Theses (Department of Electrical Engineering and Mechatronics)
Állandó link (URI) ehhez a gyűjteményhez
Theses collection of the Department of Electrical Engineering and Mechatronics. The collection was started in 2023.
At the University of Debrecen, in accordance with the 2022 amendment to the 2011 Higher Education Act, student theses are only accessible from devices connected to the University's Eduroam WiFi network or from a university IP address.
“The thesis or diploma work of a student who has successfully passed the final examination shall be stored in full in the academic system of the higher education institution, and a record shall be maintained thereof. The stored theses and diploma works – with the exception of parts classified as confidential in accordance with the relevant legislation – must be made accessible and searchable without restriction through the academic system.” Further info on the National Higher Education Act in Hungarian: Felsőokt. tv. (új) - 2011. évi CCIV. törvény a nemzeti felsőoktatásról - Hatályos Jogszabályok Gyűjteménye.
Böngészés
legfrissebb feltöltések
Megjelenítve 1 - 20 (Összesen 94)
Tétel Embargó alatt Swarm-robotic exploration for mapping unknown environments using a novel approach.Abdiev, Bobur; Abdulkareem Almusawi, Husam; DE--Műszaki KarCurrently swarm applications are gaining huge interest among almost all engineering areas. Especially exploration of environments where global knowledge is limited scenarios. For instance, search and rescue operations in the after-disaster locations, extra-terrestrial environments, and hazardous environment where autonomous operations, robustness, and self-organization ability are required the most. Due to the high demand in various applications and existing research gap in research area, I focused on the construction and improvement of swarm-based exploration framework. The given system in this thesis works by deploying frontier-based search mechanism in an environment which is represented by occupancy grid. To improve the efficiency of the whole system I implemented a non-conventional PSO (particle swarm optimization) algorithm-based path planning method which showed great improvement over other conventional methods. The proposed system explores and maps the environment fully autonomously, while sharing the local maps among the members of the swarm. In addition, the system was built in ROS2(robotic operation system) system with the combination of python programming language which gives great advantages for future deployment of the framework into real robot environment.Tétel Korlátozottan hozzáférhető MOTION TRIGGERED SURVEILLANCE CAMERA USING RASPBERRY PIWALUCHIO, ELVIS ODONGO; ALOWMARI, AHMED; DE--Műszaki KarIn spite of breakthroughs in science and technology, safety remains to be of paramount significance. Technologies for surveillance are being developed in response to the need to protect our physical spaces, belongings, and health. Cameras are important because they serve as attentive observers who constantly scan our environment. Though important, standard security systems can have shortcomings. Surveillance systems fill in these holes and provide an extra layer of security. In addition to serving as a deterrent, real-time surveillance allows homeowners or security experts to take prompt action and stop minor issues from getting worse. Cameras provide actual proof in the event of an occurrence. It presents significant evidence. Contemporary surveillance system users can access live feeds and recordings online while they're not there using cell phones or PCs. A quicker response to crises, such as fire alarms, break-ins, or medical problems, is made possible by this remote access. These systems offer scalability and freedom. Our approach uses an inexpensive single-board computer called Raspberry Pi4B to offer an adjustable surveillance device. Our motion-activated camera system improves resource consumption efficiency by only gathering important events. This project offers a framework for upcoming advances in surveillance technologies in addition to meeting current needs. Through embracing innovation, we help build a future in which security is achieved through constant innovation and the smooth integration of tracking into our day-to-day activities, rather than as an extravagance.Tétel Korlátozottan hozzáférhető MILLING TOOL WEAR MEASUREMENT BASED ON ANALYSING SOUND RECORDRazzokov, Nurmukhamad; Keszán, László; DE--Műszaki KarDesign improvement of Finite Impulse Filters (FIR) and Infinite Impulse Filters (IIR) are basic requirements in various kinds of areas (Production, Aerospace fields, Neuro, Telecommunication …. etc) as main task is signal transmission depends on choosing appropriate software. Correctly formulated mathematical functions play a significant role to optimize digital signal processing, synthesizing on (FIR) and (IIR) configuration in real–time process. In this case, the simulation of digital signal architectures provides economizing energy efficiency, high-quality data exchanging speed, and frequency control for reducing approximate errors on analytical digital signals on CNC machine. Determining estimated errors and defect tools by sound power detection. Furthermore, experimental architectural module solutions depend on hardware examples. In addition, most scientific results showed that network systems should have reconfigurable and low-complication modules. In this way increasing opportunity of machine operator is important purpose.Tétel Korlátozottan hozzáférhető Machine Learning-Based Detection of 2 Riders of E-ScootersHammoud, Walid; Szilágyi, Péter; DE--Műszaki KarThe thesis is about detecting the number of people on an e-scooter using supervised machine learning. The purpose of this project is to train a model to distinguish between single-driver and double-driver on an e-scooter, this should be done through a series of measurements with different people, people with experience, and not, those of different sizes and heights. After having some graphs using an accelerometer, the gathered data is used to train the model, and then it will be trained to differentiate between the number of people in an e-scooter.Tétel Korlátozottan hozzáférhető Upper Limb Prothesis Development Based on EMG ControlPena Martinez, Jhon Nicolas; Almusawi , Husam Abdulkareem; DE--Műszaki KarThis thesis presents the design and development of upper limb myoelectric prostheses with a focus on Fused Deposition Modelling (FDM) manufacturing and anthropomorphic design, aimed at laying the foundation of a functional prothesis that can improve the quality of life of the user. Two prototypes were elaborated under the scope of the thesis: an artificial tendon-driven-finger-based arm with twelve degrees of freedom and a linkage-driven-finger-based hand with six degrees of freedom. The former integrates electromyography (EMG) signal acquisition and processing along with a developed standard servo control algorithm. The second prototype presented an improvement in reliability by enabling the development of a symbolic kinematic model - a notable contribution due to the scarcity of these models in prosthetic literature-. This mathematical model allows for predictability in artificial finger motions, thus contributing to the development of a robust, precise control system. Additionally, a custom-designed printed circuit board (PCB) was developed to integrate EMG inputs, inertial sensors (IMU), PWM control, and encoder feedback for DC motor actuation. By addressing the recognized gap in literature this project contributes towards a medically validated myoelectric prothesis with full symbolic mathematical modelling with precise control algorithm.Tétel Korlátozottan hozzáférhető The Design and Model of a 6DOF Industrial Robotic Arm for Cutting ApplicationsElhusseini, Nabil; Korsoveczki , Gyula; DE--Műszaki KarThis thesis presents the design and development of a 6DOF laser cutting robotic arm, emphasizing its kinematic modeling, trajectory smoothing, and MATLAB use to for testing. A 3D model is created using SolidWorks. Kinematic analysis employs Denavit-Hartenberg (DH) parameters to establish transformation matrices between joints and the end effector. Matlab was used for trajectory smoothing, optimizing motion paths for precision, efficiency, and reduced mechanical wear. Simulation and experimental validation confirm improved cutting speed and accuracy, making the arm suitable for high-precision manufacturing applications.Tétel Korlátozottan hozzáférhető Detection of safety vests and face recognitionDanabek, Magzhan; Taleb Abdullah Abdo, Mayar; DE--Műszaki KarIn this paper, we describe a real-time detection system that utilizes a live feed through a camera to identify workers and detect protective safety vests using algorithms based on deep learning. Due to large and complex sites the proposed project will automate the process by providing real-time alerts to safety supervisors by email to ensure corrective action of the violation. The system combines FaceNet, a facial recognition model to identify workers, and YOLOv8n, technology that can analyse real-time video footage to identify personnel and assess safety compliance protocols. The proposed dual functioning system coded with Python and developed in Jupyter Notebook is designed to adapt to a variety of industrial environments. Custom dataset of 15 individual worker images in varying light conditions, different poses, occlusions and with labelled PPE data were made to meet specific algorithmic training requirements. Testing phases have effectively demonstrated positive results of the system, where it recognises faces and detects safety vests with high accuracy of 0.81 for both facial