Repository of FERIT Osijek
Not a member yet
4053 research outputs found
Sort by
Components and applications of smart power grids
No full textKroz diplomski rad opisan je pojam napredne mreže i njegova razlika od sadašnje, konvencionalne mreže. Definirane su napredne komponente unutar naprednih mreža i njihova uloga u poboljšanju pouzdanosti, učinkovitosti i održivosti elektroenergetske mreže te ovaj rad pruža uvid u razumijevanje komponenti i njihovog doprinosa za moderniji i sofisticiraniji sustav. Diplomski rad se sastoji od dva glavna dijela, a to su teorijski dio i praktični dio. U teorijskom dijelu se detaljno opisuju različite komponente napredne mreže kao što su pametni uređaji, pametni senzori, sustavi za pohranu energije i sustavi za napredno mjerenje. Opisana je struktura njihovog upravljanja, prednosti i izazovi integracije tih komponenti u kontekstu naprednih mreža. Praktični dio diplomskog rada uključuje izradu nadomjesne sheme sastavljenog ormara, u zgradi Fakulteta elektrotehnike, računarstva i informacijskih tehnologija u Osijeku, koji predstavlja mikromrežu. Osim nadomjesne sheme, u praktičnom dijelu se opisalo pametno brojilo ET340, njegova instalacija i spajanje s uređajima za komunikaciju. Obradila su se i mjerenja električnih veličina koje su bitne za rad mikromreže te njihova analiza. Mjerenja uključuju razmjenu energije s mrežom, proizvodnju iz fotonaponskog sustava, razmjenu snage s baterijom, stanje napunjenosti i potrošnju energije, a sva su mjerenja provedena tijekom mjernog razdoblja od 24 sata. Kombinirajući teorijsko znanje s praktičnim mjerenjima i njihovom analizom, diplomski rad nudi sveobuhvatno istraživanje naprednih komponenti u naprednim mrežama.The master's thesis describes the concept of an advanced grid and its difference from the present, convencional grid. Advanced components within advanced grid and their role in improving the reliability, efficiency and sustainability of the power grid are defined. This thesis provides insight into the understanding od components and their contribution to a more modern and sophisticated system. The master's thesis consists of two main parts, the theoritical part and the practical part. The theoritical part provides a detailed description of various components of an advanced grid, such as smart devices, smart sensors, energy storage systems and advanced measurement systems. The structure of their management, advantages and challenges of integrating these components in the context of advanced grid are described. The
practical part of the master's thesis includes the making of a substitution scheme for an assembled cabinet in the building of the Faculty of Electrical Engineering, Computer Science and Information Technology in Osijek, which represents a microgrid. In addition to the substitution scheme, the practical part describes the smart meter ET340, its installation and
connection with communication devices. The measurement of electrical quantities essential for the operation of the microgrid and their analysis are also described. The measurements include energy exchange with the grid, production from the photovoltaic system, power exchange with the battery, state of charge and energy consumption, all of them were performed during a 24-hour measurement period. By combining theoretical knowledge with practical measurements and their analysis, the master's thesis offers a comprehensive exploration of advanced components in advanced grids
Algorithm for extracting signposts from the scene and understanding the text on them
No full textU sklopu ovog rada razvijen je algoritam za detekciju putokaza u sceni i razumijevanje teksta na njima, koristeći vlastitu bazu podataka. Cilj je bio izolirati putokaze iz scene i razumjeti tekst na njima, uključujući smjer na koji pokazuju. Algoritam je izgrađen koristeći metode dubokog učenja, odnosno YOLOv7 za detekciju putokaza i smjera na njima, u kombinaciji s OCR alatima
za razumijevanje teksta. Razvoj algoritma proveden je u Python programskom okruženju. Testiranja su provedena na različitim slikama, koje su snimljene u različitim uvjetima. Rezultati su pokazali visoku točnost detekcije putokaza i smjera na njime te razumijevanja teksta, ali i prostor za poboljšanje u situacijama kada su putokazi djelomično zaklonjeni ili kada je kvaliteta
