A hybrid algorithm based on neural-fuzzy system for interpretation of dissolved gas analysis in power transformers

College

Gokongwei College of Engineering

Department/Unit

Manufacturing Engineering and Management

Document Type

Conference Proceeding

Source Title

IEEE Region 10 Annual International Conference, Proceedings/TENCON

Publication Date

12-1-2012

Abstract

Dissolved gas analysis (DGA) is a well-known method for diagnosis of incipient faults in power transformers. Some traditional criteria of the dissolved gas analysis are published in standards and technical reports which are still in use in many electrical utilities around the world. This paper describes a hybrid algorithm using neural-fuzzy system for incipient fault detection in power transformers. In order to reach a higher degree of reliability with respect to each technique individually, the proposed method is based on the combined use of six standardized criteria. Six neural networks are trained based on randomly generated data considering the individual standards and the results are mixed to give the better results. The proposed method is tested using realistic data. The experiments results showed that the proposed algorithm is accurate, reliable and robust in identifying incipient faults in power transformers. © 2012 IEEE.

html

Digitial Object Identifier (DOI)

10.1109/TENCON.2012.6412171

Upload File

wf_yes

This document is currently not available here.

Share

COinS