Railways are facing significant challenges with the ever-growing demand for transportation, the imperative to reduce carbon emissions, and the need to maintain operational efficiency and safety. However, an increase in rail traffic and load can lead to an increase in degradation of the track components and thus reduce the infrastructure quality. Such degradation leads to failures of components, consequently resulting in a higher frequency of interventions for maintenance and renewal activities. Traditionally, railway track component inspection relies on visual based inspection techniques that are carried out during walking inspections or by using measurement cars. Manual inspections are slow, cost and labour intensive and are prone to human errors. Inspections based on measurement cars are cost intensive and requires track possession and thus cannot be utilised frequently without compromising the operational capacity. Further, the inclement weather conditions, especially in the north of Sweden, inhibits regular inspection based on these visual inspection methods. To overcome these challenges a train based differential eddy current sensor, based on the principle of electromagnetic induction, was developed to monitor railway track components. The sensor system was able to detect fastening system and identify missing clamps within the fastening system during regular operations. The aim of this study is to investigate the possibility of using the proposed sensor system to detect railway joints. Railway joints are where two rail segments meet, which makes them a structural weak point, and these are prone to wear, loosening, and misalignment over time. Constant monitoring helps to ensure that the joints maintain their integrity under varying weather conditions, heavy loads, and repeated stress. This paper will investigate the effectiveness of the proposed eddy current sensor to monitor such railway joints realised through laboratory and field measurements.

Ensuring rail infrastructure integrity is crucial for passenger safety and freight transport efficiency. Continuous monitoring of railway track components, therefore, plays a vital role in ensuring safe and reliable railway operations. Traditional inspection methods, such as manual and visual inspections, often miss subtle defects, especially when track components are obscured due to harsh environmental conditions, leading to increased risks and costly maintenance. To address these challenges, a differential eddy current sensor was developed that can be mounted on in-service trains for regular inspections. The current study aims to enhance the knowledge of the sensor capability by developing data driven and multi-physics simulation models to analyze the magnetic response of critical track components and their defects. Comprehensive simulations will consider interactions among the sensor, track components, operational and environmental conditions, and train dynamics, thus ensuring robust and resilient infrastructure. This paper proposes a methodology for developing a baseline multiphysics simulation model to generate synthetic data, enhancing and complementing data-driven approaches to improve the sensor system’s detection capabilities, addressing the need for an efficient inspection procedures and optimized maintenance practices. The findings highlight the potential of Multi-physics simulations in detecting critical rail defects and advancing railway infrastructure resilience.

Introduction: Curve squeal is a loud tonal noise from railway traffic that contributes to environmental noise pollution. Squealing arises from friction-induced vibrations in the wheel-rail contact during vehicle curving under specific friction conditions. Environmental factors are known to influence these friction conditions and, consequently, the tendency of squeal occurrence. This study investigates whether environmental variables measured from the wayside of the track can be used to predict curve squeal using machine learning models.

Methods: Separate prediction models were developed for low-rail and high-rail squeal using a labeled dataset collected during a 19-month measurement campaign at a commuter railway curve in Sweden. Multiple machine learning algorithms were evaluated, and feature importance analysis was used to investigate the environmental predictors associated with low-rail and high-rail squeal. The practical usefulness of the prediction models was further assessed for adaptive top-of-rail friction modifier (TOR-FM) application.

Results: Environmental variables contained useful predictive information regarding curve squeal occurrence, although the overall predictive performance remained limited. The tree-based ensemble models generally achieved the highest performance, while the feature importance analysis indicated that low-rail and high-rail squeal relied on different feature patterns. The operational assessment demonstrated that the prediction models could reduce unnecessary TOR-FM triggering while maintaining high squeal detection rates.

Discussion: The results demonstrate the potential of combining environmental monitoring with machine learning to support site-specific predictive railway noise mitigation and maintenance decision-making. The differences between low-rail and high-rail prediction further indicate the value of treating the two squeal types as separate prediction tasks.