slike niska. Algoritam predstavlja dobar korak prema poboljšanju navigacijskih sustava kroz detekciju i interpretaciju putokaza. Iako su rezultati obećavajući, daljnja optimizacija je potrebna kako bi se poboljšala performansa u realnom vremenu i u različitim uvjetima na cesti. U okviru testiranja, posebno je važno istaknuti primjenu implementiranih algoritama na Raspberry Pi 4 ugradbenoj računalnoj platformi. Iako su početni rezultati obećavajući, primjetna je potreba za dodatnom optimizacijom kako bi se osigurala pouzdana i brza obrada slika u stvarnom vremenu zbog softverskih i hardverskih ograničenja ugradbene računalne platforme. To uključuje optimizaciju hardverskih resursa, kao i prilagodbu algoritama kako bi se što efikasnije koristili ograničeni resursi ugradbenih računalnih platformi. Činjenica koja ide u prilog tom zaključku dolazi iz usporedbe performansi rada na osobnom računalu i ugradbenoj računalnoj platformi, gdje osobno računalo pokazuje bolje performanse te je veći spektar algoritama koji se mogu koristiti.As part of this work, an algorithm was developed for the detection of road signs in the scene and the understanding of the text on them, using our own database. The goal was to isolate the signposts from the scene and understand the text on them, including the direction they point to. The algorithm was built using deep learning methods, namely YOLOv7 to detect road signs and directions on them, combined with OCR tools for text understanding. The development of the algorithm was carried out in the Python programming environment. The tests were carried out on different photos, which were taken in different conditions. The results showed a high accuracy of the detection of road signs and the direction on them, as well as understanding of the text, but also room for improvement in situations where the road signs are partially obscured or when the image quality is low. The algorithm represents a good step towards the improvement of navigation systems through the detection and interpretation of road signs. Although the results are promising, further optimization is needed to improve real-time performance under different road conditions. As part of the testing, it is particularly important to highlight the application of the implemented algorithms on the Raspberry Pi 4 embedded computer platform. Although the initial results are promising, there is a noticeable need for further optimization to ensure reliable and fast real-time image processing due to the software and hardware limitations of the embedded computer platform. This includes the optimization of hardware resources, as well as the adaptation of algorithms to make the most efficient use of the limited resources of embedded computer platforms. The fact that supports this conclusion comes from a comparison of the performance of work on a personal computer and on an embedded computer platform, where the personal computer shows better performance and the spectrum of algorithms that can be used is greater
Development and testing of SVM control of an autonomous three-phase inverter by using Typhoon HIL tools
No full textModulacija prostornog vektora jedna je od najčešće korištenih metoda upravljanja trofaznim naponskim izmjenjivačima. U ovom radu, provedena je analiza rada trofaznih naponskih izmjenjivača napona te je predstavljen matematički model modulacije prostornog vektora. Definiran je pojam prostornog vektora kojim se prikazuje referentni trofazni sustav napona kako bi se odredila vremena uključenosti upravljačkih ventila. Također, izveden je MATLAB/Simulink model algoritma s ciljem testiranja modulacije unutar Typhoon HIL sustava. Generiranje upravljačkih impulsa izmjenjivača vršeno je pomoću TMS320F2808 mikrokontrolera spojenog na Typhoon HIL hardver. Snimljeni su dobiveni upravljački impulsi te fazni i linijski naponi koji su kasnije uspoređeni s onima dobivenim u provedenoj analizi rada.Space vector modulation is one of the most commonly used methods of controlling three-phase voltage inverters. In this paper, an analysis of the operation of three-phase voltage inverters was carried out and a mathematical model of space vector modulation was presented. The concept of a space vector is defined, which shows the reference three-phase voltage system in order to determine the on-times of the control valves. Also, a MATLAB/Simulink algorithm model was developed with the aim of testing the modulation within the Typhoon HIL system. The generation of control pulses of the inverter was performed using a TMS320F2808 microcontroller connected to the Typhoon HIL hardware. The obtained control pulses and phase and line voltages were recorded, which were later compared with those obtained in the performed work analysis
Mobile application regression testing automation
No full textTestiranje je kao faza razvojnog ciklusa softvera proces kojim se osigurava što veća kvaliteta softvera. Pri tome se koriste razne strategije i oblici testiranja. Jedno od oblika testiranja je regresijsko testiranje koje provjerava sve funkcionalnosti softvera. Regresijsko testiranje se može izvoditi manualno no zbog repetitivnosti testnih slučaja testeri često automatiziraju regresijsko testiranje. Za automatizaciju testeri mogu koristiti već postojeće alate ili kreirati svoje vlastito rješenje za automatizaciju. U radu su automatizirani testni slučajevi u već postojećem alatu Tricentis Testim te je razvijeno novo rješenje za automatizaciju. Vlastito rješenje je ostvareno koristeći alat Appium te je potom vlastito rješenje evaluirano