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.

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 paper proposes a two-steps hybrid method, which uses the strengths of both methods. The approach uses the evolutionary k-means clustering algorithm based on the genetic algorithm 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.

In this contribution, a new dissolved gas analysis (DGA) method combining key gases and ratio approaches for power transformer fault diagnostic is presented. It is based on studying subsets and uses the five main hydrocarbon gases including hydrogen (H ₂ ), methane (CH ₄ ), ethane (C ₂ H ₆ ), ethylene (C ₂ H ₄ ), and acetylene (C ₂ H ₂ ). The proposed method uses 475 samples from the dataset divided into subsets formed from the maximum and minimum(s) concentrations of the whole dataset. It has been tested on 117 DGA sample data and validated on the International Electrotechnical Commission (IEC) TC10 database. The performance of the proposed diagnostic method was evaluated and compared with the following diagnostic methods: IEC ratios method, Duval's triangle (DT), three ratios technique (TRT), Gouda's triangle (GT), and self‐organizing map (SOM) clusters. The results found were analysed by computer simulations using MATLAB software. The proposed method has a diagnosis accuracy of 97.42% for fault types, as compared to 93.16% of TRT, 96.58% of GT method, 97.25% of SOM clusters method and 98.29% of DT method. However, in terms of fault severity, the proposed method has a diagnostic accuracy of 90.59% as compared to 78.90% of SOM clusters method, 83.76% of TRT, 88.03% of DT method, and 89.74% of GT method.

This contribution presents a two‐step hybrid diagnostic approach, combining k ‐means clustering for subset formation, followed by subset analysis conducted by human experts. As the feature input vector has a significant influence on the performance of unsupervised machine learning algorithms, seven feature input vectors derived from traditional methods, including Duval pentagon method, Rogers ratio method, three ratios technique, Denkyoken method, ensemble gas characteristics method, Duval triangle method, and Gouda triangle method were explored for the subset formation stage. The seven proposed individual methods, corresponding to the seven feature input vectors, were implemented using a dataset of 595 DGA samples and tested on an additional 254 DGA samples. Furthermore, a combined technique based on a support vector machine was introduced, utilising the diagnostic results of the individual methods as input features. From training and testing, with diagnostic outcomes of 91.09% and 90.94%, the combined technique demonstrated the highest overall diagnostic accuracies. Using the IEC TC10 database, the diagnosis accuracies of the proposed diagnostic methods were compared to existing methods of literature. From the results obtained, the combined technique outperformed the proposed individual methods and existing methods used for comparison.

Dissolved Gas Analysis (DGA) in oil is one of the most common and reliable techniques for diagnosing and early detection of incipient faults in oil-immersed transformers. However, conventional methods often encounter conflicts and challenges in accurately interpreting DGA results. Addressing this, two novel graphical methods, Circle Method 1 and Circle Method 2, are proposed, represented by circles with movable axes at variable angles. These methods innovatively base their analysis on the convergence of samples with similar characteristics around their centers and the spacing of these centers for samples with differing characteristics. The primary purpose of these methods is to distinguish between different overlapping faults. To achieve this, advanced metaheuristic algorithms are employed to determine the optimal angles that yield the best distribution of samples. Utilizing insights from previous DGA methods and field experiences, initial fault zones within Circle Methods 1 and 2 are estimated, and precise boundaries between fault zones are established based on practical DGA data collected from multiple sources. Evaluation using IEC TC10 database of fault cases demonstrates that Circle Methods 1 and 2 exhibit superior diagnostic accuracy compared to existing methods, including the Mansour Pentagon, the Duval Pentagon, the Gouda Triangle, and the Cartesian Graphical Method. This innovation significantly enhances the interpretative capabilities of DGA, offering a more reliable tool for fault diagnosis in oil-immersed transformers.