article · IEEE Transactions on Dielectrics and Electrical Insulation
Power transformers are critical components of electrical transmission and distribution networks, requiring reliable condition monitoring to detect and classify early faults. Dissolved gas analysis is a proven diagnostic tool for this purpose, with current interpretation techniques split between traditional rules and intelligent computational methods. A two-step hybrid approach has been developed that combines evolutionary k-means clustering, driven by a genetic algorithm, with human expertise to form and analyse data subsets. In this framework, an operational sample is first matched to an identified subset before a dedicated diagnostic sub-model is used to determine its condition. The model was trained using 595 data samples, tested on 254 samples, and verified using the International Electrotechnical Commission TC10 benchmark database. It achieved an overall diagnostic accuracy of 98.29 per cent, outperforming several standard ratio and graphical assessment techniques.
Faults in electrical power transformers can lead to catastrophic grid failures and costly disruptions. Reliable dissolved gas analysis helps utility operators detect internal damage before critical breakdowns occur. By combining automated clustering with expert human knowledge, this hybrid technique significantly increases diagnostic accuracy, offering network managers more dependable insights into equipment health and maintenance needs.
This technique applies directly to condition monitoring and asset maintenance software used by electrical transmission and distribution network operators. It represents an applied, tested algorithmic model validated on standard industry benchmark datasets. Potential commercialisation pathways include integrating the hybrid algorithm into commercial transformer monitoring platforms or industrial diagnostic software tools to automate and improve early fault identification in high-voltage infrastructure.
AI-generated from the published abstract. Always read the original work before citing.
Considered as the heart of electrical power transmission and distribution networks, power transformers are essential part of the electricity transmission grid. Among the condition monitoring and fault diagnosis tools for these machines, dissolved gas analysis (DGA) has proven its effectiveness in their early detection and classification of faults. Up to date, many methods have been proposed in the literature for the interpretation of DGA data, classified into traditional and intelligent methods. This article proposes a two-step hybrid method, which uses the strengths of both methods. The approach uses the evolutionary <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula> -means clustering algorithm (k-MCA) based on the genetic algorithm (GA) for subset formation and subset analysis by human expertise. In the diagnostic procedure, to determine the condition of a sample, the subset to which it belongs is first identified and then the corresponding diagnostic sub-model is applied. The proposed method has been implemented with 595 DGA data, tested on 254 DGA data, and validated on the International Electrotechnical Commission (IEC) TC10 database. Their performances were evaluated and compared with existing traditional, intelligent, and hybrid methods. From the results obtained with the IEC TC10 database, the newly proposed approach depicts the best overall diagnosis accuracies. Indeed, the best performance is achieved with the proposed method compared to other models in the literature, with diagnostic accuracy of 98.29% compared to 88.89% of the Gouda triangle method, to 88.03% of the Hyosun Corporation gas ratio method, or to 86.32% of the three ratios technique.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/tdei.2023.3275119
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
