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.

Modern smartphones, widely available and equipped with multiple sensors, offer the potential for railway infrastructure condition monitoring through mobile crowdsensing without disrupting operational railway services. This paper investigates key factors influencing the use of smartphone accelerometers for railway track quality assessment and highlights the associated challenges. Differences in accelerometer characteristics across three budget smartphones, including variations in sampling frequencies and dynamic sensitivity, are analyzed. A case study conducted on in-service passenger trains examines the effects of operational conditions, specifically vehicle speed and smartphone placement within the car body, on the frequency content and magnitude of recorded signals. Additionally, this study compares smartphone measurement results with a conventional track quality index derived from track geometry measured by specialized vehicles. Promising correlations are observed between the standard deviation of the smartphone vertical acceleration signals and the longitudinal level-based track quality index, demonstrating the potential of smartphones to assess track quality and detect local anomalies. However, variations caused by vehicle speed and smartphone placement pose challenges for standardizing track quality assessments. These findings highlight the potential of mobile crowdsensing for railway infrastructure monitoring while emphasizing the need for strategies to address variability in operational conditions and device characteristics.

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.

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.

This study presents a measuring framework for railway transition zones using a case study on the Swedish line between Boden and Murjek. The final goal is to better understand the vertical dynamics of transition zones using hammer tests, falling weight measurements, and axle box acceleration (ABA) measurements. Frequency response functions (FRFs) from hammer tests indicate two track resonances, for which the FRF magnitudes on the plain track are at least 30% lower than those at the abutment. The falling weight measurements indicate that the track on the bridge has a much higher deflection than the track on the embankment. Two features from ABA signals, the dominant spatial frequency and the scale average wavelet power, show variation along the transition zone. These variations indicate differences in track conditions per location. Finally, the ABA features in the range of 1.05–2.86 m⁻¹ are found to be related to the track resonance in the range of 30–60 Hz. The findings in this paper provide additional support for physically interpreting train-borne measurements for monitoring transition zones.

Railway transition zones connecting conventional embankments and rigid struc-tures, such as bridges and tunnels, usually degrade much faster than other railway sections. Efficient health condition monitoring of transition zones is important for preventative track maintenance. In this paper, a methodology for monitoring rail-way transition zones using acceleration measurements on multiple axle boxes (multi-ABA) of a passing train is presented. To showcase its capability, the measurements in the Netherlands, Sweden, and Norway are analyzed and dis-cussed. It is found that different bridges and transition zones exhibit unique char-acteristics including dominant wavelengths and energy distribution. Based on these unique characteristics, the geometry and support conditions at different lo-cations of a transition zone can be evaluated. Higher train speed makes the char-acteristics more pronounced. The results demonstrate that the multi-ABA meas-urement has the potential to evaluate and thus monitor the health conditions of various transition zones.

This work presents the results of a measurement campaign to demonstrate the effectiveness of the axle box acceleration (ABA) technology for detecting rail defects. The measurements were conducted along the Iron Ore line between Sweden and Norway for the IN2TRACK3 project. This line is mostly single-track with passenger-freight mixed traffic and heavy axle load. Historical data and track information data were not considered in this study. By analyzing data acquired from the accelerometers in vertical and longitudinal directions, rail defects were detected in near real-time using big-data analytics. For our validated sections, 100% of rail defects (including squats) were detected using time-frequency analysis and an outlier detection approach. The methodology also allows for identifying priority locations, e.g., defective welds, joints, transition zones, etc., and its use for prescriptive maintenance recommendations is being explored in the framework of the IAM4RAIL project.

A train-borne laser Doppler vibrometer (LDV) directly measures the dynamic response of railway track components from a moving train, which has the potential to complement existing train-borne technologies for railway track monitoring. This paper proposes a holistic methodology to characterize train-borne LDV measurements by combining computer-aided approaches and real-life measurements. The focus is on the speed-dependent characteristics because the train speed affects the intensity of railway sleeper vibrations and the intensity of speckle noise, which further affects the quality and usability of the measured signals. First, numerical models are established and validated to simulate sleeper vibrations and speckle noise separately. Then, a vibration–noise separation method is proposed to effectively extract speckle noise and structural vibrations from LDV signals measured at different speeds. The parameters of the separation method are tuned using simulation signals. The method is then validated using laboratory measurements in a vehicle-track test rig and applied to field measurements on a railway track in Rotterdam, the Netherlands. Further, the speed-dependent characteristics of train-borne LDV measurement are determined by analyzing the competition between sleeper vibrations and speckle noise at different speeds. Simulation and measurement results show that an optimal speed range yields the highest signal-to-noise ratio, which varies for different track structures, measurement configurations, and operational conditions. The findings demonstrate the potential of train-borne LDV for large-scale rail infrastructure monitoring.

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.

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.

This article develops and tests a self-contained railway track monitoring system that fits in existing vehicles without the need for speed and load control. Combining a train-borne laser Doppler vibrometer and axle box accelerometers enables synchronized measurements of train-track response under operational conditions. Utilizing a GPS antenna and video camera, we propose the multisignal processing method to obtain train-track vibrations with train position and speed. Then, we fuse the multiple signals to extract an impact index and a resonance index and further propose an interpretable anomaly detection strategy. We test the system on an operational line at 20-60 km/h under different working conditions and verify the detection results using information from conventional technologies. The impact index peaks near joints and welds, and the resonance index yields a good correlation with the measured track geometry. The developed solution achieves the detection, localization, and quantification of surface and support anomalies in railway tracks.

