DescriptionThis 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.
|Event title||7th International Conference on Smart City and Informatization|
|Organisers||Guangzhou University, Central South University China|
|Degree of Recognition||International|
Documents & Links
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review