Continuous wheel condition monitoring is indispensable for the early detection of wheel defects. In this paper, we provide an approach based on cepstral analysis of axle-box accelerations (ABA). It is applied to the data in the spatial domain, which is why we introduce a new data representation called navewumber domain. In this domain, the wheel circumference and hence the wear of the wheel can be monitored. Furthermore, the amplitudes of peaks in the navewumber domain indicate the severity of possible wheel defects. We demonstrate our approach on simple synthetic data and real data gathered with an on-board multi-sensor system. The speed information obtained from fusing global navigation satellite system (GNSS) and inertial measurement unit (IMU) data is used to transform the data from time to space. The data acquisition was performed with a measurement train under normal operating conditions in the mainline railway network of Austria. We can show that our approach provides robust features that can be used for on-board wheel condition monitoring. Therefore, it enables further advances in the field of condition based and predictive maintenance of railway wheels.

The digitalization and automatization of railway infrastructure health diagnostics using various kinds of embedded wayside and onboard sensors in combination with common monitoring and inspection motivates a more and more integrated health analysis for all the relevant asset components such as rails, ballast, switches and crossings, point machines, and others. In this context, the present contribution discusses how an integrated research data set – as currently being collected by partners within the Europe’s Rail project IAM4Rail – is going to stimulate new research and developments as well as innovative solutions with regard to several use cases from the field of railway infrastructure maintenance. This includes the application of modern data fusion techniques based on artificial intelligence as well as physical and hybrid modelling approaches.

Integrating new rail infrastructure measurement techniques requires a deep understanding of data and monitoring goals. The LEONARDO platform facilitates rapid testing of technologies, providing easy access to operational data for collaboration with industry and research partners. The platform focuses on acquiring data from infrastructure assets from on-track perspective within a ± 5-m radius, aiming to gather valuable information, including the possibility of detecting underground problems. Practical examples showcase that applications are working and are more than a one of test: this is due to the involvement of end-users and their persistence to use the information. The diverse data sources pose also intriguing challenges for in-depth research, making this setup appealing to researchers. Crucial to its success is the unobstructed access to operational infrastructure.