Maintenance and safety inspection of trains is a critical element of providing a safe and reliable train service. Checking for the presence of bolts is an essential part of train inspection, which is currently, typically carried out during visual inspections. There is an opportunity to automate bolt inspection using machine vision with edge devices. One particular challenge is the implementation of such inspection mechanisms on edge devices, which necessitates using lighter models to ensure efficiency. Traditional methods have often fallen short of the required object detection performance, thus demonstrating the need for a more advanced approach. To address this challenge, researchers have been exploring the use of deep learning algorithms and computer vision techniques to improve the accuracy and reliability of bolt detection on edge devices. High precision in identifying absent bolts in train components is essential to avoid potential mishaps and system malfunctions. This paper presents “BoltVision”, a comparative analysis of three cutting-edge machine learning models: convolutional neural networks (CNNs), vision transformers (ViTs), and compact convolutional transformers (CCTs). This study illustrates the superior assessment capabilities of these models and discusses their effectiveness in addressing the prevalent issue of edge devices. Results show that BoltVision, utilising a pre-trained ViT base, achieves a remarkable 93% accuracy in classifying missing bolts. These results underscore the potential of BoltVision in tackling specific safety inspection challenges for trains and highlight its effectiveness when deployed on edge devices characterised by constrained computational resources. This attests to the pivotal role of transformer-based architectures in revolutionising predictive maintenance and safety assurance within the rail transportation industry.

The railway industry forecasts growth in passenger and freight traffic over the next 30 years. This places additional demands on rolling stock depot facilities, many of which were designed and built before the modern age of information technology. This paper explores the potential of improving the efficiency and effectiveness of rolling stock maintenance management to meet the challenges of the near future, by utilising advanced computing techniques. The objective of the work is to create optimised maintenance plans for a fleet of trains, considering optimal use of resources. As a “glue” for joining up functions and operations, a generic Depot and Vehicle ontology (called the Virtual Depot) is introduced. The ontology captures the structures, relationships, and attributes of objects in the Depot (rolling stock, sensors, depot assets, tools, resources, and staff). The ontology is populated with example company and fleet-specific knowledge using an automated knowledge acquisition method. This paper describes the systematic method for the creation of a Virtual Depot. Two particular aspects are discussed in detail—knowledge acquisition of fleet-specific information obtained from a manufacturer’s Vehicle Maintenance Instruction manuals and the construction of a short-term scheduling process within the Virtual Depot. Our evaluation considers the integrative aspects of the method, demonstrating how the ontological structure and its acquired specific information informs and benefits the scheduling process, in particular with respect to schedule optimisation. Results from an initial case study show there is significant potential to optimise short-term maintenance schedules, and the ability to automatically consider resource availability in short-term scheduling is demonstrated.

The requirements for track loading limits are one of the main barriers to simple cross-acceptance of vehicles where rolling stock that is already operating successfully in one (or more) networks has to be retested before it can be approved for operation on another network. DynoTRAIN Work Package 4 studied this area in order to determine whether the additional requirements were justified, or if the process could be made much cheaper and simpler without increasing the risk of track deterioration for the networks. The review of national requirements identified modified criteria and limit values for track forces in some member states; however, these can be obtained from additional analysis of the normal test results with no new tests required. The influence of design rail inclination has also been found not to be significant, provided a realistic range of wheel–rail contact conditions are included in the tests. For line speeds greater than or equal to 160 km/h, the current standards for track construction across the member states appear to be similar. On lower speed lines in some countries, a ‘weaker’ track condition may require a lower limit on one of the vehicle assessment parameters. Track dynamics modelling has shown that the vehicle assessment parameters used in international standards are suitable for use in cross-acceptance for track forces. The use of multiple regression analysis allows the estimated maximum value for relevant parameters to be evaluated for different target conditions and then compared with the appropriate limit value, or with values for existing, comparable vehicles. Guidance has also been provided on the relevant parameters to consider when developing operating controls for different types of track deterioration.

Diesel engine failures are one reason for delays and breakdowns on the UK rail network, resulting in significant fines and related financial penalties for a train operating company. Preventing such failures is the ultimate goal, but forecasting or predicting future failures before they occur would be highly desirable. In this study, we take real world Diesel Multiple Unit sensor data, recorded in the form of event data, and repurpose it for the remote condition monitoring of critical diesel engine operations. A methodology based on windowing of data is proposed that demonstrates the effective processing of event data for predictive modelling. This study specifically looks at predicting engine failures, and through this methodology, models trained on the processed data resulted in accuracies of 88%. Explainable AI methods are then utilised to provide feature importance explanations for the model’s performance. This information helps the end user understand specifically which sensor data from the larger dataset is most relevant for predicting engine failures. The work presented is useful to the railway industry, but more specifically to train operator companies who ideally want to foresee failures before they occur to avoid significant financial costs. The methodology proposed is applicable for the predictive maintenance of many systems, not just railway diesel engines.

Squat defects are one of the most common rail surface defects. Significant research effort has gone into understand squat defects over the last 10 years which has brought about important developments in the understanding of their initiation mechanism; however, further work is still required to fully understand squat and the best methods to control them.