Browsing by Author "Rojek, Artur"

Now showing 1 - 6 of 6

Control of Drum Shear Electric Drive Using Self-Learning Artificial Neural Networks
(MDPI, Basel, Switzerland, 2025) Batyrbek, Alibek; Kuznetsov, Valeriy; Kuznetsov, Vitalii V.; Rojek, Artur; Kovalenko, Viktor; Tkalenko, Oleksandr; Tytiuk, Valerii; Krasovskyi, Pavlo
ENG: The objective of this work was to study the possibility of upgrading the control system of the drum shear mechanism by using neural network PI controllers to improve the efficiency of the sheet-metal cutting process. The developed detailed model of the mechanism, including a dual DC electric drive with three subordinate control loops for the voltage of the thyristor converter, current and speed of the motors, a 6-mass kinematic system with viscoelastic connections as well as a model of the metal cutting process, made it possible to uncover that the interaction of electric drives with the mechanical part leads to significant speed fluctuations during the cutting process, which worsens the quality of the sheet-metal edge. A modified system of current and speed controllers with built-in three-layer fitting neural networks as nonlinear components of proportional-integral channels is proposed. An algorithm for the fast learning of neural controllers using the gradient descent method in each cycle of calculating the controller signal is also proposed. The developed neuro-regulators make it possible to reduce the amplitude of speed fluctuations during the cutting process by four times, ensuring the effective damping of oscillations and reducing the duration of transient processes to 0.1 s.
Development of a Digital Twin of a DC Motor Using NARX Artificial Neural Networks
(MDPI, Basel, Switzerland, 2025) Busher, Victor; Kuznetsov, Valeriy; Ciekanowski, Zbigniew; Rojek, Artur; Grudniewski, Tomasz; Druzhinina, Natalya; Kuznetsov, Vitalii V.; Tryputen, Mykola; Hubskyi, Petro V.; Batyrbek, Alibek
ENG: This study presents the development process of a digital twin for a complex dynamic object using Artificial Neural Networks. A separately excited DC motor is considered as an example, which, despite its well-known electromechanical properties, remains a non-trivial object for neural network modeling. It is shown that describing the motor using a generalized neural network with various configurations does not yield satisfactory results. The optimal solution was based on a separation into two distinct nonlinear autoregressive with exogenous inputs (NARX) artificial neural networks with cross-connections for the two main machine variables: one for modeling the armature current with exogenous inputs of voltage and armature speed, and another for modeling the angular speed with inputs of voltage and armature current. Both neural networks are characterized by a relatively small number of neurons in the hidden layer and a time delay of no more than 3 time steps. This solution, consistent with the physical understanding of the motor as an object where electromagnetic energy is converted into thermal and mechanical energy (and vice versa), allows the model to be calibrated for the ideal no-load mode and subsequently account for the influence of torque loads of various natures and changes in the control object parameters over a wide range. The study demonstrates that even for modeling an object such as a DC electric drive with cascaded control, reducing errors at the boundaries of the known operating range requires generating test signals covering approximately 120% of the nominal speed range and 250–400% of the nominal current. Analysis of various test signals revealed that training with a sequence of step changes and linear variations across the entire operating range of armature current and speed provides higher accuracy compared to training with random or uniform signals. Furthermore, to ensure the neural network model’s functionality under varying load torque, a mechanical load observer was developed, and a model architecture incorporating an additional input for disturbance was proposed. The SEDCM_NARX_LOAD neural network model demonstrates a theoretically justified response to load application, although dynamic and static errors arise. In the experiment, the current error was 7.4%, and the speed error was 0.5%. The practical significance of the research lies in the potential use of the proposed model for simulating dynamic and static operational modes of electromechanical systems, tuning controllers, and testing control strategies without employing a physical motor.
Energy Characteristics of the DC Distributed Power Supply Systems
(University of Žilina, Slovakia, 2021) Sychenko, Viktor G.; Kuznetsov, Valeriy; Rojek, Artur; Hubskyi, Petro V.; Kosariev, Yevhen M.
EN: Currently the circuit technology of the DC traction power supply system cannot provide the necessary requirements for introduction of high-speed traffic. Numbers of measures and tools have been developed to improve the traction lines that no longer meet current requirements. One of the most promising means for strengthening the traction DC lines is transition to the distributed power supply of the rolling stock. In this article, a comparative analysis was carried out of energy indicators of the classic centralized power system and distributed power systems with use of one aggregate traction substation and with use of the solar generators. That comparative analysis of these systems was performed on a simulation model with the same parameters of the traction line and rolling stock.
