Izdelava algoritma za določanje pozicije poškodbe izolacije na vodniku statorskega navitja

Gladek, Mark (author), Nagode, Marko (mentor), Oman, Simon (comentor)

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 poškodbe izolacije na statorju elektromotorja. V algoritmu so bile uporabljene metode obdelave slik, kot je spreminjanje kontrasta. Za razvrščanje in nadaljnjo obdelavo pa je bila uporabljena konvolucijska nevronska mreža in K-means algoritem za grupiranje podatkov. Rezultat je bil funkcionalen algoritem za zaznavanje poškodbe, ki je z 95-% uspešnostjo identificiral poškodovan pol in z 87-%, 41-%, 94-% uspešnostjo identificiral lokacijo poškodbe po višini, debelini in širini statorja.

• Language: Slovenian
• Keywords: umetna inteligenca, konvolucijske nevronske mreže, strojni vid, klasifikacija slik, obdelava slik
• Work type: Master's thesis/paper
• Typology: 2.09 - Master's Thesis
• Organization: FS - Faculty of Mechanical Engineering
• Place of publishing: Ljubljana
• Publisher: [M. Gladek]
• Year: 2023
• Number of pages: XXII, 55 str.
• PID: 20.500.12556/RUL-145043
• UDC: 004.8:004.9:519.6:621.43(043.2)
• COBISS.SI-ID: 147471875
• Publication date in RUL: 31.03.2023

GLADEK, Mark, 2023, Izdelava algoritma za določanje pozicije poškodbe izolacije na vodniku statorskega navitja [online]. Master’s thesis. Ljubljana : M. Gladek. [Accessed 2 April 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=145043

Secondary language

• Language: English
• Title: Development of an algorithm for determining the insulation damage position on the stator winding wire

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.

• Keywords: artificial intelligence, convolutional neural networks, machine vision, image classification, image processing