recognition and PPE detection.Tétel Embargó alatt Organic Human Robot Interaction in the Framework of Industry 5.0Haq, Inzimam Ul; Korondi, Péter; DE--Műszaki KarThis study examines recent research on the concept of flow state in relation to Human-Robot Interaction (HRI), with a particular emphasis on Collaborative Robots (Cobots). As we transition into Industry 5.0, Cobots have been utilized for an extended period; however, their impact on the emotional and cognitive dimensions of operators and workers has been explored only infrequently. Notably, the design process continues to adopt a robot-centered approach, despite the increasing significance of human roles in Cobots operations. Given that effective collaboration between humans and Cobots is essential for achieving shared objectives, any shortcomings in either party can drastically hinder overall efficiency and productivity. Therefore, it is crucial to prioritize user experience and seek innovative strategies to enhance the emotional and cognitive well-being of human operators. Additionally, the dynamics of communication between Cobots and humans will be a key focus in our study. The multimodal approach of our study will be crucial for finding the flow experience in industrial setupsTétel Embargó alatt Design and Control of Toyota Camry 2021Maalim, Abdiwahid Abdullahi; Babangida , Aminu; DE--Műszaki KarThe thesis explores the contribution of Hybrid Electric Vehicles to sustainable transportation through emission reduction and less reliance on fossil fuels. A literature review describes the major advantages of Hybrid Electric Vehicles over traditional Internal Combustion Engine (ICE) vehicles and fully electric vehicles. An extensive survey of control techniques in Hybrid Electric Vehicles is presented. The vehicle dynamics of the 2021 Toyota Camry is also assessed. Variable-structure dynamic models of conventional and hybrid vehicles are created in MATLAB to analyze their performance. Results confirm the improved fuel economy and smoother acceleration performance of Hybrid Electric Vehicles, sustaining the proposition that Hybrid Electric Vehicles are a sustainable transportation solution capable of bridging the gap between ICE and fully electric vehicles.Tétel Korlátozottan hozzáférhető Digital extension of industrial automated production line for digital factory conceptionAnka, Samer; Korsoveczki, Gyula; DE--Műszaki KarThis Thesis discusses the digitalization process of the machine auditing and defect handling system in the Unilever factory, Nyírbátor. The configuration of the system is done using the lean tools. The system went through a performance assessment and data are collected for the purpose of optimising efficiency, productivity, competitiveness and audit performance. The thesis work serves as a part of Unilever’s sustainability plan. Eventually, the digital centerlining was configured for all the lines in the factory. The outcome of the performance assessment and data analysis shows the positive correlation between the implementation of the centerlining and increase in the overall line effectiveness (OLE) and results into enhancing the business of the factory.Tétel Korlátozottan hozzáférhető Development of a Soil Quality Assessment Remote Controlled Robot Using Raspberry PiSomuah, Gideon Yaw Ahenkrah; Abdullah, Mayer Taleb; DE--Műszaki KarThis thesis aims to leverage the Raspberry Pi platform to design and implement a remote-controlled (RC) robot for soil quality assessment. The robot measures key soil parameters such as moisture, pH, salinity, temperature, humidity, and nutrient levels (Nitrogen, Phosphorus, and Potassium). It integrates robotics, sensor technology, and remote communication to provide farmers with an affordable precision agriculture tool. The robot features a robust mechanical platform powered by four DC geared motors for navigation and a stepper motor for precise soil sensor placement. The Raspberry Pi serves as the central processor, collecting sensor data, controlling motors, and streaming real-time video and soil data to a webpage accessible via Wi-Fi or a mobile hotspot. Designed in Autodesk Inventor and fabricated with PLA material using a CraftBot+ 3D printer, the robot promotes sustainable agriculture by minimizing manual labor and optimizing available resources.Tétel Korlátozottan hozzáférhető Solar Cells in Smart Cyber Physical SystemsJamil, Muhammad Umer; István, Balajti; DE--Műszaki KarThis thesis focuses on optimizing energy generation in vertical bifacial solar panels for desert environments by harnessing both direct and reflected sunlight. Through MATLAB and Simulink simulations, bifacial panels demonstrate a 20-30% higher energy yield compared to traditional monofacial panels due to rear-side albedo capture. Key challenges such as dust accumulation, temperature variations, and wind loads are addressed by