Learning models of plant behavior for anomaly detection and condition monitoring

A.J. Brown, V.M. Catterson, M. Fox, D. Long, S.D.J. McArthur

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)
155 Downloads (Pure)


Providing engineers and asset managers with a too] which can diagnose faults within transformers can greatly assist decision making on such issues as maintenance, performance and safety. However, the onus has always been on personnel to accurately decide how serious a problem is and how urgently maintenance is required. In dealing with the large volumes of data involved, it is possible that faults may not be noticed until serious damage has occurred. This paper proposes the integration of a newly developed anomaly detection technique with an existing diagnosis system. By learning a Hidden Markov Model of healthy transformer behavior, unexpected operation, such as when a fault develops, can be flagged for attention. Faults can then be diagnosed using the existing system and maintenance scheduled as required, all at a much earlier stage than would previously have been possible.
Original languageEnglish
Pages (from-to)61-67
Number of pages7
JournalEngineering Intelligent Systems for Electrical Engineering and Communications
Issue number2
Publication statusPublished - Jun 2007


  • cooperative systems
  • decision support systems
  • Hidden Markov models
  • intelligent systems
  • learning systems
  • monitoring
  • partial discharges
  • power systems
  • power transformers


Dive into the research topics of 'Learning models of plant behavior for anomaly detection and condition monitoring'. Together they form a unique fingerprint.

Cite this