Electronics and Control Systems

Research of Aerodynamic Airfoil with Vortex Ceerators in Wind Tunnel

2024-10-09T08:13:31+03:00

This article deals with researching the aerodynamic airfoil model in the wind tunnel using volume vortex generators. The volumetric vortex generators of three types for the definite blowing model are described including their geometrical characteristics. The features of volume vortex generators mounting on the surface of the aerodynamic airfoil model are represented. Features of the experiment in the wind tunnel are described. Comparative changes in aerodynamic characteristics of the aerodynamic airfoil model with and without volume vortex generators in the form of graphical dependencies have been shown. The comparison has been made for different values of Re numbers. The analysis of the obtained dependencies has carried out. The visualization of airflow in an experimental way is illustrated. The results are directed at improving the aerodynamic characteristics of unmanned aerial vehicles. The main significance of the research lies in improving the behavior of unmanned aerial vehicles in the area of critical angles of attack. The obtained results can also be useful for aircraft of the wide class.

Conceptual Aspect of Measuring the Efficiency of Cargo Unmanned Aerial System

2024-10-08T14:22:51+03:00

This article examines the conceptual framework for measuring the efficiency of unmanned systems, focusing on a task-oriented and problem-solving approach to evaluating the performance of cargo unmanned aerial vehicles. The efficiency of cargo unmanned aerial vehicles pertains to their ability to complete missions on time and cost-effectively, while maximizing utilization, minimizing resource loss, and maintaining an acceptable level of flight safety. It is important to highlight that the efficiency of cargo unmanned aerial vehicles is multifaceted, encompassing technical, operational, economic, environmental, and regulatory dimensions. Progress in each of these areas contributes to the successful deployment and optimization of cargo drones across various applications, from last-mile deliveries to supply chain operations in remote regions. The article presents two methodologies for assessing the efficiency of cargo drones.

Voice Control System for Robotics in a Noisy Environment

2024-10-08T14:05:45+03:00

This paper analyzes the effectiveness of the developed voice control system for robotics based on MFCC and GMM-SVM under the influence of interference in the communication channel. The system allows characterizing individual features of speech signals with their subsequent classification and making a reliable decision on the interpretation and execution of voice commands by robotic equipment. The proposed voice control system for robotics based on MFCC and GMM-SVM is implemented using the following technologies: 1) selection of active speech areas by calculating the short-term energy and the number of zero crossings between adjacent frames of the speech signal; 2) adaptive wavelet filtering of the speech signal, where it is necessary to generate threshold values, which will reduce the impact of additive noise; 3) selection of recognition features, which are used as mel-frequency cepstral coefficients; 4) classification of recognition features based on mixtures of Gaussian distributions and the support vector method using the linear Campbell kernel and the principal component method with a projection on latent structures, which will reduce errors of the 1st and 2nd kind.

Advanced Copula-based Methods for Nonparametric Detection and Characterization of Wideband Radar Signals

2024-10-03T15:55:03+03:00

This paper introduces advanced copula-based methods for the nonparametric detection and characterization of wideband radar signals. The research focuses on developing signal detection algorithms that are invariant to changes in the probability density function of the sounding or reflected signals, employing multiscale analysis techniques and copula-based statistics. Two primary approaches are explored: multiscale analysis using wavelet transforms and rank-based signal detection with copula-based ambiguity functions. Simulation results confirm the effectiveness of the proposed approaches. The research demonstrates that integrating rank-based methods with copula-based statistics significantly improves the detection and analysis of wideband radar signals, particularly in complex scenarios where signals exhibit intricate dependency structures. This comprehensive detection framework is well-suited for handling high-dimensional radar signal data, enhancing accuracy and reliability under varied conditions. Future work will focus on optimizing copula selection and permutation strategies to further improve performance.

Algorithm for Precise Payload Drop From FPV Drone with Account of Wind Strength and Automatic Position Correction

2024-10-02T14:57:50+03:00

The work is devoted to the development of an automatic system for dropping cargo from an first-person view drone. An analysis of approaches to the construction of this type of system was performed. It is proven that this problem has not been fully solved, which requires the development of new approaches. In order to increase accuracy, it is proposed to use mathematical models that describe the process of cargo unloading. Mathematical models are given that connect such variables as Height, wind speed, drone speed, cargo weight, cargo surface area, wind direction angle relative to the drone, air density. The use of the obtained mathematical models allows you to calculate the coordinates of the reset point. The developed approach was tested in real conditions. The obtained results showed a significant improvement in the accuracy of dropping the load in the presence of a constantly acting wind.

Comparative Analysis of the Methods of Planning and Coordinating of Manipulator Robot Movement

2024-10-01T15:33:02+03:00

This paper presents a comparative analysis of two methods for planning and coordinating the movement of robot manipulators in dynamic environments: a neural network-based approach for solving dynamic production scenarios and the rapidly exploring random trees algorithm. The study aims to enhance the trajectory planning of robot manipulators by leveraging the strengths of intelligent systems. The neural network method is designed to perceive the environment, generate accurate control commands, and adapt to changing conditions in real-time. The paper the processes involved in environmental analysis, collision avoidance, and control signal generation for actuators, with an emphasis on the neural network architecture tailored for these tasks. The results demonstrate that the neural network approach offers significant improvements in adaptability and efficiency, providing a robust solution for optimizing automated processes in dynamic production environments.

