Ahmed Boubakeur

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.

This paper reports the results of an experimental study that examines the impact of thermal aging on the electrical and chemical properties of insulating oil used in power transformers. Transformer-oil samples were thermally aged over a 5000 h period at different temperatures varying between 80 °C and 140 °C, replicating both normal and extreme operating conditions. Measurements of breakdown voltage, dielectric dissipation factor, acidity, and water content were taken at 500 h intervals. A novel approach of this research is the integration of these electrical and chemical characteristics into a comprehensive exponential regression analysis model. The results indicate that breakdown voltage and resistivity decrease with aging time, whereas the dielectric dissipation factor, acidity, and water content increase with aging time. The degradation trends computed by the proposed model show close correlation with both electrical and chemical properties, with correlation coefficients generally equal to or exceeding 90%, which demonstrates its reliability in predicting aging behavior of transformer oil. This integrated approach offers valuable insights into the combined electrical and chemical degradation processes due to thermal aging and assists in the condition assessment of power transformers.

The effect of thermal aging on the electrical properties of the insulating oil used for transformers has been explored in this experimental work. In particular the dielectric dissipation factor, the resistivity and the breakdown voltage have been measured and correlated. The numerical results predicted by mathematical model and those measured in the laboratory have been compared by using a regression analysis. Experiments on thermal aging were performed on insulating oil (Borak 22, Nynas, Austria) during a period of time of 5000-h at three different temperatures. First, the transformer oil’s dielectric dissipation factor, the resistivity and the breakdown voltage are measured after every 500 h of aging. Then, polynomial and exponential regression expressions are proposed for modelling the oil’s electrical parameters variations with thermal ageing at different aging temperatures and periods. The results show that after thermal aging, the resistivity and the breakdown voltage decrease with thermal aging, however, the dielectric dissipation factor which increases. This trend is similar for all different aging temperatures. The numerical results show close agreement with the measured results for all the samples and all studied properties. The regression model presents strong correlation with high coefficients (>94%).

The effect of isothermal conditions on the trapping/detrapping process of charges in e-beam irradiated thermally aged XLPE insulation in scanning electron microscopy (SEM) has been investigated. Different isothermal conditions ranging from room temperature to 120 °C are applied on both unaged and aged XLPE samples (2 mm thick) by a suitable arrangement associated with SEM. For each applied test temperature, leakage, and influence currents have been measured simultaneously during and after e-beam irradiation. Experimental results show a big difference between the fresh and aged material regarding trapping and detrapping behavior. It has been pointed out that in the unaged material deep traps govern the process, whereas the shallow traps take part in the aged one. Almost all obtained results reveal that the trapped charge decreases and then increases as the temperature increases for the unaged sample. A deflection temperature corresponding to a minimum is observed at 50 °C. However, for the aged material, the maximum trapped charge decreases continuously with increasing temperature, and the material seems to trap fewer charges under e-beam irradiation at high temperature. Furthermore, thermal aging leads to the occurrence of detrapping process at high temperatures even under e-beam irradiation, which explains the decrease with time evolution of trapped charge during this period. The recorded leakage current increases with increasing temperature for both cases with pronounced values for aged material. The effect of temperature and thermal aging on electrostatic influence factor (K) and total secondary electron emission yield (σ) were also studied.

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.

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.

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 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.