In recent decades, the demand for rail transport has been growing steadily and faces a double problem. Not only must the transport capacity be increased, but also a more flexible service is needed to meet the real demand. Both objectives can be achieved through virtual coupling (VC), which is an evolution of the current moving block systems. Trains under VC can run much closer together, forming what is called a virtually coupled train set (VCTS). In this paper, we propose an approach in which virtual coupling is implemented via model predictive control (MPC). For this purpose, we define a robust controller that can predict, based on a dynamic model of the train, the state of the system at later moments of time and make the appropriate control decisions. A robust MPC (RMPC) is obtained by introducing two uncertain variables. The first uncertain variable is added to the acceleration equation of the dynamic model, while the second uncertain variable is used to define the uncertainty in the train positioning. To test the RMPC for virtual coupling, two simulation cases are performed for a metro line, analysing the influence of both the uncertainties. In all cases, the results obtained show a safer operation of the virtual coupling without significantly affecting the service.

In the railway sector, rolling stock and infrastructure must be maintained in perfect condition to ensure reliable and safe operation for passengers. Climate change is affecting the urban and regional infrastructure through sea level rise, water accumulations, river flooding, and other increased-frequency extreme natural situations (heavy rains or snows) which pose a challenge to maintenance. In this paper, the use of artificial intelligence based on predictive maintenance implementation is proposed for the early detection of degraded conditions of a bridge due to extreme climatic conditions. For this prediction, continuous monitoring is proposed, with the aim of establishing alarm thresholds to detect dangerous situations, so restrictions could be determined to mitigate the risk. However, one of the main challenges for railway infrastructure managers nowadays is the high cost of monitoring large infrastructures. In this work, a methodology for monitoring railway infrastructures to define the optimal number of transductors that are economically viable and the thresholds according to which infrastructure managers can make decisions concerning traffic safety is proposed. The methodology consists of three phases that use the application of machine learning (Random Forest) and artificial cognitive systems (LSTM recurrent neural networks).

Recently, passenger comfort and user experience are becoming increasingly relevant for the railway operators and, therefore, for railway manufacturers as well. The main reason for this to happen is that comfort is a clear differential value considered by passengers as final customers. Passengers’ comfort is directly related to the accelerations received through the car-body of the train. For this reason, suspension and damping components must be maintained in perfect condition, assuring high levels of comfort quality. An early detection of any potential failure in these systems derives in a better maintenance inspections’ planification and in a more sustainable approach to the whole train maintenance strategy. In this paper, an optimized model based on neural networks is trained in order to predict lateral car-body accelerations. Comparing these predictions to the values measured on the train, a normal characterisation of the lateral dynamic behaviour can be determined. Any deviation from this normal characterisation will imply a comfort loss or a potential degradation of the suspension and damping components. This model has been trained with a dataset from a specific train unit, containing variables recorded every second during the year 2017, including lateral and vertical car-body accelerations, among others. A minimum average error of 0.034 m/s² is obtained in the prediction of lateral car-body accelerations. This means that the average error is approximately 2.27% of the typical maximum estimated values for accelerations in vehicle body reflected in the EN14363 for the passenger coaches (1.5 m/s²). Thus, a successful model is achieved. In addition, the model is evaluated based on a real situation in which a passenger noticed a lack of comfort, achieving excellent results in the detection of atypical accelerations. Therefore, as it is possible to measure acceleration deviations from the standard behaviour causing lack of comfort in passengers, an alert can be sent to the operator or the maintainer for a non-programmed intervention at depot (predictive maintenance) or on board (prescriptive maintenance). As a result, a condition-based maintenance (CBM) methodology is proposed to avoid comfort degradation that could end in passenger complaints or speed limitation due to safety reasons for excessive acceleration. This methodology highlights a sustainable maintenance concept and an energy efficiency strategy.

Corrugated cardboard has waved cores with small flutes that prevent the use of detailed numerical models of whole structures. Many homogenization methods in the literature overcome this drawback by defining equivalent homogeneous plates with the same mechanical behaviour at a macro-mechanical scale. However, few homogenization works have considered complete structures, focusing mainly on beams or plates. For the first time, this study explores the application of homogenization approaches to larger structures as an aid in their design process. We also considered triple-wall boards rather than single- and double-wall configurations commonly addressed in the literature. To this end, we adapted the homogenization methods proposed by Talbi and Duong to analyze thin-walled stools made of triple-wall corrugated cardboard. Using a progressive design process, we performed an efficient stool design by removing material zones with lower stresses, with 35% less material, 35% lower vertical deflections, and 66% lower stresses than the initial design. Unlike other corrugated cardboard stools, this design comprises just one folded piece instead of three, thus saving storage space. These results demonstrate the utility of homogenization techniques as an aid in the design process of whole structures made of corrugated cardboard. Further research will consider buckling analysis.

Bearing overheating and anomalous accelerations are two principal failure modes for this safety component. The supervision of bearing’s behaviour is essential to ensure a safe and reliable operation. A safety component’s failure may cause a speed limitation or even a non-available train for operating, so a predictive maintenance for bearings and other critical components is mandatory for the manufacturers, operators and maintainers in the railway sector. Bearing temperature, exterior temperature, train speed and other variables are measured every second in real time. From all the data collected and stored in the last years some algorithms and models are designed and trained in this paper to detect bearing anomalies 2 days before a real failure is detected and the safety alarm is enabled. The methodology for obtaining the optimal algorithm is exposed. Different artificial neural networks based on different optimization models such as the Mini-batch Gradient Descent (MGD) or Adam optimizer are compared. A final neural network with 10 hidden layers to detect bearing failure is proposed reaching 99% of accuracy, 95% of precision and 90% of sensitivity. The objective of predicting a bearing anomaly with some days in advanced is reached with high precision level, which will lead also to cost savings and a contribution for the sustainability because many inspections could be reduced and the energy cost associated to them.

The objective of this paper is to design a new system to reduce the risk of derailment at crossings, which are critical points in railway lines. Crossings are a common element in conventional lines of current railway systems and are the only point on the track where there is a discontinuity. Our proposal is based on adding an element to the crossing that occupies part of the crossing gap, providing a larger support surface next to the wing rail, such that the wheel does not fall into the gap. The lateral force—which is the most influential parameter in derailments—is substantially decreased, thus reducing the risk of derailment due to lifting on the rail. The proposed approach also increases the safety of the dynamic behaviour, which has a direct impact on passenger comfort and influences the service life of both the rolling stock and the track, thus reducing the cost and even increasing safety at higher speeds. It has a simple structure that is easy to assemble and does not interrupt traffic during installation. The results of simulations using this innovative solution indicate a significant reduction in lateral stresses and strains on the track, which undoubtedly produces an improvement in traffic safety; however, the results cannot be fully quantified in terms of accident reduction with only the data obtained from simulations. Therefore, it was concluded that implementation of the new crossing design provides better conditions for rolling stock to run on turnouts, increasing safety by reducing the risk of derailment. Nevertheless, it will be necessary to carry out a program of experimental tests, which we intend to make the subject of future research.