DocumentCode
404972
Title
A neural network approach to power transformer fault diagnosis
Author
Yang, Fu ; Xi, Jin ; Zhida, Lan
Author_Institution
Dept. of Electr. Power Eng., Shanghai Inst. of Electr. Power, China
Volume
1
fYear
2003
fDate
9-11 Nov. 2003
Firstpage
351
Abstract
Diagnosis of power transformer abnormality is important for power system reliability. This paper introduces the dissolved gas-in-oil analysis (DGA) according to the characteristic of transformer fault diagnosis, based on fuzzy set theory and adaptive genetic algorithm, a neural network model for transformer fault diagnosis is built by using modular back-propagation (BP). The results of training and testing show that the method is effective and available.
Keywords
backpropagation; fault diagnosis; fuzzy set theory; genetic algorithms; neural nets; power engineering computing; power system reliability; power transformers; adaptive genetic algorithm; dissolved gas-in-oil analysis; fuzzy set theory; modular back-propagation; neural network; power system reliability; power transformer fault diagnosis; Algorithm design and analysis; Dissolved gas analysis; Fault diagnosis; Fuzzy set theory; Genetic algorithms; Neural networks; Power system modeling; Power system reliability; Power transformers; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Electrical Machines and Systems, 2003. ICEMS 2003. Sixth International Conference on
Conference_Location
Beijing, China
Print_ISBN
7-5062-6210-X
Type
conf
Filename
1273885
Link To Document