Abnormality Detection Methods for Utility Equipment Condition Monitoring

  • Author / Creator
    Li, Benzhe
  • The wide spread use of power quality monitoring tools in recent years has enabled utility companies to extract non-power-quality information from the power quality monitoring data. A high potential use of such data is the equipment condition monitoring. General purpose detection method for waveform abnormality is considered as an important step for data analytics based equipment condition monitoring. Two general purpose detection methods are proposed in this thesis. The first one is a modified detection method based on existing scheme, where segment RMS values of differential waveform and half-cycle refreshed RMS values of original waveform are used as features for the detection. The second method is based on statistical characteristics of current signals, where abnormalities are detected by comparing the statistical distributions of waveform variations with and without disturbances. Current waveform is used for the detection since they are more sensitive to equipment conditions than voltage waveform. An automatic threshold selection scheme is adopted in the detection method. In addition, as hard binary detection can sometimes lead to large error especially for boundary situations, a soft detection scheme is proposed which returns soft detection results. The soft detection scheme can reduce the number of missing events compared with binary detection methods. Moreover, the detection value provides reference for severity of a certain abnormal event.

  • Subjects / Keywords
  • Graduation date
    Fall 2016
  • Type of Item
  • Degree
    Master of Science
  • DOI
  • License
    This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.