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

Andrii Hrechuk

doi:10.1016/j.procir.2023.03.065

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

Andrii Hrechuk

Lunds universitet

Forskningsoutput: Kapitel i bok/rapport/Conference proceeding › Konferenspaper i proceeding › Peer review

Sammanfattning

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.

Originalspråk	engelska
Titel på värdpublikation	19th CIRP Conference on Modeling of Machining Operations
Redaktörer	Volker Schulze , Dirk Biermann
Förlag	Elsevier
Sidor	384-389
Antal sidor	6
DOI	https://doi.org/10.1016/j.procir.2023.03.065
Status	Published - 2023
Evenemang	19th CIRP Conference on Modeling of Machining Operations, CMMO 2023 - Karlsruhe, Tyskland Varaktighet: 2023 maj 31 → 2023 juni 2

Publikationsserier

Namn	Procedia CIRP
Förlag	Elsevier
Volym	117
ISSN (tryckt)	2212-8271

Konferens

Konferens	19th CIRP Conference on Modeling of Machining Operations, CMMO 2023
Land/Territorium	Tyskland
Ort	Karlsruhe
Period	2023/05/31 → 2023/06/02

Bibliografisk information

Publisher Copyright:
© 2023 Elsevier B.V.. All rights reserved.

Ämnesklassifikation (UKÄ)

Produktionsteknik, arbetsvetenskap och ergonomi

Tillgång till dokument

10.1016/j.procir.2023.03.065Licens: CC BY-NC-ND

Citera det här

@inproceedings{2a053ed3f73d427695a3da1d3a31dc14,

title = "Recognition of drilling-induced defects in Fiber Reinforced Polymers using Machine Learning",

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.",

keywords = "biocomposites, defects, drilling, Machine Learning, metrics, U-Net",

author = "Andrii Hrechuk",

note = "Publisher Copyright: {\textcopyright} 2023 Elsevier B.V.. All rights reserved.; 19th CIRP Conference on Modeling of Machining Operations, CMMO 2023 ; Conference date: 31-05-2023 Through 02-06-2023",

year = "2023",

doi = "10.1016/j.procir.2023.03.065",

language = "English",

series = "Procedia CIRP",

publisher = "Elsevier",

pages = "384--389",

editor = "{Schulze }, Volker and Biermann, {Dirk }",

booktitle = "19th CIRP Conference on Modeling of Machining Operations",

address = "United States",

}

Hrechuk, A 2023, Recognition of drilling-induced defects in Fiber Reinforced Polymers using Machine Learning. i V Schulze & D Biermann (red), 19th CIRP Conference on Modeling of Machining Operations. Procedia CIRP, vol. 117, Elsevier, s. 384-389, 19th CIRP Conference on Modeling of Machining Operations, CMMO 2023, Karlsruhe, Tyskland, 2023/05/31. https://doi.org/10.1016/j.procir.2023.03.065

Recognition of drilling-induced defects in Fiber Reinforced Polymers using Machine Learning. / Hrechuk, Andrii.
19th CIRP Conference on Modeling of Machining Operations. red. / Volker Schulze ; Dirk Biermann. Elsevier, 2023. s. 384-389 (Procedia CIRP; Vol. 117).

Forskningsoutput: Kapitel i bok/rapport/Conference proceeding › Konferenspaper i proceeding › Peer review

TY - GEN

T1 - Recognition of drilling-induced defects in Fiber Reinforced Polymers using Machine Learning

AU - Hrechuk, Andrii

PY - 2023

Y1 - 2023

N2 - 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.

AB - 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.

KW - biocomposites

KW - defects

KW - drilling

KW - Machine Learning

KW - metrics

KW - U-Net

U2 - 10.1016/j.procir.2023.03.065

DO - 10.1016/j.procir.2023.03.065

M3 - Paper in conference proceeding

AN - SCOPUS:85163078675

T3 - Procedia CIRP

SP - 384

EP - 389

BT - 19th CIRP Conference on Modeling of Machining Operations

A2 - Schulze , Volker

A2 - Biermann, Dirk

PB - Elsevier

T2 - 19th CIRP Conference on Modeling of Machining Operations, CMMO 2023

Y2 - 31 May 2023 through 2 June 2023

ER -

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

Sammanfattning

Publikationsserier

Konferens

Bibliografisk information

Ämnesklassifikation (UKÄ)

Tillgång till dokument

Fingeravtryck

Citera det här