Adaptive fuzzy diagnosis system for dissolved gas analysis of power transformers

Hong-Tzer Yang, C. C. Liao

研究成果: Article

摘要

To enhance the fault diagnosis abilities for the dissolved gas analysis (DGA) of the power transformers, this paper proposes a novel adaptive fuzzy system for the incipient fault recognition through evolution enhanced design approach. Complying with the practical gas records and associated fault causes as much as possible, a fuzzy reasoning algorithm is presented to establish a preliminary fuzzy diagnosis system. In the system, an evolutionary optimization algorithm is further relied on to fine-tune the membership functions of the if-then inference rules. To make the diagnosis system intensively compact and the inference process more understandable, a pruning scheme is then developed to filter out the insignificant or redundant rules. The capabilities of the proposed diagnosis system for the transformer DGA decision support have been extensively verified through the practical test data collected from Taiwan Power Company (TPC).

原文English
頁數1
期刊IEEE Power Engineering Review
19
發行號3
出版狀態Published - 1999

指紋

Gas fuel analysis
Power transformers
Fuzzy systems
Membership functions
Failure analysis
Gases
Industry

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

引用此文

@article{1d4bcc0baf6345c48e6e6133c1f72156,
title = "Adaptive fuzzy diagnosis system for dissolved gas analysis of power transformers",
abstract = "To enhance the fault diagnosis abilities for the dissolved gas analysis (DGA) of the power transformers, this paper proposes a novel adaptive fuzzy system for the incipient fault recognition through evolution enhanced design approach. Complying with the practical gas records and associated fault causes as much as possible, a fuzzy reasoning algorithm is presented to establish a preliminary fuzzy diagnosis system. In the system, an evolutionary optimization algorithm is further relied on to fine-tune the membership functions of the if-then inference rules. To make the diagnosis system intensively compact and the inference process more understandable, a pruning scheme is then developed to filter out the insignificant or redundant rules. The capabilities of the proposed diagnosis system for the transformer DGA decision support have been extensively verified through the practical test data collected from Taiwan Power Company (TPC).",
author = "Hong-Tzer Yang and Liao, {C. C.}",
year = "1999",
language = "English",
volume = "19",
journal = "IEEE Power Engineering Review",
issn = "0272-1724",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Adaptive fuzzy diagnosis system for dissolved gas analysis of power transformers

AU - Yang, Hong-Tzer

AU - Liao, C. C.

PY - 1999

Y1 - 1999

N2 - To enhance the fault diagnosis abilities for the dissolved gas analysis (DGA) of the power transformers, this paper proposes a novel adaptive fuzzy system for the incipient fault recognition through evolution enhanced design approach. Complying with the practical gas records and associated fault causes as much as possible, a fuzzy reasoning algorithm is presented to establish a preliminary fuzzy diagnosis system. In the system, an evolutionary optimization algorithm is further relied on to fine-tune the membership functions of the if-then inference rules. To make the diagnosis system intensively compact and the inference process more understandable, a pruning scheme is then developed to filter out the insignificant or redundant rules. The capabilities of the proposed diagnosis system for the transformer DGA decision support have been extensively verified through the practical test data collected from Taiwan Power Company (TPC).

AB - To enhance the fault diagnosis abilities for the dissolved gas analysis (DGA) of the power transformers, this paper proposes a novel adaptive fuzzy system for the incipient fault recognition through evolution enhanced design approach. Complying with the practical gas records and associated fault causes as much as possible, a fuzzy reasoning algorithm is presented to establish a preliminary fuzzy diagnosis system. In the system, an evolutionary optimization algorithm is further relied on to fine-tune the membership functions of the if-then inference rules. To make the diagnosis system intensively compact and the inference process more understandable, a pruning scheme is then developed to filter out the insignificant or redundant rules. The capabilities of the proposed diagnosis system for the transformer DGA decision support have been extensively verified through the practical test data collected from Taiwan Power Company (TPC).

UR - http://www.scopus.com/inward/record.url?scp=33747348999&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33747348999&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:33747348999

VL - 19

JO - IEEE Power Engineering Review

JF - IEEE Power Engineering Review

SN - 0272-1724

IS - 3

ER -