Volume 06,Issue 03

Apply the Artificial Neural Network to Diagnose Potential Fault of Power Transformer Based on Dissolved Gas-in-oil Analysis Data

Authors

Nguyen Tien Duy


Abstract
This paper presents the development of a potential fault diagnosis system of power transformers by an artificial neural network (ANN) based on the gas components of dissolved gas-in-oil analysis (DGA) data. The input of the ANN is five components H2, C2H4, CH4, C2H2, C2H6. The outputs are 3 major conclusions about the condition of the transformer including “normal”, “overheating” and “discharging”. Using Multi-Layer Perception network (MLP) with a selected network structure of 5-16-3. Through testing with actual DGA data, the results show that the diagnostic system makes conclusions that are reliable.

Keyword: Diagnostic system, Power transformer, Potential fault, Artificial neural network, Dissolved Gas-in-oil Analysis.

PDF [ 338.72 Kb ] | Endnote File | XML

CRPASE: TRANSACTIONS of



Follow Us

Google Scholar   Academia

JOURNAL IMPRINT