An inter-turn short circuit (ITSC) in a power transformer winding is a primary cause of transformer failure. Existing methods for ITSC identification have limitations when applied in field conditions. To address this issue, a mobile hardware–software system for identifying electrical equipment parameters (PAK IP-10) has been developed, based on analyzing the decay of a direct current pulse. Verification of the test results for reproducibility, using Cochran’s criterion, demonstrated that the developed PAK IP-10 can be recommended for identifying the presence or absence of inter-turn short circuits in transformer windings.
Keywords: power transformer, inter-turn short circuit, identification, direct current decay test, Cochran’s criterion
This article presents the technical implementation of a convolutional nueral network-based face recognition system that is able to work under variable scenarios like occlusion, angle changes, and camera rotation. various face identification algorithms were analysed with the purpose of developing a model that could identify faces at different angles. The system was experimentally verified with various datasets and compared to its accuracy, processing speed, and robustness towards environmental disturbance. Results indicate that our convolutioan neural network structure optimized achieves 90%+ accuracy under pristine conditions and maintains decent performance upon partial occlusion.
Keywords: face detection, convolutional nueral networks, model, feature extraction, deep learning, face recognition, image
The use of machine learning when working with text documents significantly increases the efficiency of work and expands the range of tasks to be solved. The paper provides an analysis of the main methods of presenting data in a digital format and machine learning algorithms, and a conclusion is made about the optimal solution for generative and discriminative tasks.
Keywords: machine learning, natural language processing, transformer architecture models, gradient boosting, large language models
This study is a testament to the potential of convolutional neural networks in softmax activation to classify mantis, honey badger, and weasel samples. The model was able to predict highly with low misclassification and had the potential to reduce environmental variance by minimizing it using data augmentation. The research shows how deep learning networks would be used in the automation of taxonomic classification, which in turn would help species identification through images and large-scale conservation monitoring.
Keywords: deep learning, machine learning, convolutional neural networks, dataset, softmax function, image classification, wildlife, data augmentations
The paper considers the problem of classifying discharge and thermal defects in power transformers according to chromatographic analysis of dissolved gases, for which an expanded feature space has been formed based on concentrations of key gases and diagnostic ratios according to the International Electrotechnical Commission IEC 60599 standard. A comparison of various machine learning methods was carried out, among which the random forest algorithm showed the best results, which ensured maximum accuracy and stability of classification. The developed classifier complements the existing decision support system, providing automatic identification of the nature of defects based on chromatographic analysis of dissolved gases. The results of the study demonstrate the effectiveness of artificial intelligence methods in improving the reliability of transformer equipment diagnostics.
Keywords: power transformer, chromatographic analysis of dissolved gases, defect diagnostics, partial discharge, automated machine learning, ensemble methods, random forest, extra-trees
This article is devoted to the study of the possibilities of machine learning technology for forecasting the demand for goods. The study analyzes various models and the possibilities of their application as part of the task of predicting future sales. The greatest attention is focused on modern methods of time series analysis, in particular neural network and statistical approaches. The results obtained during the study clearly demonstrate the advantages and disadvantages of different models, the degree of influence of their parameters on the accuracy of the forecast within the framework of the demand forecasting task. The practical significance of the findings is determined by the possibility of using the results obtained in the analysis of a similar data set. The relevance of the study is due to the need for accurate forecasting of demand for goods to optimize inventory and reduce costs. The use of modern machine learning methods makes it possible to increase the accuracy of predictions, which is especially important in an unstable market and changing consumer demand.
Keywords: machine learning algorithms, demand estimation, forecasting accuracy, time sequence analysis, sales volume prediction, Python, autoregressive integrated moving average, random forest, gradient boosting, neural networks, long-term short-term memory
The article discusses machine learning methods, their application areas, limitations and application possibilities. Additionally highlighted achievements in deep learning, which allow obtaining accurate results with optimal time and effort. The promising architecture of neural networks of transformers is also described in detail. As an alternative approach, it is proposed to use a generative adversarial network in the process of converting a scan into elements of a digital information model.
