diplomsko delo
Andrej Jukić (Author), Riko Šafarič (Mentor), Simon Klančnik (Mentor), Tadej Peršak (Co-mentor)

Abstract

V diplomskem delu so na začetku predstavljena obravnavana področja, kjer se teoretično spoznamo s proizvodnimi sistemi, umetno inteligenco, klasifikacijo, učnimi algoritmi, merami za ocenjevanje in z obdelovalnim postopkom rezkanja. Bistvenega pomena je področje klasifikacije in mer za ocenjevanje, zaradi tega sta ti dve področji bolj podrobno opisani. Po teoretičnem izhodišču sledi poglavje praktične izvedbe, pri katerem smo predstavljeno teorijo uresničili. V tem sklopu so opisani trije poizkusi, kjer smo preverjali zastavljene teze s pomočjo gravirnega stroja Lakos 150 in računalniškega programa Matlab, ki je podpiral strojno učenje (klasifikacijo). S poizkušanjem smo tako potrdili vse teze, dosegli večino zastavljenih ciljev, pri čemer nismo dosegli glavnega cilja dela (uspešna klasifikacija glede na status orodja) zaradi strokovne zahtevnosti področja.

Keywords

umetna inteligenca;strojno učenje;klasifikacija;rezkanje;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [I. Jovanovič]
UDC: 004.85:621.937(043.2)
COBISS: 139369475 Link will open in a new window
Views: 78
Downloads: 12
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Tool condition monitoring using artificial intelligence
Secondary abstract: In the diploma work, the discussed areas are presented at the beginning, where we get to know theoretically about production systems, artificial intelligence, classification, learning algorithms, evaluation measures and the machining process of milling. The area of classification and evaluation measures is of vital importance, so these two areas are described in more detail. The theoretical starting point is followed by the chapter on practical implementation, in which we put the presented theory into practice. In this section, three experiments are described, where we checked the proposed theses with the help of the Lakos 150 engraving machine and the computer program Matlab, which supported machine learning (classification). Through experimentation, we confirmed all theses, achieved most of the set goals, but did not achieve the main goal of the task (successful classification according to the status of the tool), due to the professional complexity of the field.
Secondary keywords: artificial inteligence;machine learning;classification;milling;
Type (COBISS): Bachelor thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Mehatronika
Pages: 1 spletni vir (1 datoteka PDF (XV, 50 f.))
ID: 16431916