An Intelligent Mobile Search System

2024-10-01T13:58:01+03:00

This article is devoted to the development of an intelligent mobile system used for humanitarian demining. At the same time, the problems of detection, localization and storage of the obtained data are solved. The system operation is based on the use of a synthetic aperture ground penetrating radar, which makes it possible to detect mines both on the earth's surface and underground. A quadcopter is used as a carrier. A set of technical means has been developed. The central and graphic processors are used as a processing unit. Intelligent elements for processing the obtained data are convolutional neural networks, for machine learning of which a synthetic dataset was used. The data is organized into S3 segments based on various parameters, such as date, location and sensor type. This organization facilitates data retrieval and management. Data is encrypted both during transmission and at rest using AWS Key Management Service to ensure confidentiality.

Soil Parameters Monitoring System

2024-10-01T13:07:09+03:00

Soil parameters monitoring is vital for different areas such as climatological and ecological studies, agriculture, etc. Large scale measurement systems are based on satellite technologies however their spatial and temporal resolutions still must be improved for real-time measurement tasks and control of local areas. Such systems also require in-situ measurements for calibration. It rises the need of local sensor networks development. The paper proposes a soil monitoring system which allows measuring temperature and humidity. Wireless communication between sensors and data collection unit allows to form sensor array at required area without additional cables. Usage of thermal noise method allows to perform measurement of both parameters with a single sensor which allows to avoid soil moisture content changes due to absence of local soil heating which could be caused by probing currents in other methods. Proposed method also allows to increase measurement accuracy.

Small-scale Bio Gas Combined Heat and Power Plant with Biochar Catalyst

2024-10-01T10:33:06+03:00

Alternative energy sources allows to replace traditional fossil fuels and firewood. However the most widely used wind and solar power plants can not provide constant power generation due to multiple factors that makes necessary to develop new types of power sources and to to improve efficiency of already existing ones. One of such energy sources are bio gas-fueled power plants which allow to combine the power generation and organic waste disposal functions. Efficiency and quality of bio gas production in such facilities can be significantly increased by using different catalysts such as biochar. A brief analysis of biochar production usage perspectives was held which showed that it can be used in different applications and can significantly increase efficiency of different technological processes. The influence of biochar on the biogas production processes was studied. The structure of bio gas-fueled heat and power plant with local bio gas generation was proposed.

Semi-supervised Segmentation of Medical Images

2024-10-01T09:26:53+03:00

This article is devoted to the development of a method (algorithm) of medical image segmentation based on semi-supervised learning. Semi-supervised learning methods are shown to have significant potential for improving medical image segmentation through effective use of unlabeled data. However, challenges remain in adapting these methods to the specific characteristics of medical images, such as high variability, class imbalance, and the presence of noise and artifacts. To overcome these difficulties, it is proposed to integrate several approaches (consistency regularization, pseudo-labeling, average teacher model) into a single structure. To increase the robustness and generalizability of the model for different imaging methods, we include industry-specific data supplements tailored to the unique characteristics and challenges of each method. Large-scale experiments on magnetic resonance imaging, computed tomography, and optical coherence tomography datasets demonstrate that the proposed framework significantly outperforms fully supervised and individual semisupervised learning methods, especially in scenarios with low data labeling.

Semi-supervised Multi-view Ensemble Learning with Consensus

2024-09-30T09:24:48+03:00

This paper is devoted to enchasing existing multi-view semi-supervised ensemble learning algorithms by introducing a cross-view consensus. A detailed overview of three state-of-the-art methods is given, with relevant steps of the training highlighted. A problem statement is formed to introduce both semi-supervised framework and consider the semi-supervised learning in the context of optimization problem. A novel multi-view semi-supervised ensemble learning algorithm called multi-view semi-supervised cross consensus (MSSXC) is introduced. The algorithm is tested against 5 synthetic datasets designed for semi-supervised learning challenges. The results indicate improvement in the average accuracy of up to 10% in comparison to existing methods, especially in low-volume, high density scenarios.

Language Model Adaptation for Legal Ukrainian Domain

2024-09-30T08:43:44+03:00

Language models in recent decades make a huge step towards solving the tasks that previously could be done only by humans. Development of NLP area is different scopes gives an opportunity to solve domain specific tasks and transfer knowledge from learnt data towards the useful inferences based on that. This article provides the NLP model approach in specific legal domain. Additionally, this article explores performance of pre-training small models and its utilization and checks the scores on fine-tuned task of checking sentence similarities via SBERT. According to this articles it is proven that domain-specific pre-trained models can perform better results than generally trained language model. This article also provides the language model that is adopted to the Ukrainian legal domain.

Spectral Analysis of Autocorrelation Functions of Roll and Pitch Angles

2024-06-21T12:18:13+03:00

This article addresses issues related to assessing the impact of a pilot's psychophysiological stress on the quality of aircraft piloting techniques. The quality of aircraft control was evaluated through changes in flight parameters, specifically the roll and pitch angles during the landing approach. The study utilized the analysis of autocorrelation functions of the controlled parameter and their spectra. The proposed mathematical apparatus allows tracking the moment when the pilot's psychophysiological stress increases to the point of emotional instability, constructing a function of its influence on the quality of aircraft piloting. This method is necessary for improving crew training for special situations in flight.

Complementary Filter in Inertial-Doppler System of Navigation

2024-06-21T11:55:04+03:00

The article is devoted to filtering algorithms that are used to process flight speed data from an inertial navigation system and from a Doppler speed and angle demolition meter. It is shown that the compensation scheme and the filtering scheme, the more common name of which is the complementary filter scheme, are the most common for processing flight and navigational information in inertial-Doppler navigation systems. The paper proves the equivalence of the compensation scheme and the complementary filter scheme, and also substantiates that these schemes, unlike Kalman filtering, are simple to implement, and for design, they require the selection and setting of only one parameter - the filter time constant.
A technique for choosing the optimal value of the filter time constant is proposed, which ensures the
maximum accuracy of the estimated parameter, namely: the aircraft's cruising speed. The methodology is based on the analysis of error spectra of integrated systems: the inertial system - with a low-frequency
error spectrum, and the Doppler system with a high-frequency spectrum. Studies of synthesized filtering schemes have been conducted.

