ЕлАр ХНУРЕ:: Головна

ISSN: 2310-8061

Репозиторій Харківського національного університету радіоелектроніки «ElAr КhNURE» є електронною платформою, що містить публікації наукових праць та досліджень науково-педагогічних працівників, інших співробітників, здобувачів вищої освіти ХНУРЕ. Серед них монографії, статті з наукових журналів та збірників, матеріали науково-практичних заходів, наукові публікації (розміщуються за умови наявності рецензії наукового керівника) та кваліфікаційні роботи здобувачів вищої освіти (розміщуються за дозволом автора КвР).

З усіх питань звертатися до адміністратора ElAr KhNURE за адресою: yuliia.derevianko@nure.ua

Фонди в ЕлАр ХНУРЕ

Виберіть фонд для перегляду його колекцій.

Зараз показано 1 - 13 з 13

Останні подання

Research of control methods for a mobile manipulation robotic platform within the framework of industry 5.0 concepts
(ONUT Publishing House, 2025) Elgun Jabrayilzade
The paper considers current methods of controlling a mobile robotic manipulation platform in the context of implementing Industry 5.0 concepts, which envisage the integration of humans and robots into a single collaborative production environment. The research focuses on analyzing the possibilities of applying predictive control models, impedance strategies, and machine learning methods to achieve adaptability, flexibility, and safe interaction with the operator in dynamic conditions. The feasibility of using hybrid control architectures that combine the reliability of classical approaches and the intelligence of modern algorithms is substantiated. The results emphasize that effective control of mobile manipulation platforms is the key to creating innovative, human-centered production systems that comply with Industry 5.0 principles.
Features of the Use of Quantum Computing in Constructing Trajectory of Collaborative Mobile Robot
(ONUT Publishing House, 2025) Yevsieiev, V.; Demska, N.
This paper considers the features of the application of quantum computing to construct trajectories of a collaborative mobile robot. Compared with classical pathfinding algorithms and evolutionary stochastic methods, quantum approaches provide an efficient search for globally optimal solutions in complex and dynamic environments through the use of superposition and parallel computing. The proposed models formalize the trajectory planning problem in the form of a QUBO formulation, which allows taking into account safety constraints, avoiding collisions, and scaling the system for multi-robot scenarios in Industry 5.0.
Intelligent Microclimate Control: From Reactive Algorithms to Predictive Models
(2025) Holod, I. V.; Yevsieiev, V. V.
The paper discusses the limitations of reactive algorithms for microclimate control in industrial premises and justifies the need for a transition to predictive models. An analysis of traditional and intelligent approaches is carried out, and the mathematical formulation of the microclimate forecasting problem is presented. The use of the NNARX architecture and its combination with fuzzy logic for the development of a hybrid control system is proposed. The advantages of this approach for improving the stability of technological processes and the energy efficiency of production are demonstrated.
The role of artificial intelligence in optimizing information retrieval systems
(ONUT Publishing House, 2025) Levenets, I. O.; Sotnik, S. V.
The paper presents a comprehensive analysis of the application of artificial intelligence methods for the optimization of information retrieval systems. The main problems of modern IRS are investigated, particularly the inefficiency of traditional algorithms in the context of exponential growth of unstructured data volumes. Key AI methods for search improvement are systematized, including natural language processing, vector semantic search, Learning to Rank models, personalization systems, and thematic modeling. Particular attention is paid to the analysis of the balance between the power of intelligent search and ensuring information security. Promising directions for further research are identified, among which are the development of multimodal systems, the implementation of proactive search mechanisms, and the integration of dynamic ontologies.
Application of artificial intelligence in additive manufacturing (3D printing)
(ONUT Publishing House, 2025) Nevludov, I. Sh.; Sotnik, S. V.
The paper presents a comprehensive analysis of artificial intelligence application to improve additive manufacturing quality. Systemic problems of modern 3D printing are identified: quality instability, high defect probability, and labor-intensive model preparation. Six key AI-based quality control methods are analyzed: digital twin, intelligent monitoring, predictive modeling, defect classification, predictive maintenance, and generative design. The combination of deep learning methods (CNN, U-Net, LSTM/GRU) with classical machine learning algorithms (XGBoost, Random Forest) and explainable AI technologies (XAI) ensures high defect detection accuracy and decision interpretability. Particular attention is given to the digital twin concept as an integrating platform for creating a dynamic virtual replica of the printing process. The results confirm that AI integration represents a fundamental transformation of approaches to design, production, and quality control in additive technologies.