prikaz prve stranice dokumenta Predikcija postupaka održavanja uljem uronjenih transformatora na temelju fizikalno-kemijskih analiza
  Download
PDF 2.9 MB
master's thesis
Predikcija postupaka održavanja uljem uronjenih transformatora na temelju fizikalno-kemijskih analiza
2024. urn:nbn:hr:200:089147
Delić, Igor
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Cite this document

Delić, I. (2024). Predikcija postupaka održavanja uljem uronjenih transformatora na temelju fizikalno-kemijskih analiza (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:089147

Delić, Igor. "Predikcija postupaka održavanja uljem uronjenih transformatora na temelju fizikalno-kemijskih analiza." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2024. https://urn.nsk.hr/urn:nbn:hr:200:089147

Delić, Igor. "Predikcija postupaka održavanja uljem uronjenih transformatora na temelju fizikalno-kemijskih analiza." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2024. https://urn.nsk.hr/urn:nbn:hr:200:089147

Delić, I. (2024). 'Predikcija postupaka održavanja uljem uronjenih transformatora na temelju fizikalno-kemijskih analiza', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 21 September 2024, https://urn.nsk.hr/urn:nbn:hr:200:089147

Delić I. Predikcija postupaka održavanja uljem uronjenih transformatora na temelju fizikalno-kemijskih analiza [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2024 [cited 2024 September 21] Available at: https://urn.nsk.hr/urn:nbn:hr:200:089147

I. Delić, "Predikcija postupaka održavanja uljem uronjenih transformatora na temelju fizikalno-kemijskih analiza", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2024. Available at: https://urn.nsk.hr/urn:nbn:hr:200:089147

Please login to the repository to save this object to your list.
Metadata
TitlePredikcija postupaka održavanja uljem uronjenih transformatora na temelju fizikalno-kemijskih analiza
Title (english)Prediction of maintenance procedures for oil-immersed transformers based on physical-chemical analyses
AuthorIgor Delić
MentorAlfonzo Baumgartner (mentor)
Committee memberAlfonzo Baumgartner (predsjednik povjerenstva)
Committee memberTomislav Keser (član povjerenstva)
Committee memberTomislav Galba (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2024-07-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
Transformatori su jako bitne komponente elektroenergetskih sustava. Njihova pouzdanost i dugovječnost utječe na stabilnost i učinkovitost cijele elektroenergetske mreže. Stoga je bitno kontinuirano pratiti i procjenjivati stanje transformatora kako bi se osigurala pravovremena intervencija i spriječili kvarovi koji mogu uzrokovati ozbiljne poremećaje i gubitke. Nakon upoznavanja s pojmovima strojnog učenja i obrade podataka naredni cilj je bio metodama strojnog učenja razviti model i aplikaciju koja će predvidjeti stanje transformatora na temelju analiza ulja te predložiti i uputiti u potrebne postupke održavanja. Uspoređeno je nekoliko algoritama za klasifikaciju, a najbolje rezultate je imao Random Forest algoritam koji je potom korišten u izradi aplikacije. Aplikacije je jednostavna za korištenje te upućuje korisnika kako bi trebao postupiti. Aplikacija je realizirana u Streamlit razvojnom okruženju koristeći Python programski jezik.
Abstract (english)
Transformers are very important components of power systems. Their reliability and longevity affect the stability and efficiency of the entire power network. Therefore, it is essential to continuously monitor and assess the condition of transformers to ensure timely intervention and prevent failures that could cause serious disruptions and losses. After familiarizing ourselves with the concepts of machine learning and data processing, the next goal was to develop a model and application using machine learning methods to predict the condition of transformers based on oil analysis and to suggest and guide the necessary maintenance procedures. Several classification algorithms were compared, and the Random Forest algorithm produced the best results, which was then used in the application development. The application is easy to use and guides the user on how to proceed. The application was implemented in the Streamlit development environment using the Python programming language.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:089147
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: sveučilišni/a magistar/magistra inženjer/inženjerka računarstva (sveučilišni/a magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2024-07-24 07:30:44