Qualitative Qoe Assessment when Choosing a Web Service Using an Expert Hybrid System

2024-06-21T11:28:55+03:00

In the article proposes a new method, based on a hybrid fuzzy expert system, for assessing the QoE of web services. It also shows how different QoS parameters affect QoE. To do this, a subjective test was conducted in a controlled environment with real users to correlate QoS parameters with a subjective QoE score. Based on the test results, affiliation functions and rules for the fuzzy system were obtained. The membership function is derived using a probabilistic approach, and the derivation rules are generated using fuzzy set theory. The evaluation simulation environment using the Matlab software package. The results of the simulation show that the quality of the website is rated and has a high correlation with the subjective quality assessment received from the participants of the control test.

Comprehensive Framework for Design and Modernization of Avionics Management Systems

2024-06-21T10:31:39+03:00

The efficiency and safety of civil aviation heavily depend on the robust performance of avionic systems, which provide essential communication, navigation, and surveillance capabilities for flight operations. To sustain the requisite level of reliability in these complex systems, a methodological foundation for their design and modernization is critical. This paper presents a comprehensive framework for the Avionics Management System, emphasizing systematic component analysis and developmental methodologies. This framework includes a multidisciplinary approach that integrates advanced principles, theories, models, and methods drawn from current achievements in information technology, artificial intelligence, mathematical statistics, and decision-making theory. It also considers societal needs, economic trends, and future developmental prospects. Proposed approach ensures that AMS not only addresses immediate operational requirements but is also adaptable to future technological evolutions, thus supporting the life cycle of avionic systems from conception through to utilization. The proposed framework is poised to guide the industry in achieving higher levels of system reliability and maintenance efficiency, with potential implications for the broader realm of civil aviation and its ever-advancing technological landscape.

Nonlinear Optical Properties of Ionic Thermotropic and Lyotropic Liquid Crystals

2024-06-20T22:19:29+03:00

This work presents the analysis of experimental research on the optical and nonlinear optical properties of two different representatives of metal alkanoate-based liquid crystals. Namely, ionic lyotropic liquid crystals of potassium caprylate doped with electrochromic viologen additives, and anisotropic glasses of ionic thermotropic liquid crystals of cobalt alkanoates of the homologous series (n = 7, 9, 11) and their multicomponent mixtures. Prior to the nonlinear optical experiment, the optical absorption spectra of all samples were investigated. For proposed absorbing media, laser-induced dynamic grating recording under the action of nanosecond laser pulses has been realised, observed and analysed. The studied materials were found to exhibit cubic optical nonlinearity, with cubic nonlinear susceptibility χ⁽³⁾ and hyperpolarizability γ values comparable to the best organic dyes. The possible mechanism of nonlinear response in the systems studied was considered on the basis of the data obtained. The nonlinear response mechanism is related to the non-linear polarisation of the π-electrons in the field of the laser radiation.

Artificial Ineligence for Synthetic Aperture Radar Image Processing

2024-06-20T21:38:43+03:00

The object of this research is the processing of synthetic aperture radar (SAR) images using artificial intelligence. The subject of the study focuses on the utilization of artificial intelligence for the object detection on SAR images. The primary goal of this thesis is to investigate the principles of SAR operation, analyze various systems for detecting anomalous objects in soil, develop an intelligent system for processing SAR images, and evaluate the potential of the developed system for the classification of explosive objects. The research methods include the analysis of existing literature and programming in Python. The findings and materials from this thesis are recommended for use in the analysis of current underground anomaly detection systems, the potential application of artificial intelligence and machine learning in demining processes, and the examination of radar image processing methods.

Synthesis of Robust System for Spatial Stabilization of Ground Vehicle Equipment

2024-06-19T20:27:13+03:00

The article deals with the approach to designing robust system for stabilization of equipment assigned for operation on ground moving vehicles. The mathematical model of stabilization system including non-linear differential equations and state space representation is given. The features of basic external disturbances specific for ground moving vehicles are represented and analysed. The classification of external disturbances is suggested. Expressions for forming filters providing simulation of specific external disturbances are derived. The basic peculiarities of synthesis of spatial stabilization system for ground moving vehicle equipment are described. The simulation results are represented. During simulation, irregularities of different types are taken into consideration. The description of means for simulation of stabilization system of the studied type are considered. The obtained results can be useful for equipment operated on moving vehicles of the wide class.

Single-electron Sequential Nanocircuits and their Models

2024-06-19T15:36:26+03:00

Memorizing nanodrives are distinguished by a large variety of majority trigger structures, which are the basic fragments of the the nanocircuit of a high integration level. The paper describes the synthesis of reliable sequential nanodevices of single- electronics based on the technology of quantum cellular automata. When constructing majority nano-circuits with memory, the theory of finite automata is used. The order of computer design of different types of arithmetic and logic nanodevices is analyzed. High-speed parallel-acting and paraphase control nanoregisters control are created.

Adaptive Control of Manipulator Robots in a Dynamic Environment Using Neural Networks

2024-06-19T14:41:22+03:00

The purpose of the study is to develop an approach to planning the trajectory of the manipulator robot using an intelligent system based on neural networks. For this purpose, the work considered the processes of planning and deploying the movement of the robot. The analysis of existing methods of planning the movement of manipulator robots and the review of intelligent control systems made it possible to obtain a complete picture of the current state of this issue. A system is proposed that can perceive the environment and control the movement of the robot by generating the correct control commands. For this, 3 tasks were solved, namely: analysis of the environment in order to determine its features, determination of the trajectory in order to neutralize the collision and determination of controlled influences for the executive authorities in order to implement the movement. The functionality and structure of the neural network for solving each of the tasks are proposed.

