An artificial neural network approach to transformer fault diagnosis

被引：292

作者：

Zhang, Y ^{[1
]}

Ding, X ^{[1
]}

Liu, Y ^{[1
]}

Griffin, PJ ^{[1
]}

机构：

[1] DOBLE ENGN CO,WATERTOWN,MA 02172

来源：

IEEE TRANSACTIONS ON POWER DELIVERY | 1996年 / 11卷 / 04期

基金：

美国国家科学基金会;

关键词：

artificial neural network; dissolved gas analysis (DGA); fault detection and diagnosis; transformers;

D O I：

10.1109/61.544265

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper presents an artificial neural network (ANN) approach to diagnose and detect faults in oil-filled power transformers based on dissolved gas-in-oil analysis. A two-step ANN method is used to detect faults with or without cellulose involved. Good diagnosis accuracy is obtained with the proposed approach.

引用

页码：1836 / 1841

页数：6

共 8 条

[1]

BHATTACHARYYA SK, 1993, NEURAL NETWORK APPRO

[2]

DING X, 1993, PREDICTING POWER TRA

[3]

Griffin P. J., 1988, STP998 AM SOC TEST M, P89

[4]

GRIFFIN PJ, 1995, DOUBL CLIENT C P

[5]

HALSTEAD WD, 1973, J I PETROL, V59, P239

[6]

LIN CE, 1993, 57 AM POW C APR CHIC, V8

[7]

Pao YH, 1989, ADAPTIVE PATTERN REC

[8] IEEE AND IEC CODES TO INTERPRET INCIPIENT FAULTS IN TRANSFORMERS, USING GAS IN OIL ANALYSIS [J].

ROGERS, RR .

IEEE TRANSACTIONS ON ELECTRICAL INSULATION, 1978, 13 (05) :349-354

← 1 →