International Conference on Computer and Knowledge Engineering

Home / 13th International Conference on Computer and Knowledge Engineering

A New Application of Machine Learning Based Methods for Disk Space Variation Fault Diagnosis in Transformer Windings

Authors :

Reza Behkam¹ Amir Lotfi² Gevork B. Gharehpetian³

1- Amirkabir university of technology 2- University of Waterloo 3- Amirkabir university of technology

Keywords :

Power transformer،disk space variation (DSV)،machine learning (ML)،frequency response analysis (FRA)،classification

Abstract :

Frequency response analysis (FRA) is an excellent technique to identify mechanical defects in power transformer windings. In this research, disk space variation (DSV), one of the most prevalent transformer winding faults, is considered on a 1.6 MVA distribution transformer with 20 kV windings in different locations, with various severities, and the corresponding FRA results are measured and computed. All four frequency response components (amplitude, phase, real, and imaginary) are explored in this study's dataset. The constructed dataset is utilized to predict DSV faults using trained Decision Tree, Random Forest, SVM Linear, SVM Polynomial, and XGBoost. The applied new machine learning (ML) approaches for interpreting FRA results are used to extract essential features from frequency response traces in order to detect the position and intensity of DSV in the transformer windings. The experimental results confirm the effectiveness of the proposed intelligent methods, which can predict fault location and extent with 93.5% and 100% accuracy in validation and test datasets, respectively.