prikaz prve stranice dokumenta Automatizirana sortirnica za grah
  Download
PDF 8.22 MB
master's thesis
Automatizirana sortirnica za grah
Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2023. urn:nbn:hr:235:391827
Maletić, Ivan
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture

Institutional repository: Repository of Faculty of Mechanical Engineering and Naval Architecture University of Zagreb

Cite this document

Maletić, I. (2023). Automatizirana sortirnica za grah (Master's thesis). Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:235:391827

Maletić, Ivan. "Automatizirana sortirnica za grah." Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2023. https://urn.nsk.hr/urn:nbn:hr:235:391827

Maletić, Ivan. "Automatizirana sortirnica za grah." Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2023. https://urn.nsk.hr/urn:nbn:hr:235:391827

Maletić, I. (2023). 'Automatizirana sortirnica za grah', Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, accessed 17 November 2024, https://urn.nsk.hr/urn:nbn:hr:235:391827

Maletić I. Automatizirana sortirnica za grah [Master's thesis]. Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture; 2023 [cited 2024 November 17] Available at: https://urn.nsk.hr/urn:nbn:hr:235:391827

I. Maletić, "Automatizirana sortirnica za grah", Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:235:391827

Metadata
TitleAutomatizirana sortirnica za grah
Title (english)Automatizen beans sorter
AuthorIvan Maletić
MentorTomislav Stipančić (mentor)
GranterUniversity of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Zagreb
Defense date and country2023-07-20, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Abstract
U sklopu ovog diplomskog rada opisan je postupak razvoja linije za automatizirano sortiranje plodova graha. Linija je zamišljena na način da se iz nesređenog stanja (hrpe) zrna graha odvajaju pojedinačno te nakon toga, s određenim razmakom, dolaze na konvejer. Iznad konvejera nalazi se kamera koja kontinuirano snima stanje te šalje podatke na računalo. Na računalu se obrađuje signal s kamere i koristi se kao ulaz u neuronsku mrežu koja prepoznaje 3 klase - dobar, loš i ništa. Klasa dobar predstavlja sliku na kojoj se nalazi zrno graha koje je ispravnog oblika, boje i veličine. Klasa loš predstavlja sliku na kojoj se nalazi zrno graha s bilo kojom vrstom oštećenja - otkinut dio zrna uslijed djelovanja sile prilikom prijašnje obrade, promjena boje uslijed djelovanja vlage, premala veličina i slično. Klasa ništa predstavlja sliku bez prisutstva zrna graha. U normalnom režimu rada stroja to su sva moguća stanja. Izlaz neuronske mreže određuje poziciju servo motora čiji nastavak usmjerava zrno prema odgovarajućem izlazu. Kroz rad su detaljno prikazani procesi razvoja svake komponente sustava te su dani razlozi za odabir kupovnih komponenti.
Abstract (english)
This masters thesis describes the process of developing a line for automated sorting of bean grains. The line is designed in such a way that individual grains of beans are separated from an unsorted state (pile) and then, at a certain distance, they come onto a conveyor. Above the conveyor, there is a camera that continuously records the state and sends the data to a computer. The camera signal is processed on the computer and used as input to a neural network that recognizes 3 classes - good, bad, and nothing. The class good represents an image containing a bean grain that is of correct shape, color, and size. The bad class represents an image containing a bean grain with any type of damage - a broken part of the grain due to previous excessive force, color change due to moisture, undersized grain, and so on. The nothing class represents an image without the presence of a bean grain. In normal machine operation mode, these are all possible states. The output of the neural network determines the position of a servo motor whose extension directs the grain towards the corresponding output. The thesis provides a detailed presentation of the development processes of each system component and gives reasons for choosing commercial components.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:235:391827
Study programmeTitle: Mechanical Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-07-06 13:29:12