Solution of the Problem of Identification of Aerodynamic Coefficients of Aircraft According to the Data of Their Full-Scale Tests

2024-06-19T12:48:02+03:00

The methodology of the correct identification of the aerodynamic coefficients of the aircraft is considered, namely the determination of the partial derivatives of the aerodynamic forces and moments of the aircraft according to its state variables. The method of determining static (balancing) dependencies from short-term dynamic modes of a natural experiment is also presented. The effectiveness of the proposed approach is confirmed by the practice of determining the aerodynamic coefficients and aerodynamic characteristics of various aircraft.

Automated Camouflage Design Based on Artificial Intelligence

2024-06-19T12:19:41+03:00

The article discusses the development of a camouflage uniform production system for civilian use with an emphasis on survival and hunting. Effective camouflage requires precise reproduction of the colors, textures, and patterns of specific landscapes, increasing hunting success and unnoticed movement. The technological process of fabric dyeing, necessary for the production of high-quality camouflage uniforms, includes fabric preparation, dyeing and strict quality control.. Fabric preparation includes cleaning, soaking, bleaching, and mercerization to ensure uniform dye absorption and durability. Dyeing methods vary by fabric type, with reactive dyes for natural fibers and disperse dyes for synthetics. Quality control includes visual inspections and tests for colorfastness under various conditions. Advanced dyeing techniques such as continuous dyeing, spray dyeing, stencil dyeing and digital printing have been analyzed to offer certain advantages. Machines like the Mimaki TX300P handle various fabric widths with high precision and reliability, enhancing efficiency. Automation using the Mimaki TX300P streamlines the dyeing process, optimizing ink consumption and integrating fabric loading, printing, and cutting systems. A customer relationship management system further automates garment creation, enhancing design, order management, and quality control. Tools like CLO3D enable detailed 3D modeling and accurate pattern reproduction. The customer relationship management system coordinates production stages and provides precise paint usage recommendations, ensuring efficient resource management and high-quality outcomes. In conclusion, developing and automating fabric dyeing processes for camouflage uniforms involve advanced technologies and meticulous quality control, ensuring durable, colorfast camouflage clothing that blends effectively into natural environments for civilian use.

Analysis of Ukrainian, Turkish, Moldova Air Network Using Graph Theory

2024-06-19T10:26:51+03:00

The article considers the application of the analysis method using graph theory to determine critical points in the air networks of Ukraine, Turkey and Moldova. The goal is to identify critical points in the above-mentioned aerial networks. The reason is the probability of resuming air traffic between Ukraine and neighboring countries (with the exception of the Russian Federation). The data on the network is obtained from collections of aeronautical information. Modeling was performed in the Python software environment using libraries for processing and visualizing the received data. The main criteria used to determine the criticality of a radio navigation point are Betweenness centrality and Closeness centrality. In addition, the collection and comparison of statistical data on the number of routes and radio navigation points in each of the studied countries will be performed. The obtained data are useful, because it will give an opportunity to compare the results with those obtained during the study of the Ukrainian network and for air navigation service providers to improve the existing network.

Intelligent System of Generation of Camouflage Patterns Based on Artificial Intelligence Technologies

2024-06-19T10:01:08+03:00

The work is devoted to the development of an intelligent system for generating camouflage patterns based on artificial intelligence technologies. A generative-competitive network is used as an intellectual element of this system. To solve the problem of the collapse mode, the architecture of progressively growing GANs (ProGAN) is used. The system allows you to generate completely new camouflage patterns for the selected area by iteratively improving the pattern. Due to the mechanism of restrictions, it is possible to fix the desired aspects of the drawing (color scheme, pattern, number of colors) from an existing drawing and adapt it to the desired area. The system provides the possibility of generating micropatterns on the drawings to improve camouflage at close distances. When evaluating a camouflage pattern, the system takes into account additional parameters, such as angle (from the ground and air), time and weather.

Two-circuit System of Automated Control of Low-Altitude Helicopter Flight

2024-04-02T12:12:33+03:00

The mode of automatic control of a low-altitude flight of a helicopter over heavily rugged
terrain based on information about the inclined range is considered. It is shown that at high flight speeds it is impossible to overcome strictly vertical obstacles without changing the angle of inclination of the rangefinder antenna to the horizon depending on the flight speed, or without reducing the flight speed when approaching such an obstacle. Algorithms for controlling low-altitude flight using a two-channel scheme are proposed, namely, at high speeds through the longitudinal channel of the swashplate, and at low speeds – through the channel of the general pitch of the main rotor. The problem of optimal control of low-altitude helicopter flight is formulated, which can be presented as a variational problem with
restrictions on phase coordinates and control influences. Ways to optimize the process of circumventing an obstacle with forecasting the trajectory of the helicopter on a certain section of the route with
subsequent stabilization of the helicopter on this trajectory are shown.

Methods for Measuring the Efficiency of UAVs in the Air Navigation System

2024-04-02T11:47:46+03:00

The article discusses the concept of efficiency in the context of assessment system solutions and the methods used to measure it. Efficiency is defined as the ability to produce effects and achieve results, while effectiveness is understood as the outcome of certain actions. Efficiency theory is based on operations research and decision-making methods using mathematical models such as probability theory and machine learning techniques. The results of performance measurements can be used to solve a variety of practical problems related to unmanned aerial vehicles, including comparing similar systems, conducting operational assessments, and optimizing requirements. The paper also discusses the modification of flight control and planning models, where stochastic parameters that affect mission quality need to be considered. Societal effects, such as flight normality and safety, can be measured by direct assessment methods and statistical metrics. More generalized metrics can be used to assess flight safety by comparing the number of accidents and workload. Suggested methods include the use of mathematical models and integration techniques to assess flight safety.

