•  
  •  
 

Keywords

transformer fault diagnosis, neighborhood rough set, improved particle swarm algorithm, extreme learning machine

Abstract

The accuracy of the intelligent transformer fault diagnosis method based on the DGA data is easily affected by the input characteristics, and the parametersof the extreme learning machine model is difficult to select. Thus, a transformer fault diagnosis method based on the neighborhood rough set and the adaptive mutation particle swarm extreme learning machine algorithm is proposed. Firstly, the initial feature set of transformer faults is established based on the various DGA fault diagnosis standards, and the key feature indicators with higherimportance according to the neighborhood rough set analysis.Secondly, when optimizing the parameters of the extreme learning machine on the basis ofthe particle swarm algorithm, it is easy to be premature and fall into the local maximum. Hence, an improved particle swarm optimization algorithm with premature self-check mutation mechanism is proposed.Finally, through a case study, the proposed methodis compared with the IEC three-ratio method and the different combinations of extreme learning machines,which verifies that the better diagnosis accuracy of the proposed method.

DOI

10.19781/j.issn.1673-9140.2022.03.019

First Page

157

Last Page

164

Share

COinS