Keywords: scanning, point cloud, information model, construction, objects, representation, neural network, machine learning
Modern web applications are becoming more complex and feature-rich, which creates the need for effective tools for dependency management, optimization, and project assembly. Buider allow you to optimize your code, which directly affects the download and execution speed of applications. The purpose of the work is to conduct a comparative analysis of JavaScript builders: Webpack, Parcel, and Rollup in order to identify their advantages and disadvantages from the point of view of frontend development ergonomics. This includes evaluating the convenience of configuration, resource efficiency, build speed, and other factors that affect developer productivity and the final quality of web applications. Practical testing of the builders was carried out using the example of a standard web project. The ergonomics of working with tools is evaluated: criteria are identified and a comparison is made based on the data obtained. Recommendations have been developed for choosing the optimal tool for various types of projects in front-end development. The research results can be used as a basis for training new specialists, as well as for improving existing practices in developing web applications when making informed decisions on the choice of technologies for long-term projects.
Keywords: web development, development efficiency, ergonomics, frontend development, testing, builder
This paper explores the content-based filtering approach in modern recommender systems, focusing on its key principles, implementation methods, and evaluation metrics. The study highlights the advantages of content-based systems in scenarios that require deep object analysis and user preference modeling, especially when there is a lack of data for collaborative filtering.
Keywords: сontent - oriented filtering, recommendation systems, feature extraction, similarity metrics, personalization
The paper is devoted to the problems of MicroGrid technology development, consisting in the construction of a distributed energy supply system based on autonomous energy generation sources. The objective of the paper is to construct models and procedures for decision support in multi-criteria selection of combined autonomous energy generation projects from a large number of possible alternatives. To achieve the objective, a morphological analysis of the subject area was carried out (using the method of systematic field coverage by F. Zwicky), as a result of which a space of alternatives of combined energy sources was constructed. A group ordering of criteria was carried out based on their expert assessment. Sequential application of the modified analytical network method using ordered groups of criteria made it possible to limit the number of criteria taken into account at each stage (by the number of criteria in a group) and consistently reduce the number of alternatives (considering only a few of the best alternatives of the previous stage). The proposed multi-stage procedure makes it possible to reduce (at each stage) the dimension of the supermatrix of the analytical network method and, thereby, reduce the time complexity of the procedure compared to the direct application of this method. The use of the proposed procedure makes it possible to consider a larger number of alternatives taking into account a larger number of criteria (compared to traditional methods of decision support), and, therefore, allows for an increase in the level of scientific validity of technical and economic decisions when designing MicroGrid systems
Keywords: MicroGrid, autonomous power system, decision support, analytical network method
This article presents a comprehensive analysis of Russian-language texts utilizing neural network models based on the Bidirectional Encoder Representations from Transformers (BERT) architecture. The study employs specialized models for the Russian language: RuBERT-tiny, RuBERT-tiny2, and RuBERT-base-cased. The proposed methodology encompasses morphological, syntactic, and semantic levels of analysis, integrating lemmatization, part-of-speech tagging, morphological feature identification, syntactic dependency parsing, semantic role labeling, and relation extraction. The application of BERT-family models achieves accuracy rates exceeding 98% for lemmatization, 97% for part-of-speech tagging and morphological feature identification, 96% for syntactic parsing, and 94% for semantic analysis. The method is suitable for tasks requiring deep text comprehension and can be optimized for processing large corpora.
Keywords: BERT, Russian-language texts, morphological analysis, syntactic analysis, semantic analysis, lemmatization, RuBERT, natural language processing, NLP
The paper considers the solution of the problem of synthesis of a multiconnected nonlinear system with polynomial and piecewise linear approximations. The generalized Galerkin method is used as a mathematical apparatus. The synthesis results and advantages of each of the approximations are presented.
Keywords: multivariable automatic control systems, parametric synthesis, nonlinear automatic control systems, generalized Galerkin method, polynomial approximation, piecewise-linear approximation, saturation, minimization, objective function, recurrent relations
The article presents a study of various approaches to implementing micro-frontend architecture in high-load web applications. It describes a comparative analysis of four main micro-frontend integration patterns: Module Federation, Single-SPA, Web Components, and iframe approach. An experimental performance study of each pattern was conducted, measuring key loading and interaction metrics
Keywords: micro-frontends, web architecture, Module Federation, Single-SPA, high-load systems, web application performance
Introduction: Mobile Gaming Addiction (MGA) has emerged as a significant public health concern, with the World Health Organization recognizing it as a gaming disorder. Russia, with its growing mobile gaming market, is no exception. Aims and Objectives: This study aims to explore the feasibility of using neural networks for early MGA detection and intervention, with a focus on the Russian context. The primary objective is to develop and evaluate a neural network-based model for identifying behavioral patterns associated with MGA. Methods: A proof of concept study was conducted, employing a simplified neural network architecture and a dataset of 101 observations. The model's performance was evaluated using standard metrics, including accuracy, precision, recall, F1-score, and AUC-ROC score. Results: The study demonstrated the potential of neural networks in detecting MGA, achieving an F1-score of 0.75. However, the relatively low AUC-ROC score (0.58) highlights the need for addressing dataset limitations. Conclusion: This study contributes to the growing body of literature on MGA, emphasizing the importance of considering regional nuances and addressing dataset limitations. The findings suggest promising avenues for future research, including dataset expansion, advanced neural architectures, and region-specific mobile applications.
