Exploiting the Feature Space Structures of KNN and OPF Algorithms for Identification of Incipient Faults in Power Transformers
Authors:
- André GifalliAGAndré Gifalli
- Marco Akio IkeshojiMIMarco Akio Ikeshoji
- Danilo Sinkiti GastaldelloDGDanilo Sinkiti Gastaldello
- Victor Hideki Saito YamaguchiVYVictor Hideki Saito Yamaguchi
- Welson BassiWBWelson Bassi
- Talita MazonTMTalita Mazon
- Floriano Torres NetoFloriano Torres Neto
- Pedro da Costa JuniorPJPedro da Costa Junior
- André Nunes de SouzaASAndré Nunes de Souza
Open Access
- 18 September 2025
- journal article
- research article
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 7 (3) , 102
Abstract
Power transformers represent critical assets within the electrical power system, and their unexpected failures may result in substantial financial losses for both utilities and consumers. Dissolved Gas Analysis (DGA) is a well-established diagnostic method extensively employed to detect incipient faults in power transformers. Although several conventional and machine learning techniques have been applied to DGA, most of them focus only on fault classification and lack the capability to provide predictive scenarios that would enable proactive maintenance planning. In this context, the present study introduces a novel approach to DGA interpretation, which highlights the trends and progression of faults by exploring the feature space through the algorithms k-Nearest Neighbors (KNN) and Optimum-Path Forest (OPF). To improve accuracy, the following strategies were implemented: statistical filtering based on normal distribution to eliminate outliers from the dataset; augmentation of gas-related features; and feature selection using optimization algorithms such as Cuckoo Search and Genetic Algorithms. The approach was validated using data from several transformers, with fault diagnoses cross-checked against inspection reports provided by the utility company. The findings indicate that the proposed method offers valuable insights into the progression, proximity, and classification of faults with satisfactory accuracy, thereby supporting its recommendation as a complementary tool for diagnosing incipient transformer faults.Keywords
Funding Information
- São Paulo State University (UNESP), Brazil
This publication has 25 references indexed in Scilit:
- An interpretable machine learning method for fault diagnosis of oil-immersed transformers based on edge inferenceInternational Journal of Electrical Power & Energy Systems, 2025
- Machine learning based multi-method interpretation to enhance dissolved gas analysis for power transformer fault diagnosisHeliyon, 2024
- Conventional methods of dissolved gas analysis using oil-immersed power transformer for fault diagnosis: A reviewElectric Power Systems Research, 2022
- Fault Prediction of Transformer Using Machine Learning and DGA2020
- IEEE Guide for the Interpretation of Gases Generated in Mineral Oil-Immersed Transformers2019
- A novel extended binary cuckoo search algorithm for feature selection2017
- A comparison between k-Optimum Path Forest and k-Nearest Neighbors supervised classifiersPattern Recognition Letters, 2014
- Cuckoo search: recent advances and applicationsNeural Computing and Applications, 2013
- Supervised pattern classification based on optimum‐path forestInternational Journal of Imaging Systems and Technology, 2009
- Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databasesIEEE Electrical Insulation Magazine, 2001