integrating AI-driven Smart Cyber-Physical Systems (S-CPS) for real-time monitoring, adaptive orientation, and automated maintenance. The results highlight significant efficiency improvements and operational resilience, making vertical bifacial systems a sustainable and cost-effective solution for large-scale energy production in arid regions. Future work explores further optimization through advanced AI algorithms and materials for enhanced energy capture.Tétel Embargó alatt Motion Analysis of Industrial Robotic Arm in Singularity EncounterYasser Hassan Mohamed Elkamshoushy, Yara; Korsoveczki, Gyula; DE--Műszaki KarWe will mainly be discusses the topic of singularities. More importantly, how the mathematical representation i.e., inverse kinematics calculations relevance to World (Cartesian) and Joint spaces. More importantly, we will understand their benefit in terms of understanding the motion of the robot. Moreover, we will delve into simulations of software RoboDK and MATLAB to utilize these kinematic advantages. Furthermore, we will compute inverse kinematic calculations by extracting the homogeneous transformation matrix from prior examples (and new examples) using a MATLAB code that was purposely created to display the individual joint angles based on the final homogeneous transformation matrix. Moreover, we will construct a singularity detection algorithm to detect the elbow and shoulder singularities. We will finally test these parameters with a few case studies of the Mitsubishi RV-2AJ 5 degree of freedom robot. All joint angles are compared to the actual, and an analysis of the accuracy will be made. Prospects include utilizing the results and the simulations made to create a trajectory.Tétel Embargó alatt Kinematic Analysis and Motion Simulation of Six Degrees of Freedom FANUC Robotic ArmAttar, Mohammed Afif; Korsoveczki, Gyula; DE--Műszaki KarThis thesis presents a comprehensive kinematic analysis and motion simulation of the FANUC LR Mate 200iD/ER4iA robotic arm. Using the Denavit-Hartenberg (D-H) convention, the forward kinematics of the six-joint manipulator are modeled and validated, calculating the homogeneous transformation matrix to determine the end-effector's position and orientation. MATLAB is employed to compute kinematic parameters and simulate joint movements, while RoboDK provides a visual analysis of the kinematic model. The inverse kinematics are analyzed through the Jacobian matrix, offering insights into joint velocities and end-effector dynamics. Furthermore, a Unity-based simulation integrates these findings into a virtual environment, enhancing visualization and validating the robot's real-world behavior.Tétel Korlátozottan hozzáférhető Simulation of Mobile Robot Movement Around ObstaclesAttar, Mohammed Atif; Mikuska, Robert; DE--Műszaki KarMobile robotics has completely revised automation, healthcare, and exploration. This paper thesis discusses about obstacle avoidance, path planning, and simulation environments. Advanced sensors, such as LiDAR and stereo cameras, allow mapping and decision-making in real time. Techniques such as the point cloud data and filtering it to maintain the data within LiDAR and stereo camera range, ensure safe navigation in dynamic settings. Simulations using MATLAB and Autodesk Inventor allow for design optimization and testing, minimizing risk and costs. Features like sensor fusion, occupancy grid mapping, and adaptive path adjustment enhance navigation. This research advances mobile robotics, highlighting simulation's role in bridging theory and practice for autonomous systems.Tétel Korlátozottan hozzáférhető Advanced Health Monitoring System with Mobile ApplicationSayed, Hana Hesham Ibrahim; István, Balajti; DE--Műszaki KarThis paper outlines the development of a prototype health monitoring system. This system integrates five specifically chosen sensors based on their plethora of connections and low cost, which address cost-efficiency concerns. The five sensors are heart rate, pulse oximetry, temperature, galvanic skin response (GSR), and blood glucose for diabetes monitoring. The Raspberry Pi 5 was selected as the controller for this system. This addresses accessibility concerns since it’s an open-source platform. In today's world, artificial intelligence represents a significant breakthrough. As a result, machine learning algorithms were utilised for this project. Several machine learning models were tested to choose the most suitable and appropriate for anomaly identification and data analysis. This paper also presents the integration of a mobile application for visualising the data and offering insights into the user’s health status. This system aims to monitor a person’s health data in real time, facilitating early detection of potential health issues.Tétel Embargó alatt Comparisons of artifical intelligence algorithms for collision