Planned maintenance
A system upgrade is planned for 10/12-2024, at 12:00-13:00. During this time DiVA will be unavailable.
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • harvard-cite-them-right
  • 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
Data Driven Quality Assurance in Laser Powder Bed Fusion
University of Borås, Faculty of Textiles, Engineering and Business.
University of Borås, Faculty of Textiles, Engineering and Business.
University of Borås, Faculty of Textiles, Engineering and Business.
2022 (English)Independent thesis Basic level (university diploma), 180 HE creditsStudent thesis
Abstract [en]

Additive manufacturing (AM), more commonly known as 3D- printing, is the process of joining materials layer by layer to fabricate an object. Today AM is used in many fields, including medical, aerospace, and automotive industries. The industries mentioned are highly regulated. Therefore, there is a need that the process monitoring and controlling must be on par with the high demands and result in a reduction of variation and ensure good quality. In this thesis work, the AM-techniques that have been utilized are Laser Powder Bed Fusion systems. When analysing the Laser Powder Bed Fusion process, there are a lot of working with large batches of data for many different data sources such as Images, sensors, log-files, point clouds, STL(CAD), 3D-scan, and CT-scan. This thesis explores a step toward quality assurance by analysing this data through digital analytics software focusing on two areas, image analysis and visualisation. The analysis covers distortions during the printing process by using edge detection to compare the printed part against a 3D-model. An improvement of this analysis using state-of-the-art machine learning is explored. The visualisation of data was compiled in various combinations through graphs, images, 3D-scan, CT-scan, Point Cloud and CAD. With the objective to detect abnormalities within 3D-printed parts.

Abstract [sv]

Additiv tillverkning (AM), mer känd som 3D-printning, är processen att sammanfoga material lager för lager för att tillverka ett objekt. Idag används AM inom många områden, inklusive medicin-, flyg- och fordonsindustrin. De nämnda branscherna är starkt reglerade. Därför finns det ett behov av att processövervakningen och styrningen ska stå i nivå med de höga kraven och resultera i minskad variation och säkerställa god kvalitet. I detta examensarbete är AM-teknikerna som har använts Laser Powder Bed Fusion-system. När man analyserar Laser Powder Bed Fusion-processen är det mycket arbete med stora mängder data från många olika datakällor såsom bilder, sensorer, loggfiler, punktmoln, STL(CAD), 3D-scan och CT-scan. Detta examensarbete utforskar ett steg mot kvalitetssäkring genom att analysera dessa data genom digital analysmjukvara med fokus på två områden, bildanalys och visualisering. Analysen identifierar distorsioner under utskriftsprocessen genom att använda kantdetektering för att jämföra den utskrivna modellen mot en 3D-modell. En förbättring av denna analys med hjälp av state-of-the-art maskininlärning utforskas. Visualiseringen av data sammanställdes i olika kombinationer genom grafer, bilder, 3D-scan, CT-scan, punktmoln och CAD. Med målet att upptäcka abnormiteter i 3D-printade delar.

Place, publisher, year, edition, pages
2022.
Keywords [en]
Additive Manufacturing, Powder Bed Fusion – Laser Based, Quality Assurance, Machine Learning, Edge Detection, Digital Visualisation Software, Data Analysis, Selective Laser Melting
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:hb:diva-28411OAI: oai:DiVA.org:hb-28411DiVA, id: diva2:1690139
Supervisors
Examiners
Available from: 2022-08-26 Created: 2022-08-25 Last updated: 2022-08-26Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Faculty of Textiles, Engineering and Business
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 206 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • harvard-cite-them-right
  • 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