Rotor-to-stator rubbing in rotating machinery, resulting from tight clearances, introduces complex dynamics that can potentially lead to high vibrations and machine failure. Historically, the rubbing models were addressed using cylinder-to-cylinder contacts; however, recent attention has shifted towards examining blade-tip contact in turbines, which affects the systems dynamics and efficiency. This study investigates the impact of the variations in blade number on bladed rotor systems, emphasizing on the types of motion that occur as function of the operational speed in the sub-critical range. A simplified bladed rotor model has been developed, using a Jeffcott rotor with blades represented as damped elastic pendulums. The equations of motion are derived and numerical simulations are performed to explore the system’s behaviour with varying blade numbers (3, 5, 7, and 10) in order to analyse displacements, contact forces and bifurcation diagrams as function of the rotating speed. Results reveal distinct regions: periodic motion (I and III) and chaotic motion (II and IV) appear alternatively in the bifurcation diagram, with the chaotic regions occurring at specific fractions of the natural frequency and the number of blades. The study concludes that chaotic motions are associated with larger displacements and higher contact forces, and the vibrational behaviour becomes less hazardous as the number of blades increases. In addition, the appearance of periodic and chaotic motions occur in the same regions by scaling the rotating speed with the number of blades and natural frequency of the system. From an operational perspective, this dynamic investigation offers valuable insights into the severity of blade rubbing in industrial systems. It can guide the implementation of mitigation solutions to prevent worst-case failure scenarios and help to perform adjustments to either operational or design parameters. 

The railway industry relies heavily on the efficient operation of its infrastructure to facilitate the transportation of goods and passengers over long distances. In the last decades, wayside monitoring systems have emerged as crucial tools for ensuring the safety, reliability, and optimal performance of railway vehicles. This article investigates the evolving role of wayside monitoring, particularly focusing on the utilization of hot-box and hot-wheel detectors for proactive maintenance strategies. Traditional approaches to hot-box monitoring have been reactive, primarily focusing on detecting critical states of vehicles. However, a shift towards predictive maintenance using these classical systems may still be feasible by analysing deeply the detector data and extracting insights into the condition of bearings. The methodology involves reorganizing and redefining HB/HW data to identify anomalies indicative of changes in bearing operation or condition. Moreover, by assessing the quality of detector data and implementing adaptive thresholding and anomaly detection algorithms, false alarms and false negatives can be minimized, enhancing the efficiency of maintenance operations, and improving the reliability of railway networks. Overall, this study investigates and highlights the potential of utilising classical wayside monitoring systems to improve railway maintenance practices and contributing to safer and more efficient railway operations.

Gearbox faults can lead to significant damage and downtime in industrial machinery, resulting in substantial losses for manufacturers. Detection of faults in gears in the incipient state is essential to ensure safe and reliable operation of industrial machineries. In recent years, there has been an increasing interest in using machine learning algorithms to automate gearbox fault detection. This paper proposes a machine learning approach for identifying different categories of faults in a gearbox based on vibration signals. The proposed method was evaluated on a dataset of vibration signals collected from a two-stage gearbox under different operational conditions. The research is focused on developing a sequential neural network-based method for detecting multiple gear faults simultaneously. The results showed that the developed method achieved high training and validation accuracies and relatively low training and validation losses, indicating the model's ability to accurately detect and classify faults in gearboxes. The testing accuracies were also high, demonstrating the model's ability to generalize well to new data. The practical implications of the research are significant for improving the reliability and maintenance of gearboxes in various industrial applications. The developed method has the potential to reduce downtime, maintenance costs, and improve safety and efficiency.

Wheelsets form an indispensable part of the railway rolling stock and need to be periodically inspected to ensure stable, safe, reliable, and sustainable rail operation. Wheel profiles are usually inspected and measured in a workshop environment using handheld equipment or by utilizing wayside measuring equipment. A common practice for both methods is to measure the wheel profile at one position along the circumference of the wheel, resulting in a one-slice measurement strategy, based on the assumption that the wheel profile has the same shape independent of the measurement position along the wheel. In this article, the representability of a one-slice measurement strategy with respect to the wheel profile parameters is investigated using handheld measurement equipment. The calculated range of standard deviation of the parameters estimated such as flange height, flange width, flange slope, and hollow wear from the measurements shows a spread in the parameter value along the circumference of the wheel. As an initial validation of the results, measurements from the wayside monitoring systems were also investigated to see if a similar spread was visible. The spread was significantly higher for flange height, flange width, and flange slope estimated from wayside measurement equipment than for the same parameters estimated using the handheld measurement equipment.

Switches and crossings (S&Cs) are also known as turnouts or railway points. They are important assets in railway infrastructures and a defect in such a critical asset might lead to a long delay for the railway network and decrease the quality of service. A squat is a common rail head defect for S&Cs and needs to be detected and monitored as early as possible to avoid costly emergent maintenance activities and enhance both the reliability and availability of the railway system. Squats on the switchblade could even potentially cause the blade to break and cause a derailment. This study presented a method to collect and process vibration data at the point machine with accelerometers on three axes to extract useful features. The two most important features, the number of peaks and the total power, were found. Three different unsupervised machine learning algorithms were applied to cluster the data. The results showed that the presented method could provide promising features. The k-means and the agglomerative hierarchical clustering methods are suitable for this data set. The density-based spatial clustering of applications with noise (DBSCAN) encounters some challenges.