The Latest Means of Communications Based on LTE and MIMO Technologies in 3G, 4G Networks: Application for Contemporary Biomedical Practice in Rural Ukraine

2024-04-02T11:15:24+03:00

The network organization of the systems of economic entities, which are distributed remotely over large territories, require the creation of high-quality communications for them. The purpose of present work was to demonstrate the possibility of using the latest means of communication based on Long-Term Evolution and Multiple-Input Multiple-Output technologies (LTE- and MIMO- technologies) in 3G and 4G networks to solve contemporary tasks of organizing of high-quality mobile communication in some places of the territory of Ukraine for the works that need biological and medical information in rarely settled, remote regions. The publication provides the author's data on the practical organization of communication in rural areas and considers the following issues. 1- Determination of spatial parameters of the LTE standard network. 2- Preparation of a map of the area. 3- Choosing an LTE network planning option. 4- Principles of construction and operation of LTE networks. 5- P-GW (Packet Data Network Gateway) functions. 6- MME (Mobility Management Entity) functions. 7- Functions of PCRF. MME (Mobility Management Entity) functions. 8- Functions of PCRF. 9- Peculiarities of using upper and lower frequencies for LTE. 10- Application of MIMO technology in LTE. 11- Application of MIMO technology in 3G and 4G networks. The results of the performed works can be applied for the networked structures development for the use in domestic economy, agriculture, for the science branches like biology, nature protection, and for information systems for such branches. In the result of the work done the type of antenna, other equipment were suggested; they should be used to strengthen 3G and 4G Long-Term Evolution communication in such conditions, as well as suitable 4G antenna for modem or router. Obtained results are suitable for providing of the work of information systems in agriculture, ecological monitoring, other areas of activities, based on biological and medical information; they all need quick data exchange as well as for scientific centers, other settlements, for which such communication possibilities primarily were developed.

Absorbance Spectra of Co2+ Alkanoate Liquid Crystals and Smectic Glasses

2024-04-02T10:32:35+03:00

The work is devoted to the study of the optical properties of ionic thermotropic liquid crystals of the homologous series of cobalt alkanoates and their smectic glasses using methods of electronic spectroscopy. The aim of the study was to determine the dominant coordination of cobalt cations in the alkanoate matrix and the nature of the matrix's influence on the absorption of samples. It is shown that the dominant coordination of cobalt ions in the studied media is the octahedron. A significant decrease in the absorption coefficient with the increase in the length of the aliphatic chain in the homologous series of cobalt alkanoates is due to a decrease in both the volume concentration of the cobalt cation complexes and the values of the dipole moments of the d-d transitions.

Method of Planning and Coordination of Robot Movement Using Neural Networks for Solution of Dynamic Production Scenarios

2024-04-02T09:20:59+03:00

The purpose of the study is to develop an approach to planning the trajectory of a robot manipulator using an intelligent system based on neural networks. For this purpose, the work considered the processes of planning and deploying the movement of the robot. The analysis of existing methods of planning the movement of robot manipulators and the review of intelligent control systems provided a comprehensive picture of the current state of this issue. A system is proposed that can perceive the environment and controls the movement of the robot by generating correct control commands. For this purpose, 3 tasks were solved, namely, the analysis of the environment in order to determine its features, the determination of the trajectory in order to neutralize the collision, and the determination of controlled influences for the executive bodies in order to implement the movement. The functionality and structure of the neural network for solving each of the tasks is proposed. The proposed approach is compared with existing approaches on key parameters, such as the execution time of the planned movement and the time of calculating the movement trajectory. The results confirmed that the use of neural network to optimize the trajectory and dynamic prediction to avoid obstacles significantly increased the adaptability of the system to the changing conditions of the production environment, which opens up new opportunities for improving automated processes and providing optimal conditions for the functioning of manipulator robots in real-time.

Modeling of Ferric Nanoparticles Fe3+ Interactions with thin Films of Organic Substances

2024-04-01T21:02:12+03:00

The results of solving the problem of modeling the interaction of iron Fe³⁺ nanoparticles with thin bilayer membranes were represented. The purpose of the work was to create a physical model of the behavior and interaction of Fe³⁺ iron nanoparticles, which are located near thin films of organic substances. For this, physical model systems with thin films - BPM (bilayer phospholipid membranes) and BLM (bilayer lipid membranes) were considered and analyzed, and iron nanoparticles were introduced into these systems. To fulfill the given task, the data search methods ("data mining") obtained by the gas-liquid chromatography were used, as well as ones obtained in experiments with registration of transmembrane electric currents through artificial two-layer BPM and BLM membranes, and partially ones from the experiments on natural membranes with technique of voltage clamp. Since the applied FeCl₃ undergoes hydrolysis, the formed hydroxyl groups interact with BLM membranes, also participating in the sum of interaction effects. Thus, it was concluded about the important role of hydroxyl groups in the mechanism of anionic selectivity of BLM, which is a confirmation of previously obtained research data. A number of effects with participation of ionophores, which increase the ion permeability of artificial BLM membranes, were also considered; they can bind metal ions due to ion-dipole interaction. The described system with a membrane and iron (III) ions located near it can be used to study a number of phenomena on both artificial and natural membranes, for example, when iron nanoparticles were absorbed by human body from the environment. For all considered cases, known physical and physico-chemical regularities and the corresponding developed mathematical apparatus were verified. Namely, analytical expressions based on electrostatic interactions of electric charges associated with Fe³⁺ ions and localized on membrane surfaces were valid for describing the considered effects. The considered model membranes are on the border between living and non-living nature. At the same time, these systems are simple systems to which the laws of physics and physical chemistry are applicable. And, in some cases, when developing some technical hybrid systems, they can play the role of biosensors. Due to their simplicity, such models can be reproduced quite easily in the conditions of experiments, substances testing with analytical purpose in extreme situations. Therefore, such simple, reliable, tested methods can be used in wartime situations with limited laboratory resources.

