umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Defect detection and classification on painted specular surfaces
Umeå University, Faculty of Science and Technology, Department of Mathematics and Mathematical Statistics.
2018 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

The Volvo Trucks cab plant in Umea is one of the northern Sweden’s largestengineering industries. The plant manufactures only cabs for trucks and is one of the most modern production plants in the world. Despite a highly automated and computerized system among many processes, the paint quality inspection process is still mainly performed manually. A real-time automated and intelligent quality inspection for painted cabs is highly desired to decrease the costs and at the same time to increase both the production efficiency and the product quality. This project is one step forward to the automation of paint quality control. Two different issues were treated during this project, namely defect detection and defect classification. These problems were solved by feeding four statistical approaches such as support vector machine, random forests, k-nearest neighbors and neural networks with extracted histogram of oriented gradients features from the captured images. The results revealed that support vector machine and random forests outperformed their contenders in terms of accuracy to both detect and to classify the defects.

Abstract [sv]

Volvokoncernens hyttfabrik i Umeå är en av Norrlands största verkstadsindustrier.Hyttfabriken tillverkar bara hytter för lastbilar och tillhör en av världens modernaste produktionsanläggningar. Trots ett hög automatiserat och datoriserat system bland många processer så är kvalitetsinspektionen av målade hytter fortfarande utförd manuellt. En smart och automatiserad kvalitetskontroll kan leda till lägre kostnader, högre kvalitet samt högre produktions effektivitet. Den här studien är ett steg framåt mot en automatiserad kvalitetskontroll. Två slagsproblem undersöktes närmare i den här studien nämligen defekt inspektion och defekt klassificering. Dessa problem åtgärdades genom att förse fyra statistiskametoder, support vector machine, random forests, k-nearest neighbors och neuralnetworks, med extraherade HOG egenskaper från tagna bilder. Resultaten visade att support vector machine och random forests presterade bättre än dess konkurrenter i förhållande till förmågan att både inspektera och klassificera defekter.

Place, publisher, year, edition, pages
2018. , p. 55
National Category
Natural Sciences Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:umu:diva-146063OAI: oai:DiVA.org:umu-146063DiVA, id: diva2:1193907
External cooperation
Volvo lastvagnar Umeå
Presentation
2018-03-02, Umeå, 10:37 (English)
Supervisors
Examiners
Available from: 2018-04-16 Created: 2018-03-28 Last updated: 2018-04-16Bibliographically approved

Open Access in DiVA

fulltext(9288 kB)96 downloads
File information
File name FULLTEXT01.pdfFile size 9288 kBChecksum SHA-512
71cc01f6161ad33bf6090cf583fedb0bc1eaadb777883f6ef6812c88e6e8ba186e579dfc1b0e69dbde36eb885933efeac3aa82f5e4ddcfd76e0468e434a374d1
Type fulltextMimetype application/pdf

By organisation
Department of Mathematics and Mathematical Statistics
Natural SciencesProbability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar
Total: 96 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 160 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf