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.
Sea- and inner ports are intermodal traffic nodes that play an important role in transportation, especially in the transportation of goods. The appearance of track defects in a harbour railway network has a negative impact on safety, cost and comfort (for example due to noise emission).
The analysis of data obtained by embedded acceleration sensors, which are installed at the axle box of an equipped in-service vehicle, allows for continuous condition monitoring of the track infrastructure. The German Aerospace Center (DLR) develops prototypical modular multi-sensor systems
that are used in different operational environments, including on a shunter locomotive operating in an industrial harbour railway network in Braunschweig, Germany. Within the HavenZuG research project, extensive rail longitudinal profile and track geometry measurements have been performed
using established inspection methods to obtain the true underlying condition of the railway network. In the present paper, methods for gaining relevant information from the axle-box acceleration (ABA) data are presented and validated with the given reference data. The focus is on detecting
defects that are visible in the rail longitudinal profile, mainly rail corrugation. It can be shown that ABA data gathered during everyday shunting operation can be used for detecting corrugation and for inferring rail longitudinal profile parameters.
The application of AI methods to industry requires a large amount of training data that covers all situations appearing in practice. It is often a challenge to collect a sufficient amount of such data. An alternative is to artificially generate realistic data based on training examples. In this paper we present a method for generating the electric current time series produced by railway switch engines during switchblades repositioning. In practice, this electrical signal is monitored and can be used to detect unusual behaviour associated to switch faults. The generation method requires a sample of real curves and exploits their systematic temperature dependence to reduce their dimensionality. This is done by extracting the effect of temperature on specific parameters, which are then re-sampled and used to generate new curves. The model is analyzed in different practice-relevant scenarios and shows potential for improving condition monitoring methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.