Health Index for Power Transformer Condition Assessment: A Comparison of Three Different Techniques.

Main Article Content

Diego Armando Zaldivar, Mr.
https://orcid.org/0000-0002-9287-1027
Andres Arturo Romero, Mr.
http://orcid.org/0000-0002-6530-852X

Abstract

In practice, the condition state of Power Transformers (PT) is quantified by using Health Index (HI). This paper
analyzes and compares three different state-of-the-art algorithms to compute HI. The first one uses a Weighted Sum
Model (WSM), the second is based on a Fuzzy Inference System (FIS), and the third combines both techniques, i.e.,
WSM and FIS. These three approaches are tested in a PT fleet composed of 30 units. Results show that each
approach produces different HI values for the same PTs. Therefore, decision making regarding the PT fleet will
depend on the selected approach for HI calculation. This work proposes merging the knowledge involved in each
analyzed approach by using a K-means clustering technique to overcome this drawback. This solution could help the
asset manager to make adequate decisions regarding the maintenance scheduling of PT when there is uncertainty
about the appropriate approach to be selected.

 

PLUM ANALYTICS

Article Details

How to Cite
Zaldivar, D., & Romero, A. (2022). Health Index for Power Transformer Condition Assessment: A Comparison of Three Different Techniques. Journal of Applied Research and Technology, 20(5), 536-545. https://doi.org/10.22201/icat.24486736e.2022.20.5.1606
Author Biographies

Diego Armando Zaldivar, Mr., Universidad Nacional de San Juan

Faculty  of Engineering, Instituto de Energia Electrica (IEE), Master's Student.

Andres Arturo Romero, Mr., Universidad Nacional de San Juan

Researcher at the Consejo Nacional de Investigaciones Científicas y Técnicas,
CONICET, at the IEE UNSJ-CONICET