Dissolved gas analysis (DGA) is the standard technique to diagnose the fault types of oil-immersed power transformers. Various traditional DGA methods have been employed to detect the transformer faults, but their accuracies were mostly poor. In this light, the current work aims to improve the diagnostic accuracy of power transformer faults using artificial intelligence. A KNN algorithm is combined with the decision tree principle as an improved DGA diagnostic tool. A total of 501 dataset samples are used to train and test the proposed model. Based on the number of correct detections, the neighbor's number and distance type of the KNN algorithm are optimized in order to improve the classifier's accuracy rate. For each fault, indeed, several input vectors are assessed to select the most appropriate one for the classifier's corresponding layer, increasing the overall diagnostic accuracy. On the basis of the accuracy rate obtained by knots and type of defect, two models are proposed where their results are compared and discussed. It is found that the global accuracy rate exceeds 93% for the power transformer diagnosis, demonstrating the effectiveness of the proposed technique. An independent database is employed as a complimentary validation phase of the proposed research.

The main objective of the current work was to enhance the transformer fault diagnostic accuracy based on dissolved gas analysis (DGA) data with a proposed coupled system of support vector machine (SVM)-bat algorithm (BA) and Gaussian classifiers. Six electrical and thermal fault classes were categorized based on the IEC and IEEE standard rules. The concentration of five main combustible gases (hydrogen, methane, ethane, ethylene, and acetylene) was utilized as an input vector of the two classifiers. Two types of input vectors have been tested; the first input type considered the five gases in ppm, and the second input type considered the gases introduced in the percentage of the sum of the five gases. An extensive database of 481 had been used for training and testing phases (321 data samples for training and 160 data samples for testing). The SVM model conditioning parameter “λ” and penalty margin parameter “C” were adjusted through the bat algorithm to develop a maximum accuracy rate. The SVM-BA and Gaussian classifiers’ accuracy was evaluated and compared with several DGA techniques in the literature.

The electric field distribution is one of the main factors governing the long-term reliability of high voltage composite insulators. However, under severe pollution conditions, electric field stresses, when exceeding thresholds and applying for long periods, could lead to degradation and deterioration of the housing materials and, therefore, to failures of the composite insulators. This paper is intended to improve the distributions of the electric field and potential by minimizing the corona ring on a 400 kV AC transmission line composite insulator. The performances of three powerful multi-objective meta-heuristic algorithms, namely Ant Lion Optimizer (MOALO), Particle Swarm Optimizer (MOPSO), and non-dominated sorting genetic algorithm (NSGA-II) are established to achieve this goal. First, variations of electrical fields on the critical parts of the string are obtained using three-dimensional finite element method (FEM) software. Then, three objective functions are developed to establish the relationships between the electric field and the guard ring parameters. Finally, the optimization parameters consist of diameter, tube diameter, and installation height of the corona ring. The obtained results confirm the effectiveness of the three algorithms; the MOLAO is the better in terms of computing time and solution quality.

This paper deals with the detection and classification of two types of lamination faults (i.e., edge burr and lamination insulation faults) in a three-phase transformer core. Previous experimental results are exploited, which are obtained by employing a 15 kVA transformer under healthy and faulty conditions. Different test conditions are considered such as the flux density, number of the affected laminations and fault location. Indeed, the current signals are used where four features (Average, Fundamental, THD and STD) are extracted. Elaborating A total of 328 samples, these features are utilized as input vectors to train and test classification models based on SVM, KNN and DT algorithms. Based on the selected features, the results confirm that the transformer current can be used for the detection of lamination faults. An accuracy rate of more than 84% is obtained using three different classifiers. Such findings provide a promising step toward fault detection and classification in electrical transformers, helping to prevent the system and avoid other related issues such as the increase of power loss and temperature.

In this paper, a Support Vector Machine (SVM) and the k nearest neighbor (KNN) classifiers are employed to diagnose the power transformer oil insulation using dissolved gas analysis (DGA). Different vectors are used as inputs for classifiers to achieve a maximum accuracy rate. The five input vectors that are considered: DGA in ppm, DGA in percentage, Dörnenberg ratios, Rogers ratios and Duval triangle reports. Concerning the classes of faults, five types are adopted as output of classifiers (PD, D1, D2, T1&T2 and T3). In order to perform a better fault classification, The SVM parameters have been optimized with a Particle Swarm Optimization (PSO). Using Duval triangle reports, the PSO-SVM algorithm provides the highest accuracy rate than the KNN algorithm one.

Power transformers, as oil-immersed equipment, are primarily diagnosed using dissolved gas analysis (DGA), a widely recognized and effective fault detection method. Over time, numerous approaches have been developed to identify transformer faults through DGA, with many incorporating artificial intelligence to enhance diagnostic accuracy. In this context, this study enhances the support vector machine and k-nearest neighbors algorithms by integrating them into the iterative processes of the artificial bee colony and crow search algorithms for fault identification. Chaos theory was embedded into the optimization framework to improve convergence and avoid local optima. Nine input vectors, derived from a dataset of 501 samples covering six fault types, were used to evaluate the enhanced algorithms. An improved binary crow search algorithm was employed to optimize the input vectors, effectively identifying the key features for fault diagnosis. The proposed enhancement achieved an accuracy exceeding 94%, demonstrating the potential of refined methodologies for practical transformer diagnostics.