About this document
Transformer Failure Classification Improvement by Parth Vyas is a document available to read on EtoBox.
This study explores improving transformer failure classification by addressing imbalanced dissolved gas analysis (DGA) data using various data-level balancing techniques. The research found that the combination of Edited Nearest Neighbors (ENN) with Support Vector Machine (SVM) yielded the best classification performance, achieving 88% accuracy. The findings suggest that data-level techniques can significantly enhance transformer fault diagnosis, paving the way for future research to optimize these methods.
- Author
- Parth Vyas
- Language
- EN