Image noise reduction is an important task in the field of computer vision and image processing. Traditional noise filtering methods may be limited by their ability to preserve image details. The purpose of this work is to study and apply deep learning methods to reduce noise in images. The main tasks of noise reduction in images are the removal of Gaussian noise, salt and pepper noise, noise of lines and stripes, noise caused by compression, and noise caused by equipment defects. In this paper, such noises as the removal of raindrops, dust, and traces of snow on the images were considered. In the work, complex patterns and high noise density were studied. A deep learning algorithm, such as the decomposition method with and without preprocessing, and their effectiveness in applying noise reduction are considered. It is expected that the results of the study will confirm the effectiveness of deep learning methods in reducing noise in images. This may lead to the development of more accurate and versatile image processing methods capable of preserving details and improving the visual quality of images in various fields, including medicine, photography, and video.

This paper investigates the problems of increasing the efficiency of technological installations of oil refineries, which produce high-octane and environmentally friendly motor fuels. We used methods of mathematical modeling and fuzzy mathematics to maximize the volume of gasoline produced and improve its quality indicators, taking into account the imposed restrictions. On the basis of a systematic approach, an effective methodology is created for the development of a package of models of interconnected plant units using available information of a different nature, including fuzzy information. The resulting package of models makes it possible to systematically simulate the work of the unit under study and to increase the efficiency of the facility by increasing the volume of manufactured target products and improving its quality indicators. There are presented results of the analysis and expert assessment of the catalytic reforming unit LG-35-11/300-95 and the choice of the optimal type of model for individual units. A scheme is being created for combining the developed models into a single package of models. On the basis of the proposed methodology, hybrid models are being developed that make it possible to determine the volume of produced catalyzate and its quality indicators.

This work is dedicated to the analysis and development of an integrated production system that combines wells and surface facilities to select the optimal operating mode for equipment. The main focus is on studying data analysis methods, as well as collecting and processing information, which ensures high accuracy in process control and optimal use of technological capabilities. The integration of data from various levels of the production chain, from the well to the surface facilities, opens up new opportunities for optimizing equipment performance and improving resource management quality. Integration of wells and surface facilities – The effective integration of wells and surface facilities is crucial for optimizing production processes, minimizing operational costs, and reducing environmental impact. Integrated management systems allow the automation of many processes, providing continuous monitoring of operating parameters, automatic adjustment of settings, and supplying data for quick decision-making. This includes real-time data collection, analysis, and the use of the obtained information to select optimal operating modes, which helps improve both overall efficiency and safety in production processes. In the modern oil and gas industry, the efficient use of equipment at all stages of hydrocarbon production is of particular importance. Optimizing the operation of wells and surface facilities is a key aspect for increasing economic efficiency and reducing environmental impact. In this regard, the development and application of integrated systems that enable real-time control and adaptation of equipment operating modes has become a relevant and significant task.

This study presents the adaptive three-expert ensemble (A3E), a reproducible framework for joint one-hour-ahead solar and wind power forecasting. A3E combines temporal, physically informed, and high-generation Extra Trees experts through a causal local-error gate and is evaluated under a strictly chronological, leakage-free protocol. After timestamp reconciliation and causal feature construction, the primary source yielded 8,700 model-ready observations: 5,775 for training, 1,463 for validation, 719 for internal testing, and 743 for a same-source December holdout. The primary scale-neutral comparison used Macro train-SD normalized root mean square error (NRMSE) on 672 common forecast origins. A3E achieved 0.1978, compared with 0.2314 for the official photovoltaic (PV)-Client 2026 comparator and 0.2340 for TimeMixer. However, validation-optimized static weights achieved 0.2017 on the complete 719-origin internal test, compared with 0.2025 for adaptive A3E; the difference was not statistically significant under dependence-aware analysis. On the independent CISO and ERCO systems, TimeMixer outperformed A3E, demonstrating source-dependent model rankings. Event evaluation used 98 CISO and 320 ERCO high-generation events. The results support the value of heterogeneous expert integration, but not a universal accuracy advantage of adaptive weighting.

The demand for high-quality sulfur that is used in medicine, chemistry, and other industries is growing. The technological processes for extracting sulfur from harmful acid gases in oil refining are characterized by complex, nonlinear, and fuzzy relationships between input and output parameters, complicating the development of their models. Therefore, solving the problems of modeling and optimizing sulfur production processes under uncertainty, as they occur in sulfur recovery units (SRUs), is a highly relevant scientific and practical task. To address these issues, we propose a method for synthesizing a neuro-fuzzy model for assessing the integrated quality and volume of sulfur, enabling the development of a highly adequate model under fuzzy conditions. The developed hybrid model, based on the proposed method, is trained on historical data and adapts its fuzzy rules, enabling the modeling of complex nonlinear, fuzzy relationships between the input and output parameters of sulfur production processes. An ANFIS architecture for a neuro-fuzzy model for assessing the quality and volume of sulfur from the reactor outlet of the Atyrau refinery SRU was developed. A fuzzy Pareto optimization method was proposed, which, based on the developed neuro-fuzzy model, enables vector optimization of sulfur production processes, taking into account the constraints, and determines a Pareto-optimal solution in a fuzzy environment. The best solution selected by the decision-maker from the Pareto set, depending on the current situation, ensures a balance between the sulfur volume and its integrated quality. As a result of multi-criteria optimization of sulfur production processes at the Atyrau refinery SRU based on the proposed methods, the volume of high-quality sulfur increased by 7.39%, hydrogen by 10.71%, and energy consumption decreased by 80 kW/h, demonstrating the effectiveness of the proposed methods.

Интеллектуальный анализ кадровых данных становится всё более актуальным в условиях цифровизации процессов управления персоналом и необходимости обработки как структурированных, так и неструктурированных источников информации. Современные подходы требуют внедрения реше-ний, способных эффективно обрабатывать табличные данные и одновременно извлекать смысл из текстовых описаний сотрудников. Однако в большинстве существующих систем отсутствует единая архитектура, сочетающая возможно-сти OLAP-анализа, кластеризации и семантического поиска в рамках локально исполняемой аналитической среды. Целью настоящего исследования является разработка локальной аналитической подсистемы, ориентированной на ком-плексный анализ сведений о сотрудниках организации с использованием встра-иваемой OLAP-СУБД DuckDB и векторной базы данных ChromaDB. В рамках поставленной цели были реализованы задачи по предобработке данных, агре-гации с использованием SQL-запросов, кластеризации сотрудников методом K-средних, векторизации текстовых описаний и внедрению семантического по-иска на основе модели all-MiniLM-L6-v2. В результате был создан программныйпрототип, позволяющий проводить как количественный, так и смысловой ана-лиз кадровых данных. Система продемонстрировала высокую производитель-ность при локальном исполнении, возможность быстрой сегментации персона-ла и реализацию поиска по естественно-языковым запросам без подключенияк внешним сервисам. Дополнительно обеспечена визуализация результатов вBI-среде Yandex DataLens. Предложенное решение обладает высокой степеньювоспроизводимости и может быть адаптировано к задачам внутреннего HR-а-нализа, систем поддержки принятия решений и информационно-аналитическихплатформ. Результаты исследования подтверждают перспективность объедине-ния OLAP- и векторных технологий в рамках единой локальной архитектурыдля интеллектуальной обработки кадровой информации.