u odnosu na alat Tricentis Testim.Testing, as a phase of the software development life cycle, is a process in which the highest quality of the software is ensured. In the testing phase various test strategies are being used. One of the used strategies is regression testing in which all functionalities of the software are tested. Regression testing can be conducted manually, but because of the repetitiveness, testers usually opt for automating the regression testing. Testers can use already available solutions and tools or develop their own frameworks. In this thesis a set of five test cases were automated in a commercially available tool Tricentis Testim and the newly developed framework. The framework was developed using Appium and was later evaluated in relation to the Tricentis Testim Tool
Mobile application for active involvement of children in everyday activities
No full textCilj ovog završnog rada bio je stvoriti mobilnu aplikaciju za aktivno uključivanje mladih u svakodnevne aktivnosti. Aplikacija omogućava kreiranje, dodjeljivanje i upravljanje zadataka koje roditelj dodjeljuje djeci. Teorijski dio rada opisuje tehnologije korištene u izradi aplikacije, te opisuje slijed razvoja aplikacije. Praktični dio rada sastoji se od izrade same aplikacije. Izgled i struktura mobilne aplikacije rađeni su pomoću Jetpack Compose alata za izradu korisničkog sučelja. Funkcionalni dio aplikacije napravljen je u Kotlin programskom jeziku. Za izradu baze podataka korištena je Firebase platforma.The objective of this final project was to develop a mobile application aimed at actively engaging young people in their daily activities. The application allows for the creation, assignment, and management of tasks delegated by parents to their children. The theoretical section of this paper provides an overview of the technologies employed in application development and outlines the subsequent phases of application development. The practical part of the final project consists of creating the application itself. The layout and structure of the mobile application were constructed using the Jetpack Compose UI builder, while the functional aspect of the application was implemented in the Kotlin programming language. The Firebase platform was utilized to establish and manage the database
Application of security systems using smart installations
No full textCilj završnog rada je prikazati idejni projekt KNX sigurnosne instalacije. Prilikom izrade plana za KNX pametnu sigurnosnu instalaciju, potrebno je proći kroz sličan proces koji je prikazan u završnom radu, od upoznavanja s načinom rada određenih elemenata i opreme koja se upotrebljava u KNX instalacijama, odabirom KNX uređaja, opreme te svih potrebnih dijelova koje instalacija zahtjeva, do finalnog planiranja, odabira pozicija senzora i uređaja, završni korak provedbe instalacije u praktičnom dijelu, te programiranje uređaja i kompletne instalacije u programu ETS6. Glavni zaključak završnog rada je taj da KNX sigurnosna pametna instalacija omogućava visoku razinu zaštite i sigurnosti od vremenskih utjecaja, provalnika, te smanjuje mogućnost ljudske pogreške. Uz to, ovakav tip instalacije omogućava korisniku ekonomičniju raspodjelu električne energije kao i ostalih korištenih energenata u objektu.The goal of the final paper is to present the conceptual project of the KNX security installation. When creating a plan for a KNX smart security installation, it is necessary to go through a similar process that is presented in the final paper, from getting to know the way certain elements and equipment used in KNX installations work, choosing KNX devices, equipment and all the necessary parts that the installation requires , to the final planning, selection of sensor and device positions and the final step of implementation of the installation in the practical part, and programming of the device and complete installation in the ETS6 program. The main conclusion we can draw from the final work is that the KNX security smart installation allows us almost the maximum level of protection and security against weather influences, burglars, and reduces the possibility of human error. In addition, this type of installation allows the user a more economical distribution of electricity as well as other used energy sources in the facility
A machine-learning-based method for predicting the risk of cardiovascular diseases from a patient examination
