article · IET Nanodielectrics
Early and accurate diagnosis of incipient faults is essential for the safe and efficient operation of mineral oil-immersed power transformers. Dissolved gas analysis serves as a standard preventive maintenance tool for condition monitoring, fault identification, and avoiding unplanned outages. Although artificial intelligence methods offer high diagnostic accuracy, their complexity and poor reproducibility limit practical utility. Traditional analysis methods remain favoured by maintenance professionals because they are simple, transparent, and easy to apply in field environments. Newer iterations of these conventional techniques have overcome early limitations, demonstrating greater diagnostic capability. A review of these traditional methods highlights pathways for performance improvement alongside critical pitfalls that must be addressed to ensure reliable and efficient fault detection.
Power transformers are vital components of electrical grids, and their failure can cause widespread blackouts. Early detection of internal faults prevents catastrophic breakdowns and expensive repairs. While cutting-edge computer models exist, dependable, easy-to-use diagnostic tools remain essential for engineers responsible for maintaining daily grid reliability and preventing costly operational disruptions.
The findings apply directly to condition monitoring and preventive maintenance routines for electrical grid operators and transformer maintenance professionals. Because the underlying traditional dissolved gas analysis methods are already established and widely deployed in industry, improvements and guidance from this review can be applied to current maintenance practices, requiring no extensive development of complex artificial intelligence infrastructure.
AI-generated from the published abstract. Always read the original work before citing.
Abstract A key factor in ensuring the efficient and safe operation of power transformers is the early and accurate diagnosis of incipient faults. Among the tools available to achieve this goal, dissolved gas analysis (DGA) is widely used by power transformers' maintenance professionals. It is a preventive maintenance tool, used for condition monitoring, fault diagnosis and unplanned outage prevention. With the development of artificial intelligence (AI), many intelligent‐based methods using AI tools have been proposed in the literature for DGA data interpretation. Although these methods achieve high diagnostic accuracies and improve DGA efficiency, they are generally complicated and the research documented in these publications is difficult to replicate. Traditional DGA‐based methods are simple, easy to understand and implement, and widely used by power transformers' maintenance professionals. Many methods proposed in recent years overcome the limitations of the pioneer methods and are increasingly effective. The authors present a detailed and comprehensive literature review of the traditional DGA‐based methods for mineral oil‐immersed power transformer faults diagnosis. This review also addresses ways to improve the efficiency of the available traditional methods. Some pitfalls that need to be taken into account to improve the efficiency of the DGA‐based diagnostic methods are also presented.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1049/nde2.12082
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.