avoidance in the field of Collaborative robotsJagoda Don, Danidu Rushmika Jagoda; Peter, David Nasser; DE--Műszaki KarV. SUMMARY The main objective of this thesis was to compare artificial intelligence algorithms for collision avoidance in the field of collaborative robots. Moreover, the main task was to identify algorithms that are used for collision avoidance and use these methods as a part of a neural network, to test and understand which algorithm is the most efficient, accurate, and fastest to incorporate learning. Apart from the algorithms we dived into the implementing a neutral neural network architecture which doesn’t complement any algorithm. Benefit of using the proposed Feed-Forward Neural Network is that learning happens unidirectionally and allows the algorithms themselves to make their own modifications in order to obtain the best-predicted results. Apart from this, the main challenge was to design a couple of digit fields where the algorithm can be tested for the collaborative robot. 4 environments were created, and every single environment had different amounts of dynamic and static objects. The environments surrounding from 1-4 were built to test the KUKA LBR4+. The pretext under the design of these environments was that the difficulty should arise from the first to the last one. The 3rd simulation environment consisted of the most objects, and this resulted in showcasing unexpected results. Conjointly, environment 4 was built to be the most unpredictable, trying to replicate a real-life scenario. Moreover, all four, Levenberg-Marquardt, Resilient Backpropagation, Scaled Conjugate Gradient, and Bayesian Regularisation were simulated in all the environments. A total of 64 simulations were conducted, the breakdown of the 64 is as follows; 4 environments to test, 4 algorithms proposed, and repeating the simulation 4 times to obtain an average and observe more accurate results. The creation of a neural network to implement an AI solution was the main purpose of this thesis.Tétel Embargó alatt ANALYSIS AND CONTROL STRATEGY DEVELOPMENT OF AN ELECTRIC VEHICLE REGENERATIVE BRAKING SYSTEMStocco Richter, Camila; Almusawi, Husam Abdulkareem; DE--Műszaki KarThis thesis investigates the development of a temperature-dependent regenerative braking system for electric vehicles, describing the implementation of fuzzy logic control to allocate braking force between regenerative and conventional braking techniques. The control strategy employs thermal feedback techniques that improve energy recovery dynamically, while simultaneously mitigating the risks associated with overheating and battery degradation. Simulations conducted with MATLAB/Simulink demonstrate a 10% improvement in driving range and a 16.7% extension in operational cycles. The proposed system exhibited efficiencies of 0.58 in POWER mode and 0.73 in regenerative mode, while simultaneously achieving a reduction in energy losses associated with the motor and controller by 63.6%. The findings indicate the significance of regenerative braking within the context of electric vehicle research and development.Tétel Embargó alatt Design of a smart predictive maintenance system for automotive components using MATLABMuhammad, Abubakar Dalhatu; Babangida, Aminu; DE--Műszaki KarThe design of a longitudinal smart predictive maintenance system for automotive components using MATLAB is presented. Advantages of predictive maintenance are emphasized, while Remaining Useful Life (RUL) estimation, Prognostics and Health Management (PHM), and Digital Twins are considered as key concepts. Methods are sought to integrate Machine Learning (ML) algorithms into forecasting, a methodology developed for predictive maintenance model development of a quarter car suspension using simulated fault data, and of an automotive engine using public datasets. The paper presents and discusses results, and later concludes with the areas of the benefits of the method in terms of predicting and improving the target performance of the models.Tétel Embargó alatt Designing and modelling of an automation environment in the digital spaceMensah-Hammond, Nicholas; Nusser Dávid, Péter; DE--Műszaki KarThis paper discusses the design and realization of an automated storage system utilizing racks and stacker cranes. Factory IO was used for the modelling, and TwinCAT was used for the management of Programmable Logic Controller control, facilitating the automation of storage and retrieval processes. The focus of this paper includes the analysis of the of the completed project, the review of the relevant literature on common elements of automated storage systems, and presenting the technical knowledge required for building the system. By focusing on the system’s technical foundation, the paper aims to present a viable solution for automated storage and retrieval processes in industrial environments.