Work

Towards Automated Frequency Response Analysis of Power Transformers with Deep Learning

Year: 2025

Type: article

Abstract: Frequency response analysis (FRA) has emerged as one of the standard techniques for monitoring the integrity of the mechanical structure of power transformer windings. Interpreting FRA test results, though, is still largely dependent on expert identification of graphical features. Machine learning, however, presents an opportunity to automate and improve this feature identification process. In this study, FRA measurements were simulated and then image and series data representations were used to train three neural networks. The Xception network, trained with image magnitude data, obtained the best performance, with an F1 score of 98.6%. The ResNet and Fully Connected Neural Network, trained with series magnitude data, obtained F1 scores of 94.6% and 91.4%, respectively. Results revealed that networks trained using image-encoded FRA data outperformed those trained using series FRA data.

Source: Applied Artificial Intelligence

DOI: 10.1080/08839514.2025.2479223

Authors: Micah Phillip, Arvind Singh, Craig J. Ramlal

Institutions: University of the West Indies, University of the West Indies, University of the West Indies

Language: English

Topic: Power Transformer Diagnostics and Insulation

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $2,195