Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Recognition of drilling-induced defects in Fiber Reinforced Polymers using Machine Learning

Hrechuk, Andrii LU orcid (2023) 19th CIRP Conference on Modeling of Machining Operations, CMMO 2023 In Procedia CIRP 117. p.384-389
Abstract

The machining of Fiber Reinforced Polymers (FRP) is accompanied by specific defects such as delamination, uncut fibers, and others. Such defects are unique in their shape and size for different FRP types, used tools, and applied cutting conditions. Therefore, defect recognition and quantification remain a central challenge in the quality control of FRP components from an accuracy and time balance perspective. The study presents the implementation of Machine Learning techniques for automated recognition of the hole defects resulting from drilling Flax/PLA biocomposites using HSS drills with various cutting data. The paper discusses the effectiveness and stability of the developed solution.

Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
biocomposites, defects, drilling, Machine Learning, metrics, U-Net
host publication
19th CIRP Conference on Modeling of Machining Operations
series title
Procedia CIRP
editor
Schulze, Volker and Biermann, Dirk
volume
117
pages
6 pages
publisher
Elsevier
conference name
19th CIRP Conference on Modeling of Machining Operations, CMMO 2023
conference location
Karlsruhe, Germany
conference dates
2023-05-31 - 2023-06-02
external identifiers
  • scopus:85163078675
ISSN
2212-8271
DOI
10.1016/j.procir.2023.03.065
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2023 Elsevier B.V.. All rights reserved.
id
2a053ed3-f73d-4276-95a3-da1d3a31dc14
date added to LUP
2023-07-31 10:25:49
date last changed
2024-03-08 04:09:54
@inproceedings{2a053ed3-f73d-4276-95a3-da1d3a31dc14,
  abstract     = {{<p>The machining of Fiber Reinforced Polymers (FRP) is accompanied by specific defects such as delamination, uncut fibers, and others. Such defects are unique in their shape and size for different FRP types, used tools, and applied cutting conditions. Therefore, defect recognition and quantification remain a central challenge in the quality control of FRP components from an accuracy and time balance perspective. The study presents the implementation of Machine Learning techniques for automated recognition of the hole defects resulting from drilling Flax/PLA biocomposites using HSS drills with various cutting data. The paper discusses the effectiveness and stability of the developed solution.</p>}},
  author       = {{Hrechuk, Andrii}},
  booktitle    = {{19th CIRP Conference on Modeling of Machining Operations}},
  editor       = {{Schulze, Volker and Biermann, Dirk}},
  issn         = {{2212-8271}},
  keywords     = {{biocomposites; defects; drilling; Machine Learning; metrics; U-Net}},
  language     = {{eng}},
  pages        = {{384--389}},
  publisher    = {{Elsevier}},
  series       = {{Procedia CIRP}},
  title        = {{Recognition of drilling-induced defects in Fiber Reinforced Polymers using Machine Learning}},
  url          = {{http://dx.doi.org/10.1016/j.procir.2023.03.065}},
  doi          = {{10.1016/j.procir.2023.03.065}},
  volume       = {{117}},
  year         = {{2023}},
}