Keywords: neural networks, neural network architectures, autoencoder, digital addiction, gaming addiction, digital technologies, machine learning, artificial intelligence, mobile game addiction, gaming disorder
The aim of this study was to detect synchronization between blood pressure variability (BPV) and the respiratory rhythm in healthy rats and rats with experimentally induced colitis during noxious (pain) stimulation. To this end, we used synchronization metrics based on instantaneous frequencies and phases estimated via the synchrosqueezed wavelet transform. We found that noxious stimulation promotes the emergence of synchronization between BPV and respiration. The adjustment of the BPV frequency to the respiratory frequency, followed by phase locking, indicates that the respiratory rhythm controls BPV prior to the onset of synchronization. The pathological condition associated with experimental colitis correlates with a reduction in the duration of phase synchronization.
Keywords: arterial blood pressure; respiratory activity; wavelet decomposition
The article focuses on the application of machine learning methods for predicting failures in industrial equipment. A review of modern approaches such as Random Forest, SVM, and XGBoost is presented, with emphasis on their accuracy, robustness, and suitability for engineering tasks. Based on the analysis of real-world data (temperature, pressure, vibration, humidity), models were trained and compared, with XGBoost demonstrating the best performance. Key parameters influencing failures were identified, and a recommendation system was proposed, combining statistical analysis and predictive modeling. The developed solution enables timely detection of failure risks and optimization of maintenance processes.
Keywords: machine learning, predictive modeling, equipment management, failure prediction, data analysis
For neural network algorithms to work successfully when processing 3D point clouds, it is necessary to provide a detailed point cloud of the external environment. A similar task arises when a manipulative robot is operating in a new environment, where before processing a cloud of scene points, it is necessary to obtain a detailed representation of the external environment using an RGB-D camera mounted on the end link of the robot. To solve this problem, this study proposes an algorithm for adaptive control of a manipulative robot to build a model of the external environment. By applying an adaptive approach, during the research of the external environment, the manipulative robot moves the RGB-D camera, taking into account the changes in the current environment model introduced by the previous RGB-D image. The results obtained allow us to judge the effectiveness of the proposed approach, showing that due to adaptability, it allows us to achieve high scene coverage rates.
Keywords: environment model, manipulative robot, adaptive control algorithm, surface reconstruction, RGB-D camera, visual information processing, TSDF volume
This paper examines methods for modeling the spread of infectious diseases. It discusses the features of the generalized compartmental approach to epidemic modeling, which divides the population into non-overlapping groups of individuals. The forecast of models built using this approach involves estimating the size of these groups over time. The paper proposes a method for estimating model parameters based on statistical data. It also introduces a method for estimating confidence intervals for the model forecast, based on a series of stochastic model runs. A computational experiment demonstrates the effectiveness of the proposed methods using data on the spread of influenza in European countries. The results show the model's efficiency in predicting the dynamics of the epidemic and estimating confidence intervals for the forecast. The paper also justifies the applicability of the described methods to modeling chronic diseases.
Keywords: epidemic modeling, computer modeling, compartmental models, SIR, stochastic modeling, parameter estimation, confidence interval, forecast, influenza
The paper presents a simulation of flight control of an unmanned aerial vehicle (UAV). A distributed control system is proposed that sequentially includes internal and external circuits to control the state of motion of the aircraft. The control efficiency of a cascade PD controller (proportional-differential) is higher than that of a traditional PID controller (proportional-integral-differentiating). A new cascade control algorithm with a PD controller is proposed. First, the dynamics of the UAV is modeled based on the Newton-Euler method, then the state of motion of the device is controlled by a distributed control system based on cascaded levels of proportional derivatives of the internal and external contours. The simulation results show that the controller, developed on the basis of proportional-derivative control speed of internal and external circuits, is able to achieve fast tracking of the position and orientation of the UAV in case of external disturbances and has good control quality. The developed algorithm has increased the control efficiency by 5-7% compared to the traditional PID algorithm.
