New Dissolved Gas Analysis Diagnostics Framework for Substation Transformers using Random Forest Algorithm and IEEE C57.104 – 2019TM Guide

View Full Paper

Ask AI

Bookmark

The new framework achieved 100% accuracy in diagnosing transformer health with dissolved gas analysis.
Compared to traditional methods, it outperformed Duval triangle and IEC ratio methods, which had accuracies of 98.92% and 28.32% respectively.
Analysis utilized 277 datasets from different parts of the Philippines, ensuring diverse data representation for the model.
Random forest algorithm demonstrated the highest efficacy, with a cross-validation score averaging 89.14% compared to other machine learning methods.

Discussion

No takes yet. Share an insight, caveat, or question.

Framework improves diagnostics accuracy for transformers using dissolved gas analysis, highlighting random forest algorithm effectiveness.

Tan et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

Framework improves diagnostics accuracy for transformers using dissolved gas analysis, highlighting random forest algorithm effectiveness.