Basic Stages of Technique for Designing Systems of Stabilization for Moving Vehicles Equipment

2024-04-01T20:24:19+03:00

The basic stages of technique for designing systems for stabilization of apparatus operated on moving vehicles are described. The most important design stages are listed. The main features of forming specification of requirements are represented. The characteristic of choosing basic components for the stabilization system, first of all inertial rate sensors and electric motors, are described. Principles of simulation of basic components of the stabilization system are given. The approaches for designing control laws in stabilization and tracking loops are represented including designing PID regulators and robust controllers. The basic approaches for checks of synthesised stabilization system by means of simulation are represented. The simulation results on the example of the robust stabilization system are given. The advantages of application of the robust system in conditions of disturbances are shown. The obtained results can be useful for measuring and observation devices operated on moving vehicles of the wide class.

Summation Circuits of Automatic Control Systems

2024-04-01T19:55:59+03:00

During the operation of the stabilization systems, the parameters of the control object and the regulator can change for various reasons within fairly wide limits. In such cases, they speak of the presence of parametric uncertainty. Note that the main indicator of the quality of the stabilization system is considered to be the accuracy of the stabilization of the control object. As theoretical studies show, the accuracy of stabilization systems directly depends on their rigidity and damping, because they directly affect the formation of the moment of stabilization and determine the effectiveness of the system's response to external disturbances. Changing stiffness and damping in order to ensure the necessary efficiency of stabilization systems is the basis of their operational adjustments. To change these parameters, there are summation circuits in the systems. Will the change in the summation circuit type affect the solution to the main task of the operational adjustment of the stabilization system? This article considers the possibilities of summation circuits to ensure the optimality of the settings of the stabilization system.

The Use of Artificial Intelligence Methods in the Intelligent Decision Support System

2024-04-01T19:37:38+03:00

The article is devoted to the study of the use of artificial intelligence methods in decision-making support systems, particularly in military affairs. Examples of the application of artificial intelligence methods, such as expert systems and machine learning, which can be used to optimize management and strategic decisions in military operations, are considered. Special attention is paid to the use of decision trees in military scenarios as a tool for modeling possible options for the development of events and making optimal decisions. Decision trees allow a decision support system to analyze possible courses of action based on different conditions and circumstances. The results of the study emphasize the importance of using artificial intelligence to improve the efficiency and quality of decision-making in military affairs.

Odometrical Navigation Systems

2024-03-30T21:39:10+02:00

The technology for determining the location of an object on the ground is the foundation for building vehicle navigation systems and surveillance systems after them. In general, such navigation systems make it possible to determine the coordinates of the vehicle’s location and its directional angle, find the direction to the destination, and calculate the coordinates of observation objects. The technical implementation of systems can be quite diverse – from implementation on mechanical elements to their implementation using microelectronics elements. The main factors in the development of navigation systems are the transition to computer-integrated systems and resource-saving technologies. This will make it possible to increase the accuracy of navigation information, obtain a significant gain in the weight and size characteristics of the equipment, reduce its energy consumption and increase reliability. The possibility of modernization of odometrical navigation systems based on integrated computer technologies is considered.

A Comprehensive Framework for Underwater Object Detection Based on Improved YOLOv8

2024-03-29T20:02:33+02:00

Underwater object detection poses unique challenges due to issues such as poor visibility, small densely packed objects, and target occlusion. In this paper, we propose a comprehensive framework for underwater object detection based on improved YOLOv8, addressing these challenges and achieving superior performance. Our framework integrates several key enhancements including Contrast Limited Adaptive Histogram Equalization for image preprocessing, a lightweight GhostNetV2 backbone, Coordinate Attention mechanism, and Deformable ConvNets v4 for improved feature representation. Through experimentation on the UTDAC2020 dataset, our model achieves 82.67% precision, 81.02 % recall, and 86.3 % mean average precision at IoU = 0.5. Notably, our framework outperforms the YOLOv8s model by a significant margin, while also being 15.1% smaller in terms of computational complexity. These results underscore the efficiency of our proposed framework for underwater object detection tasks, demonstrating its potential for real-world applications in underwater environments.

Solution of the Transportation Problem Employing Intelligent Technologies

2024-01-25T10:51:59+02:00

The article presents a new method of predicting the time of completion of a transport task. The method is based on the created mathematical model of the transport task process and on artificial intelligence methods. The choice of the optimal transportation route is based on the conditions of a specific task. A new method of choosing the optimal route is presented, taking into account the influence of such factors as weather conditions, day of the week, time of day, condition of the road surface, presence of residential complexes and other factors. The purpose of the study is to optimize the method of building a transport route using neural networks. The work presents the improvement of the general method of optimizing the transport process, the development of a neural network training method for predicting the time of the transport process, the development of a simulation mathematical model of the transport process and the determination of the model parameters and the effectiveness of the method verification. Research methods: methods of mathematical modeling, simulation modeling, Monte Carlo method, methods of artificial intelligence based on neural networks.

