Abstract
Early detection of faults within high voltage power generation equipment reduces the need for unplanned system downtime and loss of consumer supply. Continuous on-line condition monitoring of high voltage electrical generation equipment produces a large amount of surveillance data from connected instruments, challenges lie in being able to make sense of the data as it arrives to detect emerging faults within the equipment. With the emergence of the Industrial Internet of Things (IIOT) more is being expected of instruments in terms of intelligence and analytical capabilities. This paper presents a method for embedding the necessary analytical intelligence required for automatic fault detection in surveillance devices, through a connection to a distributed hybrid cloud platform. This platform can leverage industry recognised open-source technologies for data storage and processing. These techniques directly harness the increased computational power of the cloud platform and provide a level of data aggregation and analysis that would not have been possible in the instrument alone. The deployed system is currently capturing and analysing live surveillance data produced by a number of high voltage generator sets within a major UK power station.
Original language | English |
---|---|
Title of host publication | Proceedings: The 22nd IEEE International Conference on Computational Science and Engineering, The 17th IEEE International Conference on Embedded and Ubiquitous Computing |
Editors | Meikang Qiu |
Publisher | IEEE |
Pages | 283-288 |
Number of pages | 6 |
ISBN (Electronic) | 9781728116648 |
ISBN (Print) | 9781728116655 |
DOIs | |
Publication status | Published - 5 Dec 2019 |
Keywords
- Cloud Computing
- Data Analytics
- Data Visualisation
- Electro-Magnetic Interference
- On line Condition Monitoring