Early Warning of Incipient Faults for Power Transformer Based on DGA Using a Two-Stage Feature Extraction Technique

Yang ZHANG, Hong Cai CHEN*, Yaping DU, Min CHEN, Jie LIANG, Jianhong LI, Xiqing FAN, Ling SUN, Qingsha S. CHENG, Xin YAO

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

2 Citations (Scopus)

Abstract

Early warning for transformer faults is valuable for maintenance decision-making. However, limited work has been done in this area due to the difficulty of the model establishment. This paper proposes a two-stage feature extraction method for early warning of power transformer faults, where a novel feature extraction process is applied by combining feature ranking and genetic programming (GP). In the first stage, the data is labeled as normal and fault states and the feature extraction is evaluated on the data. Then, extracted key features and their growth rates are relabeled as normal and warning states, after which the feature extraction process is re-evaluated on the relabeled data. Obtained features and logic expression can finally be used for early warning. The proposed framework can implement an early warning with about 100 days in advance for transformer faults and is verified through 8 sequences of data. The comparisons with two recently reported methods show the superiority of the proposed method.

Original languageEnglish
Pages (from-to)2040-2049
Number of pages10
JournalIEEE Transactions on Power Delivery
Volume37
Issue number3
DOIs
Publication statusPublished - Jun 2022
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 1986-2012 IEEE.

Keywords

  • Dissolved gas analysis
  • early warning
  • feature extraction
  • genetic programming
  • transformer diagnosis

Fingerprint

Dive into the research topics of 'Early Warning of Incipient Faults for Power Transformer Based on DGA Using a Two-Stage Feature Extraction Technique'. Together they form a unique fingerprint.

Cite this