Air Traffic Control and Flight Planning for Cargo UAVS in a Single Airspace

2024-01-25T10:23:30+02:00

This article piece analyzes in detail the challenges and approaches to incorporating large cargo Unmanned Aerial Vehicles into existing airspace, focusing on air traffic management and flight operations planning. Modifications to air traffic control models required as a result of the inclusion of Unmanned Aerial Vehicles are discussed, with a focus on managing the various stochastic parameters that affect flight quality. The importance of maintaining safe takeoff and landing intervals is also emphasized. In addition, the article delves into the application of machine learning techniques in air traffic flow management, exploring the complexities of planning scheduled and special flights under conditions of incomplete information and stochastic uncertainty. The article highlights the importance of optimizing the payload-to-range ratio of Unmanned Aerial Vehicles, taking into account factors such as wind conditions and battery efficiency to improve cargo transport efficiency. In addition, the article presents a two-stage stochastic programming model for flight planning aimed at minimizing costs and efficiently allocating flights and resources. The impact of drones on "last mile" delivery logistics is also discussed, emphasizing the potential benefits of drones in terms of increased speed, cost reduction, and access to remote areas.

Modeling Complex for Studies of Methodical and Instrumental Errors of the Strapdown Inertial Navigation System

2024-01-25T10:04:01+02:00

To study the accuracy characteristics, a strapdown inertial navigation system is represented as a set of kinematic equations and equations of a mathematical model of the Earth. Based on the mathematical model in the Matlab-Simulink package, a modeling complex was created, consisting of subsystems of the reference and studied navigation system, subsystems of the reference and simplified model of the Earth and a subsystem of primary information sensors. In navigation subsystems, kinematic equations of inertial navigation algorithms are solved, and matrices of direction cosines are formed. In the subsystems of the Earth model, the parameters of the Earth's spheroid and the acceleration of gravity are calculated. The sensor models are developed based on the characteristics of low-cost microelectromechanical sensors. The purpose of the study was to assess methodological and instrumental errors as the difference in the dead reckoning signals of the flight navigation parameters of the reference and studied navigation systems. Methodological errors of the system are played up by simplifications of the parameters of the earth's spheroid, and instrumental errors are caused by errors in inertial sensors.

Implementation of 3G, 4G Mobile Connections Technologies in Urban and Rural Regions

2024-01-24T13:51:44+02:00

Currently in Ukraine, taking into account the development of the latest mobile Internet standards (3G/4G), it is possible to access the Internet even in remote places. There are no wired Internet due to the high cost of installation and maintenance. At the same time, a huge amount of equipment appeared on the market, which allows you to assemble systems for obtaining high-quality Internet over a wireless communication line. This refers to various types of antennas in the 900–2700MHz range, modems and routers with 3G/4G support. The locations of 3G/4G Internet base stations are in district centers predominantly. So, there is a situation that remote villages, settlements do not have the opportunity to get access to high-speed Internet. This especially harms the work of biological stations and rural medical clinics, which are spread over the territory of Ukraine and are often connected in a network. The purpose of the work is to describe briefly some practical results of our own development of providing high-quality mobile communication in some remote places of the territory of the state. To provide this service in remote areas of Ukraine, signal amplification is necessary. In addition, there is a problem with the propagation of radio waves over the rough terrains for the ultra short wave and microwave ranges. To solve this problem, it is proposed to use an external antenna with a high amplification factor, which will be installed at a height of at least 6 meters above the ground to reduce the impact of interference on the path of radio waves.

Researching Indices of Reliability of Navigation Parameters Meters Checking

2024-01-24T13:22:08+02:00

The article deals with the studying process of measuring navigation parameters by means of gyroscopic measurements instruments. The topic of research is connected with studying reliability of checking of gyroscopic measuring instruments. The instrumental and methodical components of the check’s reliability are determined. Probabilities of arising both false and indefinite failures are obtained. The relationship, which connects accuracy performances and mass-dimension characteristics, is represented. Graphical dependences, which characterize interconnection between the instrumental component of the check’s reliability with accuracy characteristics of navigation measuring instruments, are given. Graphical dependences, which illustrate change of the methodical component for different types of checks, are shown. The analysis of instrumental and methodical components of the reliability of checking is carried out. The obtained results can be useful for grounded assignment of tolerances on measured navigation parameters.

Intelegence Design of Hybrid Vertical-axis Rotors

2024-01-24T12:48:30+02:00

The work is devoted to the necessity of creating the vertical-axis rotors of wind power stations in the urban area, which can be placed on roofs and makes it possible to increase their energy productivity by 60-70%. It is shown that the locations of such rotors on roofs has its own characteristics, which consists in the need to take into account the shape of the topography of the house, its storey, the direction and speed of the winds above it, and others. Examples of implementation of wind farms are considered and it is proven that their energy efficiency can be increased due to the use of hybrid vertical-axis rotors, which consist of a combination of Darrieus and Savonius rotors, where the Darrieus rotor is the main source(s) of wind energy conversion into the electric one, while the Savonius rotor(s) provide the acceleration of the Darrieus rotors. For the implementation it has been used the genetic algorithm. An inelegance design system has been developed. An example of the application of this system for the design of a hybrid rotor is given.

Determination of Marketing Parameters for Building a Demand Forecasting Model using Neural Networks

2024-01-22T14:38:44+02:00

This article is dedicated to the discovery of marketing parameters for the implementation of a forecasting model using additional neural measures using data from real data. The robot looks at the problem in the field of modeling the delivery of goods to the market in marketing using additional methods of artificial intelligence and machine learning. The main features of the main approaches to introducing product models to the market, their advantages and disadvantages are shown. It has been revealed that they will require thoroughness. A new methodology for solving the problem is presented. The model's ability to accurately predict lasting demand based on a variety of marketing parameters has been demonstrated, which helps businesses effectively plan inventory, inventory, and personnel, and can lead to significant cost savings. and increased efficiency.

