Railway Point-Operating Machine Fault Detection Using Unlabeled Signaling Sensor Data
| Autor: | Paul Allen, Phil Lane, Pritesh Mistry |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Computer science
railway point-operating machines condition monitoring Real-time computing 02 engineering and technology lcsh:Chemical technology Fault (power engineering) 01 natural sciences Biochemistry Article Fault detection and isolation turnout Analytical Chemistry Smart city 0202 electrical engineering electronic engineering information engineering lcsh:TP1-1185 Electrical and Electronic Engineering signal processing Instrumentation Signal processing unlabeled data 020208 electrical & electronic engineering 010401 analytical chemistry SIGNAL (programming language) Condition monitoring fast Fourier transform Atomic and Molecular Physics and Optics fault detection 0104 chemical sciences Identification (information) smart sensors |
| Zdroj: | Sensors Volume 20 Issue 9 Sensors, Vol 20, Iss 2692, p 2692 (2020) Sensors (Basel, Switzerland) |
| ISSN: | 1424-8220 |
| DOI: | 10.3390/s20092692 |
| Popis: | In this study, we propose a methodology for the identification of potential fault occurrences of railway point-operating machines, using unlabeled signal sensor data. Data supplied by Network Rail, UK, is processed using a fast Fourier transform signal processing approach, coupled with the mean and max current levels to identify potential faults in point-operating machines. The method developed can dynamically adapt to the behavioral characteristics of individual point-operating machines, thereby providing bespoke condition monitoring capabilities in situ and in real time. The work described in this paper is not unique to railway point-operating machines, rather the data pre-processing and methodology is readily applicable to any motorized device fitted with current sensing capabilities. The novelty of our approach is that it does not require pre-labelled data with historical fault occurrences and therefore closely resembles problems of the real world, with application for smart city infrastructure. Lastly, we demonstrate the problems faced with handling such data and the capability of our methodology to dynamically adapt to diverse data presentations. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |