Nowadays, railway freight transportation is becoming more and more crucial since it represents the best alternative to road transport in terms of sustainability, pollution, and impact on the environment and on public health. Upgrading the potentiality of this kind of transportation, it would be possible to avoid delays in goods deliveries due to road accidents, traffic jams, and other situation occurring on roads. A key factor in this framework is therefore represented by monitoring and maintenance of the train components. Implementing a real time monitoring of the main components and a predictive maintenance approach, it would be possible to avoid unexpected breakdowns and consequently unavailability of wagons for unscheduled repair activities. As highlighted in recent statistical analysis, one of the elements more critical in case of failure is represented by the brake system. In this view, a real time monitoring of pressure values in some specific points of the system would provide significant information on its health status. In addition, since the braking actions are related to the load present on the convoy, thanks to this kind of monitoring, it would be possible to appreciate the different behavior of the system in case of loaded and unloaded trains. This paper presented an innovative wireless monitoring system to perform brake system diagnostics. A low-power system architecture, in terms of energy harvesting and wireless communication, was developed due to the difficulty in applying a wired monitoring system to a freight convoy. The developed system allows acquiring brake pressure data in critical points in order to verify the correct behavior of the brake system. Experimental results collected during a five-month field test were provided to validate the approach.

Bridges are strategic infrastructures which are subject to degradation during their lifetime. Therefore, structural health monitoring is becoming an essential tool in this field to drive maintenance activities. Conventional vibration monitoring systems relying on wired sensors present several limitations for continuous monitoring projects on a huge number of structures. In this work, a smart wireless monitoring system is developed for bridge modal identification with the aim of providing an alternative tool to wired sensors in this field. The main peculiarities of the designed wireless accelerometers are the low cost, the ease of installation on the structure, and the long-term autonomy granted by the use of energy harvesting techniques. To assess their measurement performance, some prototypes were installed for a field test on a railway bridge and significant data were acquired. Through the processing of the collected data, bridge main natural frequencies were estimated, and their values were in good agreement with the reference ones obtained with a conventional system. The assessment of the developed solution paves the way to the instrumentation of many bridges with the aim of performing continuous monitoring activities using simple diagnostic indicators, such as the variation of frequencies in time.

The realization of the first prototype of a vehicle requires several tests of the algorithms implemented on the electronic control unit (ECU). This represents an important step for conventional vehicles, which becomes fundamental when dealing with unmanned vehicles. Since there is no human supervision, most critical tasks are handled by the control unit, which results in higher complexity for the control algorithms. In this work, a software-in-the-loop (SiL) test bench is used to validate the control algorithms of a vehicle control unit (VCU) for a driverless railway vehicle (DLRV). The VCU manages the control of the traction motors, pneumatic braking systems, and range extender, as well as control of the hybrid powertrain configuration to guarantee a high level of availability via the use of redundant systems. The SiL test bench has been developed in a Simulink real-time environment, where the vehicle model is simulated along with its fundamental subsystems. The model communicates with the VCU through a CAN bus protocol in the same way that it will operate with a real vehicle. The proposed method can be used to simulate many mission profiles for the DLRV, which may last several hours each. Moreover, this kind of test bench ensures a high time resolution, which allows one to find solutions for problems which occur with a time scale that is much smaller than the simulation time scale.

This paper aims to discuss how Thermal Imaging could benefit of Deep-Learning approaches for increasing temperature measurement accuracy in those complex applications where thermal images are subject to severe temperature variations and the target component position varies continuously. Real-time temperature monitoring of braking components during train braking operations indeed represents a well-matched example, given the challenges embedded by this application case: relative camera-to-target movements, variable contrast levels in the thermal image, etc. just to cite some. The advantage of using a specifically trained deep-learning based semantic segmentation model to accurately locate and track target components, is demonstrated by comparing the thermal evolution of a specific component with respect to those obtained exploiting conventional machine vision tracking methods. Experimental validation in a high-speed railway environment shows the proposed method reduces temperature bias to less than 0.5°C when compared to thermocouple data. This accuracy is crucial for ensuring the safety and reliability of railway braking systems. While the widespread use of thermal cameras on trains may be impractical, the approach demonstrates that it is possibile to effectively exploit semantic segmentation models to enhance Thermal Imaging and retrieve more accurate temperature data in complex real-time applications.