Practical applications of data mining in plant monitoring and diagnostics

Research output: Contribution to conferencePaper

13 Citations (Scopus)
324 Downloads (Pure)

Abstract

Using available expert knowledge in conjunction with a structured process of data mining, characteristics observed in captured condition monitoring data, representing characteristics of plant operation may be understood, explained and quantified. Knowledge and understanding of satisfactory and unsatisfactory plant condition can be gained and made explicit from the analysis of data observations and subsequently used to form the basis of condition assessment and diagnostic rules/models implemented in decision support systems supporting plant maintenance. This paper proposes a data mining method for the analysis of condition monitoring data, and demonstrates this method in its discovery of useful knowledge from trip coil data captured from a population of in-service distribution circuit breakers and empirical UHF data captured from laboratory experiments simulating partial discharge defects typically found in HV transformers. This discovered knowledge then forms the basis of two separate decision support systems for the condition assessment/defect clasification of these respective plant items.
Original languageEnglish
Pages1-7
Number of pages7
DOIs
Publication statusPublished - 28 Jun 2007
EventIEEE Power Engineering Society General Meeting 2007. - Tampa, United States
Duration: 24 Jun 200728 Jun 2007

Conference

ConferenceIEEE Power Engineering Society General Meeting 2007.
CountryUnited States
CityTampa
Period24/06/0728/06/07

Keywords

  • data mining
  • plant monitoring
  • plant operation
  • diagnostics
  • circuit breakers

Fingerprint Dive into the research topics of 'Practical applications of data mining in plant monitoring and diagnostics'. Together they form a unique fingerprint.

  • Cite this

    Strachan, S. M., Stephen, B., & McArthur, S. D. J. (2007). Practical applications of data mining in plant monitoring and diagnostics. 1-7. Paper presented at IEEE Power Engineering Society General Meeting 2007., Tampa, United States. https://doi.org/10.1109/PES.2007.385983