Izdelava algoritma za določanje pozicije poškodbe izolacije na vodniku statorskega navitja

magistrsko delo magistrskega študijskega programa II. stopnje Strojništvo

Mark Gladek (Author), Marko Nagode (Mentor), Simon Oman (Co-mentor)

Abstract

V inženirskih aplikacijah je strojni vid ena najbolj uporabljenih metod umetne inteligence, ki se pogosto uporablja za zaznavanje napak na raznih izdelkih. Ker so aplikacije velikokrat zahtevne, se za uspešno opravljanje nalog velikokrat združuje več različnih algoritmov. Pri obravnavanem primeru je bil zasnovan algoritem za detekcijo mesta poˇskodbe izolacije na statorju elektromotorja. V algoritmu so bile uporabljene metode obdelave slik, kot je spreminjanje kontrasta. Za razvrˇsˇcanje in nadaljnjo obdelavo pa je bila uporabljena konvolucijska nevronska mreˇza in K-means algoritem za grupiranje podatkov. Rezultat je bil funkcionalen algoritem za zaznavanje poˇskodbe, ki je z 95-% uspeˇsnostjo identificiral poˇskodovan pol in z 87-%, 41-%, 94-% uspeˇsnostjo identificiral lokacijo poˇskodbe po viˇsini, debelini in ˇsirini statorja.

Keywords

magistrske naloge;umetna inteligenca;konvolucijske nevronske mreže;strojni vid;klasifikacija slik;obdelava slik;

Data

Language:	Slovenian
Year of publishing:	2023
Typology:	2.09 - Master's Thesis
Organization:	UL FS - Faculty of Mechanical Engineering
Publisher:	[M. Gladek]
UDC:	004.8:004.9:519.6:621.43(043.2)
COBISS:	147471875
Views:	336
Downloads:	118
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Development of an algorithm for determining the insulation damage position on the stator winding wire
Secondary abstract:	Computer vision is one of the most commonly used methods of artificial intelligence in engineering applications. It is often used to detect defects in various products. As the applications are often complex, several different algorithms are often combined to perform the tasks successfully. In this master’s thesis, an algorithm was designed to detect the location of insulation damage on the stator of an electric motor. Methods such as contrast enhancement were used for image preprocessing and algorithms like convolutional neural network and K-means clustering were used for image classification and further processing. The result was a functional algorithm that identified the damaged pole with 95% success rate and identified the location of the damage by stator height, thickness, and width with 87%, 41%, and 94% success rates.
Secondary keywords:	master thesis;artificial intelligence;convolutional neural networks;machine vision;image processing;
Type (COBISS):	Master's thesis/paper
Study programme:	0
Embargo end date (OpenAIRE):	1970-01-01
Thesis comment:	Univ. Ljubljana, Fak. za strojništvo
Pages:	XXII, 55 str.
ID:	18445163