Structural-parametric Synthesis of Capsule Neural Networks

2024-01-22T13:16:05+02:00

This work is dedicated to the structural-parametric synthesis of capsule neural networks. A methodology for structural-parametric synthesis of capsule neural networks has been developed, which includes the following algorithms: determining the most influential parameters of the capsule neural network, a hybrid machine learning algorithm. Using the hybrid algorithm, the optimal structure and values of weight coefficients are determined. The hybrid algorithm consists of a genetic algorithm and a gradient algorithm (Adam). 150 topologies of capsule neural networks were evaluated, with an average evaluation time of one generation taking 10 hours. Chromosomes and weights are stored in the generation folder. The chromosome storage format is JSON, using the jsonpickle library for writing. Also, when forming a new generation, chromosome files from previous generations are used as a "cache". If a chromosome of the same structure exists, the accuracy is assigned immediately to avoid unnecessary training of neural networks. As a result of using the hybrid algorithm, the optimal topology and parameters of the capsule neural network for classification tasks have been found.

Twitter Fake News Detection Using Graph Neural Networks

2024-01-22T11:09:56+02:00

This article is devoted to the intellectual processing of text information for the purpose of detecting rail news. To solve the given task, the use of deep graph neural networks is proposed. Fake news detection based on user preferences is augmented with deeper graph neural network topologies, including Hierarchical Graph Pooling with Structure Learning, to improve the graph convolution operation and capture richer contextual relationships in news graphs. The paper presents the possibilities of extending the framework of fake news detection based on user preferences using deep graph neural networks to improve fake news recognition. Evaluation on the FakeNewsNet dataset (a subset of Gossipcop) using the PyTorch Geometric and PyTorch Lightning frameworks demonstrates that the developed deep graph neural network model achieves 94% accuracy in fake news classification. The results show that deeper graph neural networks with integrated text and graph features offer promising options for reliable and accurate fake news detection, paving the way for improved information quality in social networks and beyond.

Filter for confidential information

2024-01-22T10:23:29+02:00

The research is conducted on the topic of preventing various types of attacks on large language models (LLM), as well as preventing the leakage of confidential data when working with local text databases. Research is performed by implementing a filter and testing it on an example that aims to filter requests to the model. The proposed filter does not block the request to the LLM, but removes its parts, which is much faster and makes it impossible for an attacker to pick up a request, as it destroys its structure. The filter uses word embedding to evaluate the request to the LLM, which together with the use of a hash table for forbidden topics, speeds up the operation of the filter. To protect against attacks such as prompt injection and prompt leaking attack, the filter uses the method of randomly closing the sequence. During the testing process, significant improvements were obtained in maintaining the security of data used by LLM. Currently, the use of such filters in product projects and startups is an extremely important step, but there is a lack of ready-made implementations of filters with similar properties. The uniqueness of the filter lies in its independence from LLM and the use of semantic similarity as a fine-tuned way of classifying queries.

Text Message Clustering

2024-01-22T09:51:07+02:00

The division into groups of text messages is considered, which can be useful when building a personalized approach in different systems. Тo solve this problem, the Embedded Word2Vec was proposed. To enhance the division into groups, the suggestion of employing mini-batch k-means is presented, offering a method with lower computational demands. This recommendation aligns with the practical need for efficient and scalable clustering methods, especially when dealing with large datasets. Furthermore, the proposed metric based on the greatest common sequence is highlighted as a valuable tool for evaluating the similarity of texts. This metric not only serves as a means to assess clustering quality but also underscores the methodological approach of directly working with text data. The combination of these techniques presents a comprehensive framework for robust and effective text clustering, with potential applications in diverse fields, such as personalized system interactions and information retrieval.

Comparison of Two Methods for Measuring Speech Intelligibility

2024-01-19T20:35:50+02:00

Comparing of the full speech transmission index method and full formant-modulation method of speech intelligibility measurement has been made. The methods were compared according to the accuracy of the measurements under the conditions of noise interference. The dependences of the STI estimates errors on the signal-to-noise ratio and on the duration of the test signals were obtained by means of computer simulation. It is shown that the accuracy of speech transmission index estimates is practically the same for both methods. In particular, it is shown that the use of test signals with a duration of 4 s is minimally acceptable and provides an estimation error of 0.03. Using 8 s and 16 s test signals reduces the speech transmission index estimation error to 0.02 and 0.01, respectively, for a wide signal-to-noise ratio range from minus 28 dB to plus 28 dB. The obtained results are close to those for the case of the joint action of noise and reverberation.

Aircraft Fuel Measurement System Based on Hydrostatic Pressure Sensor

2023-11-22T11:17:48+02:00

The construction of an aircraft fuel-measuring system based on hydrostatic pressure sensors is considered, which makes it possible to determine the fuel residue in the aircraft tanks during its evolutions. With the evolution of aircraft, measuring the fuel residue in existing fuel metering systems using float and capacitive fuel level sensors has a rather complex electromechanical design and significant weight and size characteristics. This together affects the reliability of such systems as a whole and leads to significant methodological errors in determining the remaining fuel during maneuverable flight. The proposed system using hydrostatic pressure sensors and a computer can significantly increase the efficiency of existing fuel metering systems, and can also be used for calibration tests both on the ground and in flight.

An Approach to Robust Control of Aircraft Motion

2023-11-22T10:15:58+02:00

The article deals with approaches to designing aircraft control systems based on the robust synthesis. The mathematical model of the aircraft control system both for deterministic and stochastic cases is considered. The Dryden filter models are represented. The state-space conception is applied. The concept of robust designing based on H-infinity synthesis, function of the mixed sensitivity, and loop shaping is represented. The features of Robust Control Toolbox necessary for automated designing of aircraft control systems are studied. The weighting transfer functions are proposed. Results of simulation of the synthesized robust control system are shown in the form of transient processes in lateral and longitudinal motions. The proposed approach is directed on providing the possibility of the aircraft to function in conditions of influence of disturbances. The possible applications of obtained results is control of aircraft motion in civil aviation.