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
Automatiserad sortering av hushållsbatterier med AI och bildigenkänning
University of Borås, Faculty of Textiles, Engineering and Business.
University of Borås, Faculty of Textiles, Engineering and Business.
2024 (Swedish)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Automated sorting of household batteries using AI and image recognition (English)
Abstract [sv]

Denna rapport presenterar utvecklingen och utvärderingen av en AI-baserad prototyp för sortering av hushållsbatterier. Syftet är att förbättra effektiviteten, noggrannheten och säkerheten i återvinningsprocessen genom att automatisera identifieringen och hanteringen av olika batterityper.

Projektet omfattar utvecklingen av en maskininlärningsmodell baserad på konvolutionella neurala nätverk (CNN), som identifierar batterier med hög precision. Modellen har integrerats i en prototyp bestående av ett transportband och en robotarm, vilket möjliggör en fullt automatiserad sorteringsprocess.

Prototypen visade hög effektivitet i att hantera flera batterier under korta tidsintervall. Den teoretiska delen av arbetet bidrar med insikter om hur AI och robotik kan integreras för att driva innovationer inom hållbarhetsteknik, medan det praktiska bidraget visar potentialen för att implementera effektiva och säkra metoder i storskalig batteriåtervinning. Forskningen belyser hur AI kan automatisera och förbättra komplexa och riskfyllda processer inom återvinningsindustrin, och öppnar för vidare forskning och utveckling inom området.

Abstract [en]

This report presents the development and evaluation of an AI-based prototype for sorting household batteries. The aim is to improve the efficiency, accuracy, and safety of the recycling process by automating the identification and handling of different battery types.

The project involves the development of a machine learning model based on convolutional neural networks (CNN), which identifies batteries with high precision. The model has been integrated into a prototype consisting of a conveyor belt and a robotic arm, enabling a fully automated sorting process.

The prototype demonstrated high efficiency in handling multiple batteries within short time intervals. The theoretical part of the work provides insights into how AI and robotics can be integrated to drive innovation in sustainability technology, while the practical contribution highlights the potential for implementing efficient and safe methods in large-scale battery recycling. The research highlights how AI can automate and improve complex and risky processes in the recycling industry, opening up further research and development opportunities in the field. 

Place, publisher, year, edition, pages
2024.
Keywords [sv]
Artificiell intelligens, Bildigenkänning, Batteriåtervinning, Automatiserad sortering
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:hb:diva-32796OAI: oai:DiVA.org:hb-32796DiVA, id: diva2:1913103
Subject / course
Maskinteknik - Högskoleingenjör
Supervisors
Examiners
Available from: 2024-11-21 Created: 2024-11-14 Last updated: 2025-09-24Bibliographically approved

Open Access in DiVA

Arbete(2131 kB)180 downloads
File information
File name FULLTEXT01.pdfFile size 2131 kBChecksum SHA-512
9ff8795040bfd8ac2c7563ad7cfd43d646ee906736f2b0e12f5cbdc0d171d3c80cb94dd1f9a5e9a7d20ad67f241edbf1d91b00a5c2f7881603ab9b42d8b24214
Type fulltextMimetype application/pdf

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

Search outside of DiVA

GoogleGoogle Scholar
Total: 180 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: 975 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