No full textU ovom je radu u Pythonu razvijen model logističke regresije namijenjen za korištenje pri predviđanju rizika od razvoja srčanih bolesti. Nakon upoznavanja podataka te detaljne obrade istih, izgradnje i treniranja modela, dobivena je ocjena osjetljivosti od otprilike 0.746 što znači da model od 100% rizičnih slučajeva točno predviđa prisutnost rizika u 74.7% slučajeva. To ukazuje na to da, iako ne savršeno, model zaista predviđa rizik te ga se može koristiti u medicinske svrhe. Model je dakle ispunio početni zadatak predviđanja rizika, a sa daljnjim usavršavanjem i proširenjem s dodatnim podacima, tehnikama i znanjem potencijalno bi se mogla i poboljšati njegova prediktivna točnost i izvedba. Motivirano činjenicom da srčane bolesti u današnje vrijeme zauzimaju broj 1 kao glavni uzrok smrti među ljudima, ovakav model predviđanja može itekako biti od koristi jer je prevencija najbolji lijek.In this assignment, a logistic regression model was developed in Python to be used in predicting the risk of developing heart disease. After getting familiar with the data and detailed processing of it, building and training the model, a recall score of approximately 0.726 was given for the model, meaning that the model accurately predicts the presence of risk in 72.7% out of a 100% of positive cases, which indicates that, although not perfectly, the model really predicts risk. The model therefore fulfilled the initial task of risk prediction, and with further refinement and extension of the model with additional data, techniques and knowledge, its predictive accuracy and performance could potentially be improved. Motivated by the fact that heart disease is currently the number 1 cause of death among humans, this kind of prediction model can be very useful since prevention really is the best medicine
Automated generation of portrait sets using the Stable Diffusion library
No full textCilj rada je bio napraviti program za generiranje portreta koristeći Stable Diffuison biblioteku. U radu su istražene vrste generativnih modela, kako se treniraju generativni modeli, te njihove prednosti i mane. U radu također prikazan način na koji Stable Diffusion koristi difuzijske modele za generiranje slika. Na osnovu stečenih znanja napravljena je desktop aplikacija za generiranje portreta pomoću koje je testirano kako različiti parametri utječu na generiranje slike.The aim of this project isto create a program for generating portraits using Stable Diffusion library. This paper explores the types of generative models, how generative models are trained and their advantages and disadvantages. The paper also shows the way in which Stable Diffusion uses diffusion models to generate images. Based on the acquired knowledge, a desktop application for generating portraits was created, which was used to test how different parameters affect image generation
Web Application for Freelancing
No full textOsnovni zadatak ovoga diplomskog rada odnosi se na izradu web aplikacije za freelancer usluge koja pruža funkcionalnosti poput stvaranja, uređivanja, brisanja, pretraživanja poslova, zapošljavanja freelancera i dodatnih mogućnosti poput ispunjavanja upitnika. Ovim radom prikazan je postupak izrade web aplikacije za freelancer usluge upotrebom MERN tehnologija. Tehnologije MongoDB, Express.js i Node.js primijenjene su za izradu poslužitelja, a React za izradu klijenta. Uz navedeno, prikazani su rezultati anketiranja grupe registriranih korisnika. Obrada rezultata anketiranja temelji se na Likertovoj skali.The main task of this paper is developing web application for freelancer services that provides functionalities such as creating, updating, deleting, searching, hiring freelancers and additional options like filling out questionnaire. This paper presents the process of creating a web application for freelancer services using MERN technologies. MongoDB, Express.js and Node.js technologies were used to create the server and React was used to create the client. In addition to the above, the survey results of a group of registered users are presented. The processing of survey results is based on a Likert scale
Voltage deviations in distribution network with connected photovoltaic power plants
No full textU ovome radu bilo je potrebno proučiti, opisati i u konačnici testirati metode za održavanje poželjnih naponskih prilika u DM s povećanom koncentracijom FN. Naglasak je stavljen na proučavanje optimalnog rješenja za probleme koje u DM stvaraju inverzni tokovi snaga u vidu porasta napona iznad zakonski propisane vrijednosti. Najprije su teorijski obrađene navedene metode, a zatim su neke od njih testirane na već postojećoj mreži u programu DIgSILENT. Nakon provođenja simulacije i obrade rezultata izveden je zaključak o učinkovitosti navedenih metoda.In this paper, it was necessary to study, describe, and ultimately test the methods for maintaining desirable voltage conditions in the distribution network with increased photovoltaic (PV) integration. The emphasis was placed on exploring an optimal solution for issues arising in the distribution network due to reverse power flows, resulting in voltage exceeding the legally prescribed value. Firstly, these methods were theoretically addressed, and then some were tested on an existing network using the DIgSILENT software. After conducting simulations and analyzing the results, a conclusion was drawn regarding the effectiveness of the mentioned methods