Picture of a black hole

Strathclyde Open Access research that creates ripples...

The Strathprints institutional repository is a digital archive of University of Strathclyde's Open Access research outputs. Strathprints provides access to thousands of research papers by University of Strathclyde researchers, including by Strathclyde physicists involved in observing gravitational waves and black hole mergers as part of the Laser Interferometer Gravitational-Wave Observatory (LIGO) - but also other internationally significant research from the Department of Physics. Discover why Strathclyde's physics research is making ripples...

Strathprints also exposes world leading research from the Faculties of Science, Engineering, Humanities & Social Sciences, and from the Strathclyde Business School.

Discover more...

Self-tuning diagnosis of routine alarms in rotating plant items

Costello, Jason and West, Graeme and Mcarthur, Stephen and Campbell, Graeme (2011) Self-tuning diagnosis of routine alarms in rotating plant items. In: The Eighth International Conference on Condition Monitoring and Machinery Failure Prevention Technologies, 2011-06-20 - 2011-06-22.

[img] PDF
BINDT_2011.pdf - Preprint

Download (708kB)

Abstract

Condition monitoring of rotating plant items in the energy generation industry is often achieved through examination of vibration signals. Engineers use this data to monitor the operation of turbine generators, gas circulators and other key plant assets. A common approach in such monitoring is to trigger an alarm when a vibration deviates from a predefined envelope of normal operation. This limit-based approach, however, generates a large volume of alarms not indicative of system damage or concern, such as operational transients that result in temporary increases in vibration. In the nuclear generation context, all alarms on rotating plant assets must be analysed and subjected to auditable review. The analysis of these alarms is often undertaken manually, on a case- by-case basis, but recent developments in monitoring research have brought forward the use of intelligent systems techniques to automate parts of this process. A knowledge- based system (KBS) has been developed to automatically analyse routine alarms, where the underlying cause can be attributed to observable operational changes. The initialisation and ongoing calibration of such systems, however, is a problem, as normal machine state is not uniform throughout asset life due to maintenance procedures and the wear of components. In addition, different machines will exhibit differing vibro- acoustic dynamics. This paper proposes a self-tuning knowledge-driven analysis system for routine alarm diagnosis across the key rotating plant items within the nuclear context common to the UK. Such a system has the ability to automatically infer the causes of routine alarms, and provide auditable reports to the engineering staff.