Primjena metodologije umjetne inteligencije i strojnog vida u području mjeriteljstva

master's thesis

• Title (english): Application of the methodology of artificial intelligence and machine vision in the field of metrology
• Author: Ines Frajtag
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2023-12-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing; Artificial Intelligence

Abstract

Mnogo je optičkih mjernih uređaja koji se danas koriste u kontroli kvalitete, a svaki od njih koristi barem neki algoritam koji spada u kategoriju strojnog učenja i umjetne inteligencije. Na temelju jednog takvog uređaja analizirat će se njegov rad i algoritmi za prepoznavanje oblika, detekciju rubova i detekciju kontura. Kako bi predmet mjerenja bio što manje ovisan o mjeritelju, napravljen je i nosač koji je postavljen na uređaj i na kojem je, nakon izrade programa, izmjereno sto uzoraka i alat kojim su oni napravljeni. Na temelju izmjera napravljena je analiza o potrošnji alata na navedenim uzorcima. Ovisnost izmjera oduvijek je povezana sa načinom osvjetljenja te su u radu navedena najčešća osvjetljenja i koja se od njih koriste na mikroskopu i optičkom profilometru. Na uređajima je napravljen i test koji pokazuje varijacije u dimenzijama ovisno o osvjetljenju.

Abstract (english)

There are many optical measuring devices used in quality control today, and each of them
employs at least some algorithm falling into the category of machine learning and artificial
intelligence. Based on one such device, its operation and algorithms for shape recognition, edge
detection, and contour detection will be analyzed. To minimize the dependence of the
measurement object on the operator, a fixture has been created and placed on the device. After
programming, a hundred samples were measured with the tool created. An analysis of tool wear
on the specified samples was conducted based on the measurements. The dependency of
measurements has always been associated with the lighting conditions, and the most common
illuminations used on the microscope and optical profilometer are mentioned in the paper. A
test was conducted on the devices to show the variations in dimensions relative to the lighting
conditions.

• Keywords: rubovi; konture; prepoznavanje oblika; kontrolni uređaj; mikroskop; nosač; osvjetljenje
• Keywords (english): edges; contours; shape recognition; control device; microscope; fixture; illumination
• Language: croatian
• URN:NBN: urn:nbn:hr:235:304422
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Embargoed access; Embargo expiration date: 2025-12-07
• Created on: 2023-11-30 18:37:42