Research

Application of self-organising map algorithm for analysis and interpretation of dissolved gases in power transformers


Reference:

Thang, K. F., Aggarwal, R. K., McGrail, A. J. and Esp, D. G., 2001. Application of self-organising map algorithm for analysis and interpretation of dissolved gases in power transformers. In: Power Engineering Society Summer Meeting, 2001. IEEE, 2001-01-01.

Related documents:

This repository does not currently have the full-text of this item.
You may be able to access a copy if URLs are provided below.

Abstract

Onset of incipient faults in power transformers can degrade the mineral oil and cellulose insulation, leading to the formation of dissolved gases. The process from oil sampling to quantification of gases is known as dissolved gas analysis (DGA). Despite the availability of DGA interpretation schemes and artificial intelligence (AI) methods for transformer condition monitoring (CM) based on DGA data, it is pointed out in this paper that these approaches are less than ideal and practical in implementation. In view of that, this paper illustrates a novel approach for analysis and interpretation of DGA data, which leads to a more credible CM of power transformers. The proposed approach, which is based on the self-organising map (SOM) algorithm, has been validated using real fault-cases and thereby is proven to be more reliable in portraying the current condition of power transformers

Details

Item Type Conference or Workshop Items (Paper)
CreatorsThang, K. F., Aggarwal, R. K., McGrail, A. J. and Esp, D. G.
Uncontrolled Keywordsmineral oil, self-organising map algorithm, dissolved gases formation, insulation testing, cellulose insulation, power transformers incipient faults detection, power engineering computing, self-organising feature maps, power transformer testing, power transformer insulation, artificial intelligence, fault diagnosis, condition monitoring, transformer condition monitoring, electric breakdown, dissolved gas analysis, computerised monitoring
DepartmentsFaculty of Engineering & Design > Electronic & Electrical Engineering
RefereedNo
StatusPublished
ID Code6127

Export

Actions (login required)

View Item