as input for optimising grinding operations to mitigate HCs.

A transfer function (TF) is an effective representation of the load-response relationship of railway track structures. To fill the gap in measuring track structure TFs over a wide frequency range from a moving vehicle, we develop a TF measurement system and the associated TF estimation methodology. Accelerometers are utilized to estimate the dynamic vehicle load to track structures, and a laser Doppler vibrometer (LDV) is used to scan track structures and measure their vibration response. First, operational modal analysis is applied to vehicle impact response over joints to identify its modal parameters, which support the estimation of dynamic wheel-rail forces from vehicle vibrations. This combination eliminates the need to pre-define the vehicle stiffness, vehicle damping, and vehicle body mass and enables the vehicle parameters to be updated under operational conditions. Meanwhile, a signal processing method is applied to LDV signals to reduce speckle noise and compensate for the effect of vehicle vibration. Then, a continuous track structure is segmented into distributed sections, and a TF is estimated for each track section using the estimated wheel-rail force as input and the extracted track vibration as output. We validate the methodology in a vehicle-track test rig on different track sections (with or without joints) and at different speeds (from 8 km/h to 16 km/h). The results are further compared with trackside measurements and hammer tests. We demonstrate that the track vibrations extracted from the LDV signals are consistent with those measured by trackside accelerometers. The shapes and resonance frequencies of the estimated TFs are in good agreement with those measured from the hammer tests in the frequency range of 200–800 Hz. The developed system captures differences in the TFs between different track sections, suggesting its potential to be used for structural health monitoring of railway tracks.

Vibrations resulting from dynamic vehicle-track interactions (VTI) offer valuable insights into track conditions. This paper presents an approach for track condition monitoring by detecting and quantifying multiple track degradations using a digital twin of the VTI system. Unlike existing techniques that focus on a specific degradation type at a single track component, our proposed method provides a generic and integrated framework. By combining a physics-based VTI model with a data-driven model, we dynamically update the digital twin’s state based on measured axle-box accelerations (ABA). We introduce a local ABA feature extracted from its spectrogram and demonstrate its effectiveness in distinguishing various degradations at different track positions. The implementation and capability of the proposed approach were demonstrated in a case study conducted on a transition zone of a railway bridge. The simultaneous track stiffness variations in the railpad/fastening and ballast layers were successfully detected, confirming the effectiveness of our approach. The case study also showcases the generality, interpretability, efficiency, and robustness of the proposed approach in identifying concurrent degradation. Our proposed framework opens new possibilities for cost-effective continuous track monitoring for railway infrastructure management.

Inefficient management of rail surface defects can increase maintenance costs, safety hazards, service disruptions, and catastrophic failures like rail breaks. To achieve adequate management, having effective technology capable of timely detecting and frequently monitoring rail defects is of utmost importance. The aim is early detection of defects to maintain safety levels and prevent the re-appearance due to residual damages.

Various measurement technologies, such as visual inspections, geometry profile measurements, and other measurement techniques, have been used for the detection of rail defects. While these methods provide insights, they often lack the capability for early-stage defect detection. Thus, most of these technologies are suitable for reactive maintenance since they detect defects when they reach a certain severity level. Axle box acceleration (ABA) technology provides a solution capable of frequent monitoring, mounted on trains in operation without dedicated measurement vehicles (see figure 71-1). Its basic principle is to use a train as a moving load that excites the infrastructure and to detect defects by evaluating the time-frequency characteristics of the dynamic response measured by accelerometers installed on axle boxes of the train. ABA systems have shown promise in detecting defects in the early stages. However, its widespread application and need for robustness require further validation and development. This work presents the results of detecting and monitoring rail surface defects using ABA technology.

Railway track stiffness is an important property closely related to track condition and maintenance. Track stiffness variations occur over time and space due to dynamic train loading and aging of track components. Track stiffness variations may further lead to geometry deteriorations and vibration problems. It is therefore essential to continuously monitor track stiffness variations, as well as related track component degradations, over time and space, so that preventive and targeted maintenance can be performed to reduce the life-cycle cost of rail infrastructures.

Various techniques exist for evaluating track stiffness from dynamic responses of the train– track system, including track-side and train-borne measurements. The track-side measurement uses sensors mounted on sleepers to measure the track stiffness at each sleeper support. Nonetheless, because of the cost of sensor deployment, the track-side measurement is more suited for discrete locations in the rail network of special interest, such as transition zones. To scan for track stiffness over a long distance, specialised measurement vehicles were developed. However, they can only measure at low speeds and require track occupation, thus not suitable for frequent measurements. In comparison, train-borne measurements using in-service vehicles are more cost-effective and allow for more frequent surveys of the entire rail network. However, existing techniques are not able to measure the respective stiffness of different track layers, such as the ballast and railpad stiffness. In addition, existing train-borne techniques using in-service vehicles have seldom been validated by field measurement data.

Excessive underground train-induced building vibration is an environmental concern resulting in human distress. Wheel polygon is probably one of the main vibration sources. In the present work, an explicit-integration time-domain, fully coupled 3D dynamic train-track-tunnel-soil-building FE model is developed and employed to investigate the effects of wheel polygon on the building vibration. Measured wheel polygon data is analyzed and input into the developed FE model. Based on the simulation results, it is found that the contribution of the wheel polygon to the building vibration is considerable in the frequency range from 30 to 180 Hz. Wheel polygon makes the building vibration more pronounced at the P2 resonance frequency and the passing frequencies (f = v/λ) of wheel polygon. From the foundation to a high floor in the building, the effect of the P2 resonance-related wheel polygon attenuates the slowest while the effects of the other orders of wheel polygon attenuate fast.

The Coefficient of Friction (CoF) is an important parameter affecting acceleration and braking behavior of trains, and consequently the inter-train distance and utilization of track. To optimize operation schedules, maximize railway capacity, and realize automatic train operations, reliable measurements of the CoFs experienced by in-service trains are desirable. In this study, a train-borne measurement approach is proposed based on a torque modulation concept. It involves superimposing a small-amplitude sinusoidal signal on the motor torque. Because the wheel-rail friction force acts as variable damping, it causes a phase difference between the angular velocity response of the wheelset and the input modulated torque signal. This phase difference can be used to determine the creep coefficient, i.e., the slope of the creep curve, and then to estimate the CoF in combination with the measured Coefficient of Adhesion (CoA), i.e., the ratio between the wheel-rail friction force and normal load. Simulations of torque modulation with VI-Rail are conducted. Variation of phase difference with the increase of the modulated torque is derived theoretically and compared with numerically obtained results using the VI-Rail multibody dynamics model under different CoF conditions. The good agreement between the results indicates the effectiveness of the proposed measurement concept.