Condition Monitoring of Motorised Devices for Smart Infrastructure Capabilities
This paper presents a signal processing methodology based on fast Fourier transform for the early fault detection of electrically motorised devices. We used time-stamped, current draw data provided by Network Rail, UK, to develop a methodology that may identify imminent faults in point machine operations. In this paper we describe the data, preprocessing steps and methodology developed that can be used with similar motorised devices as a means of identifying potential fault occurrences. The novelty of our method is that it does not rely on labelled data for fault detection. This method could be integrated into smart city infrastructure and deployed to provide automated asset maintenance management capabilities.
KeywordsCondition monitoring Fault detection Point machines Fast Fourier transform Smart city
- 2.Bian, C., et al.: Degradation detection method for railway point machines. arXiv preprint arXiv:1809.02349 (2018)
- 6.Knime (2018). https://www.knime.com/. Accessed 2 Aug 2018
- 7.Barrionuevo, J.M., Berrone, P., Ricart, J.: Smart cities, sustainable progress: opportunities for urban development. IESE Insight 50–57 (2012). https://doi.org/10.15581/002.ART-2152
- 10.R (2018). https://www.r-project.org/. Accessed 2 Aug 2018