Keywords: Unmanned Aerial Vehicle, PID controller, Cascade PD controller, Algorithm Optimization, UAV Control Algorithm
The article discusses the process of developing and modeling an impeller for an unmanned aircraft of the airplane type. Aerodynamic and strength calculations were carried out, key design parameters were determined, including the number of blades, engine power and choice of material. The developed models were created in the CAD system Compass 3D and manufactured by 3D printing using PETG plastic. Impeller thrust tests were carried out depending on engine speed, which allowed the design to be optimized for maximum efficiency.
Keywords: impeller, unmanned aircraft, aerodynamics, 3D modeling, 3D compass, additive technologies, thrust, testing, APM FEM
This article examines the issue of increasing the performance and scalability of transactional systems using the example of a sharded blockchain architecture. Particular attention is paid to the use of a search query—based approach, a model in which the user's transactional intentions are processed asynchronously and aggregatively. This allows you to significantly reduce the load on the network and achieve high throughput without compromising the user experience. The proposed architecture is based on fully controlled smart accounts, embedded wallets, and third-party processing of user search queries through a specialized module. As a result, scalability is achieved that meets the requirements of high-frequency trading and automated decentralized applications. Key performance metrics and application scenarios outside the financial sector are presented.
Keywords: blockchain, distributed ledger, transactional systems, distributed systems
Assessing the technical condition of equipment is an important task for ensuring operational strategy and planning maintenance work at an enterprise. One approach to evaluating equipment condition is the use of a well-known indicator called the 'technical condition index,' the calculation methodology for which has been approved by the Ministry of Energy of the Russian Federation. This methodology also proposes a scale for assessing the level of equipment technical condition. However, the question of the threshold or critical value of this indicator, which can determine the equipment's unsuitability for further operation, remains unresolved. This paper proposes a methodology for determining the threshold value of a modified technical condition index based on the allowable probability of failure-free operation of equipment using statistical methods. The novelty of the work lies in the proposed methodology for determining the threshold value of a modified technical condition index, developed by the author, which uses objective data for evaluation, unlike the subjective assessments of experts in existing methodologies. The proposed method was tested on a set of statistical data on the degradation of turbofan engines from NASA.
Keywords: technical condition index, modified technical condition index, threshold value, probability of equipment failure-free operation, complex technical object
The article proposes a scheme for the interaction of nodes in a secure data transmission network based on broadband wireless access equipment (BWAE). The variants of design and technological implementation of the BWAE are described, that is BWAE 7 equipment (with a seven-element antenna array) and BWAE 1 equipment (with one antenna device). For each option the composition of functionally complete devices and nodes is presented, the technical characteristics of the equipment are indicated. The functional description of components of the BWAE 7 and BWAE 1 equipment is provided.
Keywords: telecommunication equipment, information and monitoring network, wireless broadband access, data transmission, secure network
he article examines the configuration options for onboard communication equipment. Modeling and evaluation of antenna placement options onboard the unmanned aerial vehicle of helicopter type (UAV HT) are carried out taking into account the influence of design elements and payload on the antenna pattern, summary results of modeling the radiation patterns and analysis of losses due to the influence of design elements of the UAV HT with different antenna placements are presented. The loss budget is calculated for different combinations of ground and onboard equipment taking into account different ranges with a maximum altitude difference. Options for implementing a repeater based on the UAV HT are proposed.
Keywords: control system, unmanned repeater, onboard communication equipment, control channel, receiving and transmitting path
The combination of systems analysis and long-term planning is a crucial factor for ensuring sustainable development and enhancing the competitiveness of enterprises. In this context, the use of the Event Tree Analysis method plays a key role in assessing the achievement of strategic goals, tasks, and identifying potential risks. This study focuses on the development and application of an event tree to analyze various aspects of system operations, including goal setting, strategy development, and task execution. The application of the ETA method not only allows for modeling possible event scenarios but also enables the development of risk mitigation measures, contributing to long-term sustainability and successful system functioning.
Keywords: event tree, system analysis, strategic planning, risk management, threat minimization, sustainable development, enterprise competitiveness, quantitative analysis, qualitative analysis, dependent events, conditional probabilities, protective mechanisms