https://www.mdu.se/

mdu.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
Explainable Machine Learning to Improve Assembly Line Automation
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0003-3802-4721
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems.ORCID iD: 0000-0002-1212-7637
GKN ePowertrain, Volvogatan 6,73136, Köping, Sweden.
2021 (English)In: Proceedings - 2021 4th International Conference on Artificial Intelligence for Industries, AI4I 2021, 2021, p. 81-85Conference paper, Published paper (Refereed)
Abstract [en]

Faulty manufactured product causes huge economic loss in the manufacturing industry. A local company produces a power transfer unit (PTU) for the vehicle industry and in this production 3% of PTU are rejected due to a mismatch of shim (a small mechanical part supporting PTU). Today the dimension of a shim is predicted manually by human experts. However, there are several problems due to the manual prediction of shim dimension, automatic central control from the cloud cannot be done. Additionally, it increases rejection rates and as a consequence decreases the reliability of the systems. To solve these problems, in this study shim prediction is implemented in the manufacturing of PTU with explainable Machine Learning (ML) which automates the manual shim selection process in the assembly line and explains the ML prediction. A hybrid approach that combines support vector regression (SVR) and k nearest neighbours (kNN) for the first part of the assembly line and Partial Least Squares (PLS) and kNN for the second part of the assembly line is used for shim prediction. The hybrid approach is selected due to better performance compared to the single ML model approach. Then, the most important features of the hybrid approach were identified with SHAP (SHapley Additive exPlanations). The result indicates due to this improved automation faulty PTU rate decreased from 3% to only 1%. Additionally, it enabled control from the cloud and increased reliability. From the explanation of the hybrid approach, it is evident that one of the features values has more impact on the prediction output and controlling this feature will reduce the rejection rate.

Place, publisher, year, edition, pages
2021. p. 81-85
Keywords [en]
Manufacturing industries;Support vector machines;Automation;Manufacturing processes;Manufactured products;Digital twin;Manuals;Explainable Machine Learning;Power transfer unit;Hybrid approach
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mdh:diva-56398DOI: 10.1109/AI4I51902.2021.00028Scopus ID: 2-s2.0-85126020181ISBN: 978-1-6654-3411-9 (print)OAI: oai:DiVA.org:mdh-56398DiVA, id: diva2:1610018
Conference
2021 4th International Conference on Artificial Intelligence for Industries (AI4I), 20-22 Sept. 2021
Available from: 2021-11-09 Created: 2021-11-09 Last updated: 2022-03-18Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Sheuly, Sharmin SultanaAhmed, Mobyen UddinBegum, Shahina

Search in DiVA

By author/editor
Sheuly, Sharmin SultanaAhmed, Mobyen UddinBegum, Shahina
By organisation
Embedded Systems
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 35 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