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.

An experimental investigation is conducted to measure and correlate the impact of the water content on the electrical characteristics of the mineral oil for transformers, particularly the breakdown voltage, the resistivity, and the dielectric dissipation factor. Regression method is carried out to compare the results obtained through laboratory experiments with those predicted using an analytical model. A treatment to reduce water content in oil involving filtration, degassing and dehydration using a SESCO mobile station was applied to the new, regenerated, and used oil samples in service. The breakdown voltage, the resistivity, and the dielectric dissipation factor of the samples were measured. Regression analysis using an exponential model was applied to examine the samples electrical properties. The results show that, after treatment, the breakdown voltage and resistivity increase as the water content decreases, unlike the dielectric dissipation factor which exhibits a decreasing trend. This trend is found to be similar for the three oil samples: new, regenerated, and used. The results of the regression analysis give close agreement with the experimental results for all the samples and all studied characteristics. The model shows strong correlation with high coefficients (>90%).

In modern power systems, power transformers are considered vital components that can ensure the grid’s continuous operation. In this regard, studying the breakdown in the transformer becomes necessary, especially its insulating system. Hence, in this study, Box–Behnken design (BBD) was used to introduce a prediction model of the breakdown voltage (VBD) for the transformer insulating oil in the presence of different barrier effects for point/plane gap arrangement with alternating current (AC) voltage. Interestingly, the BBD reduces the required number of experiments and their costs to examine the barrier parameter effect on the existing insulating oil VBD. The investigated variables were the barrier location in the gap space (a/d)%, the relative permittivity of the barrier materials (ε_r), the hole radius in the barrier (hr), the barrier thickness (th), and the barrier inclined angle (θ). Then, only 46 experiment runs are required to build the BBD model for the five barrier variables. The BBD prediction model was verified based on the statistical study and some other experiment runs. Results explained the influence of the inclined angle of the barrier and its thickness on the VBD. The obtained results indicated that the designed BBD model provides less than a 5% residual percentage between the measured and predicted VBD. The findings illustrated the high accuracy and robustness of the proposed insulating oil breakdown voltage predictive model linked with diverse barrier effects.