Self-tuning routine alarm analysis of vibration signals in steam turbine generators

Jason Costello, Graeme West, Stephen McArthur, Graeme Campbell

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)
167 Downloads (Pure)


This paper presents a self-tuning framework for knowledge-based diagnosis of routine alarms in steam turbine generators. The techniques provide a novel basis for initialising and updating time series feature extraction parameters used in the automated decision support of vibration events due to operational transients. The data-driven nature of the algorithms allows for machine specific characteristics of individual turbines to be learned and reasoned about. The paper provides a case study illustrating the routine alarm paradigm and the applicability of systems using such techniques.
Original languageEnglish
Pages (from-to)731-740
Number of pages10
JournalIEEE Transactions on Reliability
Issue number3
Publication statusPublished - Sept 2012


  • knowledge based systems
  • nuclear power generation
  • self-tuning
  • time series analysis


Dive into the research topics of 'Self-tuning routine alarm analysis of vibration signals in steam turbine generators'. Together they form a unique fingerprint.

Cite this