Online monitoring of transformer through stream clustering of partial discharge signals

Firuzi K., Vakilian M., Phung B. T., Blackburn T.

IET SCIENCE MEASUREMENT & TECHNOLOGY, vol.13, no.3, pp.409-415, 2019 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 13 Issue: 3
  • Publication Date: 2019
  • Doi Number: 10.1049/iet-smt.2018.5389
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.409-415
  • Keywords: partial discharges, corona, power transformer insulation, condition monitoring, condition monitoring, medium-voltage power system equipment, power transformer, high-voltage power system equipment, online real-time monitoring, partial discharge, DenStream method, Density Grids method, multisource discharge signal, internal discharge, surface discharge, corona discharge source, stream clustering algorithms, active sources, multiple defects, phase-resolved discharge patterns, PATTERN-RECOGNITION, SEPARATION
  • Middle East Technical University Affiliated: No


The general method for identifying the partial discharge type in a power transformer is based on their fingerprints in the form of phase-resolved discharge patterns. In the case of multiple defects, traditional clustering methods can be applied for separation of active sources. However, such an approach is impractical for online real-time monitoring due to the very large data size. In this paper a new method using stream clustering is introduced. The method separates the active sources by processing the signal once it is captured, then only a synopsis of the discharge data is stored. Two stream clustering algorithms: Density Grids and DenStream are employed. Through measurements obtained from laboratory experimental setups (corona, surface discharge, transformer defect model) performance of the proposed algorithms are evaluated. It is shown that stream clustering method is able to separate the constituent components involved in the stream of a multi-source discharge signal without the need to store a large amount of information. The performance of the Density Grids method depends on a limited number of features that it can accommodate. In comparison, the DenStream method can capture more features which enable better separation of active sources at the expense of longer processing time.