Forecasting the Power Generation of a Solar Power Plant Taking into Account the Statistical Characteristics of Meteorological Conditions
(MDPI, Basel, Switzerland, 2025) Kuznetsov, Vitalii V.; Kuznetsov, Valeriy; Ciekanowski, Zbigniew; Druzhinin, Valeriy; Tytiuk, Valerii; Rojek, Artur; Grudniewski, Tomasz; Kovalenko, Viktor
ENG: The integration of solar generation into national energy balances is associated with a wide range of technical, economic, and organizational challenges, the solution of which requires the adoption of innovative strategies for energy system management. The inherent variability of electricity production, driven by fluctuating climatic conditions, complicates system balancing processes and necessitates the reservation of capacities from conventional energy sources to ensure reliability. Under modern market conditions, the pricing of generated electricity is commonly based on day-ahead forecasts of day energy yield, which significantly affects the economic performance of solar power plants. Consequently, achieving high accuracy in day-ahead electricity production forecasting is a critical and highly relevant task. To address this challenge, a physico-statistical model has been developed, in which the analytical approximation of daily electricity generation is represented as a function of a random variable—cloud cover—modeled by a β-distribution. Analytical expressions were derived for calculating the mathematical expectation and variance of daily electricity generation as functions of the β-distribution parameters of cloudiness. The analytical approximation of daily generation deviates from the exact value, obtained through hourly integration, by an average of 3.9%. The relative forecasting error of electricity production, when using the mathematical expectation of cloudiness compared to the analytical approximation of daily generation, reaches 15.2%. The proposed forecasting method, based on a β-parametric cloudiness model, enhances the accuracy of day-ahead production forecasts, improves the economic efficiency of solar power plants, and contributes to strengthening the stability and reliability of power systems with a substantial share of solar generation.
Mathematical Model of a Semiconductor Structure Based on Vanadium Dioxide for the Mode of a Conductive Phase
(MDPI, Basel, Switzerland, 2025) Kachura, Oleksii V.; Kuznetsov, Valeriy; Tryputen, Mykola; Kuznetsov, Vitalii V.; Kolychev, Sergei V.; Rojek, Artur; Hubskyi, Petro V.
ENG: This study presents a comprehensive mathematical model of a semiconductor structure based on vanadium dioxide (VO2), specifically in its conductive phase. The model was developed using the finite element method (FEM), enabling detailed simulation of the formation of a conductive channel under the influence of low-frequency alternating voltage (50 Hz). The VO2 structure under investigation exhibits pronounced electric field concentration at the surface, where the field strength reaches approximately 5 × 104 V/m, while maintaining a more uniform distribution of around 2 × 104 V/m within the bulk of the material. The simulation results were validated experimentally using a test circuit. Minor deviations—no greater than 8%—were observed between the simulated and measured current values, attributed to magnetic core saturation and modeling assumptions. A distinctive feature of the model is its ability to incorporate the nonlinear dependencies of VO2’s electrical properties on frequency. Analytical expressions were derived for the magnetic permeability and resistivity of VO2, demonstrating excellent agreement with experimental data. The coefficients of determination (R2) for the frequency dependence of magnetic permeability and resistance were found to be 0.9976 and 0.9999, respectively. The current version of the model focuses exclusively on the conductive phase and does not include the thermally induced metal–insulator phase transition characteristic of VO2. The study confirms that VO2-based structures exhibit high responsiveness and nonlinear switching behavior, making them suitable for applications in electronic surge protection, current limiting, and switching elements. The developed model provides a reliable and physically grounded tool for the design and optimization components based on VO2 in power electronics and protective circuitry.
Study of Short Circuit Currents in a Distributed Traction Power Supply System with Renewable Electric Power Sources
(IEEE, 2022) Kuznetsov, Valeriy; Kuznetsov, Vitaliy V.; Bondar, Oleh I.; Rojek, Artur; Hubskyi, Petro V.; Stypulkowski, Piotr
ENG: The problems of changing short-circuit currents in a distributed traction system for using renewable energy sources were analyzed in the article. Literary sources analysis shows a further tendency for increasing the share of renewable energy sources in the total energy balance of the country and a particular increase in electricity consumption by electric traction. Goal. The main goal of the study is a method development with its practical application to impact estimation of power-boost points that connected to the traction network with energy using from renewable sources on short-circuit currents values. Methodology. The method that has developed in this study is based on well-known approaches for equivalent circuits of electrical equipment definition, but elemenst pair like «solar panel - inverter» it reproduces as EMF with equivalent resistance, which significantly simplifies further calculations. Results. The study results show that the application of power-boost points will not lead to a significant increase of short-circuit currents in the traction network even if the power of photovoltaic sources will be comparable with the power of existing converting units on traction substations. This is because of the physical nature of the photovoltaic panel and its power mode which usually closer to the current source with high internal resistance. Practical value. This also allows us to conclude that in most cases from the point of view of changing the short circuit currents the integration of power-boost points that are powered by solar power plants is quite possible with operating sections of the traction power supply system.