Within railway infrastructure, railway point systems are among the most critical equipment, not only due to accidents and delays caused by their failures but also due to maintenance costs. The detection of early signs of degradation and the ability to identify the maintenance actions required to prevent a failure are key aspects of a successful and advantageous health assessment strategy. While studies focusing on the detection and prognostics of railway point systems exist, few or none address the correlation between environment, field layout and the point system behavior. This paper aims to consider the interaction between these factors and the point system behavior, and compare a fleet-based approach to an asset-based approach for the point systems health assessment, highlighting the influence of the field configuration on the effectiveness of the two methods. The proposed methods exploit Self-Organizing Maps (SOMs) to construct a health indicator for both the detection and the diagnosis of railway point systems. The approaches are applied to a case study for the on-line health assessment of 20 electro-mechanical point systems operating on a main line over the course of 6 months. The results show how an asset-based monitoring system is necessary in order to maintain a level of information which enables to achieve an efficient detection of anomalies and a correct identification of degradation mechanisms. In addition, fleet-based health assessment leads to a higher percentage of missed alarms, due to the intrinsic hypothesis of considering all point systems as operating in the same context and mission profile.
Traction motor blowers are essential components of electric trains. Their failure entails a complete disruption of the operational service, in addition to a safety hazard. Thus, maintaining them effectively is a must to guarantee the availability and reliability of the rolling-stock units. To this end, the predictive maintenance approach can add a lot of value because blowers display a complex behaviour, they seldom fail, but when they do the costs associated to their replacement and the subsequent time out of service of the train (not generating revenue) are prohibitively high and may challenge the viability of a business case. However, getting to deploy an adequate data-driven predictive approach is difficult because it entails collecting streams of useful information in order to generate bespoke diagnostics and prognostics in a timely manner. In this article, we have developed and deployed a network of intelligent wireless sensors that enable to capture vibration data easily on board, and to seamlessly integrate it into our data processing pipeline for a remote inspection of the blowers. In order to adapt the data analysis modules to the blower characteristics and test conditions, we have conducted a feature mapping with the complete fleet of blowers (288 component units) and a statistical analysis to detect anomalies. Then we have fitted a performing diagnostic function taking into account the criticality criteria from the ISO 10816 norm that is currently used as the only indicative reference for general rotational machine maintenance. Additionally, we have checked the validity of these analysis outputs with the dismantlement and visual inspection of some blowers. Our purpose is to develop a new schedule for the maintenance actions Alexandre Trilla et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. as we can now better determine the condition and predict the failure of a blower ahead of time, thus increasing the detection effectiveness of degraded blowers. We believe that an adequate maintenance of traction motor blowers with a remote predictive approach based on intelligent wireless sensors may increase the availability and reliability of the trains, and thus make the rail transport service more appealing.
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.