The reliability of electric power systems is largely determined by the insulation condition of electrical equipment. Insulation damage can lead to power losses, reduced service life of lines and devices, and emergency shutdowns, so insulation diagnostics is critical to prevent technological disruptions. However, traditional approaches to insulation monitoring are often labor-intensive and subjective. In this regard, the role of computer vision and deep learning methods, capable of automatically detecting insulation defects and thereby increasing the efficiency and objectivity of monitoring, is increasing. This study considers the application of modern architectures of deep convolutional neural networks for the problem of recognizing insulating elements of electrical equipment. Particular attention is paid to the comparative analysis of several state-of-the-art models. The considered architectures show effective results and provide deep multi-scale analysis of scene features based on convolutional networks. In this paper, the models are used in conjunction with image augmentation algorithms. Data augmentation allows you to artificially expand limited sets of training images through various transformations, which is especially important for a small dataset. The application of these methods is aimed at improving the quality of training data and reducing the risk of overfitting models, as well as overcoming the imbalance of classes in the sample by generating additional fault samples. The proposed approach includes conducting a sequential comparative experiment on a small and limited set of image data from power facilities. A comparison was made of the accuracy and completeness metrics of various neural network architectures when combining various augmentation strategies in order to identify a combination of models and data augmentation methods that provide the highest recognition accuracy. The results of the study will help determine the most effective augmentation models and techniques suitable for real-life operating conditions at power facilities, taking into account complex backgrounds, variable lighting, and different angles of equipment shooting. Identifying such optimal solutions based on deep learning is intended to improve the reliability and efficiency of automated insulation monitoring in the power industry.

Keywords: computer vision, convolutional neural networks, isolation, defect, data augmentation, machine learning, energy, automation of image analysis

The results of a study of induction wireless charging methods for batteries of unmanned aerial vehicles (UAVs) are presented. An experimental simulation of energy transfer using inductive coupling has been carried out. The main factors influencing the efficiency of the system are determined: the distance between the coils, the accuracy of their alignment, and heat losses. It is shown that energy losses with increasing distance reach 45%, and when the coils are shifted by 3 cm, the transmission efficiency decreases by more than 45%. Recommendations have been developed to improve efficiency, including optimizing coil materials, increasing the frequency of energy transmission, automating coil alignment, and introducing active cooling. The results obtained form the basis for further improvement of UAV wireless charging systems.

Keywords: wireless energy transmission, induction methods, resonant induction, unmanned aerial vehicles, optimization of charging systems

One of the causes of local overheating of submersible electric motor caused by the presence of a significant variation of electromagnetic parameters of rotor packages (RP) in the assembly of submersible electric motor is investigated in this paper. Due to the presence in the assembly of RPs with an active resistance much lower than the average resistance of the assembly, the electrical losses in RPs with resistance higher than the average increase, respectively, their heat generation increases. With the help of statistical analysis methods, the distribution of electromagnetic parameters as a two-dimensional random variable was investigated, the "convolution" of the two-dimensional distribution law was constructed. The analysis of the "convolution" of the two-dimensional law of distribution of electromagnetic parameters of the RP showed that there is a high probability of a significant scatter of parameters of the RP in the assembly.

Keywords: submersible electrical motor, rotor package, statistical analysis, local overheating, interrepair period

The article proposes a method for determining the optimal location of a self-supporting fiber-optic cable laid along the supports of high-voltage power transmission lines. The methodology is focused on the use of both a manual calculation method and with the use of electronic computing equipment.

Keywords: fiber-optic communication line, electric field, induced voltage potential, electrothermal degradation, optimization of placement of self-supporting fiber-optic cable

In the work, a method was implemented that allowed estimating the parameters of a control object based on the objective function, the least squares method, and the solution to the system of nonlinear equations was the Levenberg-Marquardt method. The numerical and laboratory experiments carried out allow us to speak about the effectiveness of the proposed method.

Keywords: identification, optimization, least squares method, Levenberg-Marquardt method, differential equation

The article raises the issue of maintaining the stability of the power system, including maintaining the balance of electric power. The occurrence of power imbalance can be determined by a criterion such as frequency. The authors have proposed a method of maintaining frequency including maintaining power balance in the power system by changing voltage on electric energy consumers, a hypothesis has been set and a corresponding laboratory study has been carried out, as a result of which dependence of frequency change on voltage of some electric power receivers has been obtained. A device an automatic unloading regulation of voltage has been developed and described, which will make it possible to supplement the existing emergency control equipment.

Keywords: renewable energy sources, grid inverters, mode parameters, Clark conversions, Park conversions

The article discusses the features of the use and applicability of identification of parameters of the equivalent circuit of an submersible electric motors. The possibilities of technical implementation with a given accuracy are evaluated for definition the parameters of submersible electric motors substitution circuits under various external influences, as well as when designing submersible electric motors as an integral part of the electro-technical complex of electrical submersible pump units.

Keywords: submersible electric motor, electrical submersible pump unit, identification of parameters of the equivalent circuit of an asynchronous electric machine, mathematic simulation, crude oil production