Developing a new transformer fault diagnosis system through evolutionary fuzzy logic

Yann Chang Huang, Hong Tzer Yang, Ching Lien Huang

Research output: Contribution to journalArticle

165 Citations (Scopus)

Abstract

To improve the diagnosis accuracy of the conventional dissolved gas analysis (DGA) approaches, this paper proposes an evolutionary programming (EP) based fuzzy system development technique to identify the incipient faults of the power transformers. Using the IEC/IEEE DGA criteria as references, a preliminary framework of the fuzzy diagnosis system is first built. Based on previous dissolved gas test records and their actual fault types, the proposed EP-based development technique is then employed to automatically modify the fuzzy if-then rules and simultaneously adjust the corresponding membership functions. In comparison to results of the conventional DGA and the artificial neural networks (ANN) classification methods, the proposed method has been verified to possess superior performance both in developing the diagnosis system and in identifying the practical transformer fault cases.

Original languageEnglish
Pages (from-to)761-767
Number of pages7
JournalIEEE Transactions on Power Delivery
Volume12
Issue number2
DOIs
Publication statusPublished - 1997 Dec 1

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Developing a new transformer fault diagnosis system through evolutionary fuzzy logic'. Together they form a unique fingerprint.

Cite this