Open AccessA Fault Diagnosis System of Power Transformers Using Acoustic Characteristics and Neural Network
Author(s) -
Mingxin Geng,
Chuang Fan,
Kun Wang,
Zhang Xiao,
Zhijun Yang
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/782/3/032098
Subject(s) - transformer , electric power system , power transmission , artificial neural network , distribution transformer , overheating (electricity) , engineering , electrical engineering , automotive engineering , voltage , computer science , reliability engineering , electronic engineering , power (physics) , physics , quantum mechanics , machine learning
As one of the most important facilities in the power system, power transformers undertake the crucial tasks of voltage transformation, power distribution and transmission. In the process of operation, the power transformers may have discharges, overheating, insulation degradation, winding and core loosing, solid pollution of insulation oil and some other faults. In order to address the aforementioned issues, a novel fault diagnosis system for power transformer is proposed. Through using the acoustic characteristics of the power transformer and establishing the model of the neural network, the proposed system is demonstrated with high accuracy in the experiment.