Due to train load and aging, the dynamic properties of railway tracks degrade over time and deviate over space, which should be monitored to facilitate track maintenance decisions. A train-borne laser Doppler vibrometer (LDV) can directly measure track vibrations in response to the moving train load, which can be potentially applied to large-scale rail infrastructure monitoring. This paper characterizes track structures as a distributed system by estimating transfer functions between the wheel-rail force and the response of each sleeper measured by a train-borne LDV. A challenge with this technique is that a train-borne LDV measures only a fragment of the response for each sleeper while the train load is moving. To investigate the feasibility of this technique and the influence of key factors, we perform numerical simulations using a vehicle-track model and analyze the estimation performance through comparison with simulated impact hammer tests. We find that the transfer function estimated under a moving excitation is close to but noisier than that estimated under an impact load. Partial measurement affects the estimation performance significantly, and a wider sleeper provides a better estimate and a higher frequency resolution. Train speed is a crucial factor for a train-borne LDV system. As the vehicle speed increases, the estimation performance gets better at high frequencies but worse at low frequencies.

Monitoring the dynamic properties of railway tracks is essential for the safety of train operation and the efficiency of track maintenance. Several vibration-based technologies are available for measuring such properties, but each has its limitations such as low efficiency and limited frequency band. There is still a lack of train-borne technologies applicable to extracting the load-response relationship of track structures, especially when a variety of track components and a wide frequency range are concerned. A laser Doppler vibrometer (LDV) is a noncontact sensing instrument for vibration measurement. A train-borne LDV can target its laser spot on tracks, continuously scan track structures during train operation, and directly measure track vibrations in response to the moving train. It has the potential to complement existing technologies and monitor the dynamic properties of railway tracks.
This dissertation develops a new technology based on train-borne LDV for measuring the vibration and load-response relationship of railway tracks over a wide frequency range…

Load identification from vibration measurements is usually cost-effective for obtaining dynamic loads on structures. Modal testing enables structural models to be validated or updated prior to being used for load identification. This paper proposes a methodology to make better use of modal test data for developing load identification methods. Modal test data are split into two datasets. One is used for model updating, and the other is used to validate load identification methods by inputting the measured vibration response and comparing the identified loads with the measured loads. Crossvalidation can be achieved by using different splitting of data. This paper demonstrates this methodology with a case study in which impact hammer tests are performed on a stiffly-connected assembly. The test data support the optimization-based updating of a simplified model and the validation of a proposed Newmark-β-based load identification method. The results show that different impact locations of the model updating dataset affect the identification accuracy of the load identification dataset. The Newmark-β- based method yields comparable performance to the traditional frequency-domain method, while it has the advantage of being implemented at each time step.

Operational modal analysis (OMA) enables the identification of modal characteristics under operational loads and conditions. Traditional frequency-domain methods cannot directly capture modal changes over time, while existing time-frequency representations are not sufficiently interpretable due to spurious modes and implicit parameter design. This paper develops a new OMA method in time-frequency representation based on frequency-domain decomposition (FDD). Short-time FDD and a convolution-based strategy are proposed to obtain singular values and local mode shape similarity, respectively, which are further fused into mode indicators by a fuzzy-based strategy mimicking the modal assurance criterion. The method provides not only a global view of the modal characteristics over time and frequency but also estimates of the modal parameters. It is applicable to strongly nonstationary responses under time-varying loads and conditions. All the parameters explicitly affect the time-frequency representation, and the interpretability is enhanced by including physical information from the user's prior knowledge in selecting parameters and peak bands. The proposed method is validated based on a study of railway sleepers under train passage. The rigid-body motions and bending modes are identified at frequencies up to 6,500 Hz in laboratory tests and 4,500 Hz in field tests at speeds up to 200 km/h. The identified natural frequencies and mode shapes agree with experimental modal analysis (EMA). The proposed method outperforms EMA in terms of broad frequency range and low measurement cost and can be potentially applied to structural health monitoring under operational conditions.

Speckle noise is a major problem for structural vibration measurements with Laser Doppler vibrometer on moving platform (LDVom) due to its highly random, frequent, and broadband nature, especially at high speeds. This paper develops a new post-processing framework to reduce speckle noise based on a case study of LDVom measurements on railway tracks. First, the characteristics of the speckle noise are studied. As the speed increases, the speckle noise occurs more frequently, with shorter intervals, shorter durations, greater amplitudes, and broader frequency bands. Then, a three-step despeckle framework is proposed, consisting of spike detection, imputation, and smoothing. This framework works by detecting and replacing spikes, recovering false positives, and smoothing false negatives and residual noise. To showcase this framework, we use a wavelet-based method for Step 1, an ARIMA-based method for Step 2, and a Butterworth filter for Step 3. Besides, the parameter selection strategies and the alternative methods are discussed. Next, the methods are validated through qualitative comparison and quantitative evaluation using a Monte Carlo-based strategy. We demonstrate that the proposed methods effectively reduce the speckle noise at speeds of at least 20 km/h while avoiding the pseudo vibrations. Finally, we show that the LDVom successfully captures the track vibrations at dominant frequencies of 500 ∼ 700 Hz with good repeatability between different laps and good agreement with trackside measurements.