Pattern Recognition Techniques for Power Transformer Insulation Diagnosis - A Comparative Study Part 2: Implementation, Case Study, and Statistical Analysis
Article
Article Title | Pattern Recognition Techniques for Power Transformer Insulation Diagnosis - A Comparative Study Part 2: Implementation, Case Study, and Statistical Analysis |
---|---|
ERA Journal ID | 36582 |
Article Category | Article |
Authors | Cui, Yi (Author), Ma, Hui (Author) and Saha, Tapan (Author) |
Journal Title | International Transactions on Electrical Energy System |
Journal Citation | 25 (10), pp. 2260-2274 |
Number of Pages | 15 |
Year | 2014 |
Publisher | John Wiley & Sons |
Place of Publication | United Kingdom |
ISSN | 1430-144X |
1546-3109 | |
2050-7038 | |
Digital Object Identifier (DOI) | https://doi.org/10.1002/etep.1963 |
Web Address (URL) | https://onlinelibrary.wiley.com/doi/10.1002/etep.1963 |
Abstract | Transformer oil tests such as breakdown voltage, resistivity, dielectric dissipation factor, water content, 2-furfuraldehyde, acidity, and different dissolved gasses have been adopted in utility companies for evaluating the conditions of transformer insulation. Over the past 20 years, various pattern recognition techniques have been applied for power transformer insulation diagnosis using oil tests results (oil characteristics). This paper investigates a variety of state-of-the-art pattern recognition algorithms for transformer insulation diagnosis. To verify the applicability and generalization capability of different pattern recognition algorithms, this paper implements 15 representative algorithms and conducts extensive case studies on eight oil characteristics datasets collected from different utility companies. A statistical performance (in terms of classification accuracy) comparison among different pattern recognition algorithms for transformer insulation diagnosis using oil characteristics is also conducted in the paper. Copyright © 2014 John Wiley & Sons, Ltd. |
Keywords | dissolved gas analysis; insulation; oil characteristics; pattern recognition; power transformer |
ANZSRC Field of Research 2020 | 400803. Electrical energy generation (incl. renewables, excl. photovoltaics) |
460308. Pattern recognition | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | University of Queensland |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q7w4v/pattern-recognition-techniques-for-power-transformer-insulation-diagnosis-a-comparative-study-part-2-implementation-case-study-and-statistical-analysis
41
total views0
total downloads2
views this month0
downloads this month