Automated defect classification of SS304 TIG welding process using visible spectrum camera and machine learning

Research output: Contribution to journalArticle

Standard

Automated defect classification of SS304 TIG welding process using visible spectrum camera and machine learning. / Bacioiu, Daniel; Melton, Geoff; Papaelias, Mayorkinos; Shaw, Rob.

In: NDT & E International, Vol. 107, 102139, 01.10.2019.

Research output: Contribution to journalArticle

Harvard

APA

Vancouver

Author

Bibtex

@article{f68e6f8077bf4a249c0294eb242f03e0,
title = "Automated defect classification of SS304 TIG welding process using visible spectrum camera and machine learning",
abstract = "Tungsten Inert Gas welding is dependent on human supervision, it has an emphasis on visual assessment, and it is performed in a controlled environment, making it suitable for automation. This study designs a system for assessing the tungsten inert gas welding quality with the potential of application in real-time. The system uses images in the visible spectrum paired with the state-of-the-art approach for image classification. The welding images represent the weld pool in visible spectra balanced using high dynamic range technology to offset the powerful arc light. The study trains models on a new tungsten inert gas welding dataset, leveraging the state-of-the-art machine learning research, establishing a correlation between the aspect of the weld pool and surrounding area and the weld quality, similar to an operator's assessment.",
keywords = "Weld monitoring, High dynamic range camera, Machine learning, Vision, Automation",
author = "Daniel Bacioiu and Geoff Melton and Mayorkinos Papaelias and Rob Shaw",
year = "2019",
month = "10",
day = "1",
doi = "10.1016/j.ndteint.2019.102139",
language = "English",
volume = "107",
journal = "NDT & E International",
issn = "0963-8695",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Automated defect classification of SS304 TIG welding process using visible spectrum camera and machine learning

AU - Bacioiu, Daniel

AU - Melton, Geoff

AU - Papaelias, Mayorkinos

AU - Shaw, Rob

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Tungsten Inert Gas welding is dependent on human supervision, it has an emphasis on visual assessment, and it is performed in a controlled environment, making it suitable for automation. This study designs a system for assessing the tungsten inert gas welding quality with the potential of application in real-time. The system uses images in the visible spectrum paired with the state-of-the-art approach for image classification. The welding images represent the weld pool in visible spectra balanced using high dynamic range technology to offset the powerful arc light. The study trains models on a new tungsten inert gas welding dataset, leveraging the state-of-the-art machine learning research, establishing a correlation between the aspect of the weld pool and surrounding area and the weld quality, similar to an operator's assessment.

AB - Tungsten Inert Gas welding is dependent on human supervision, it has an emphasis on visual assessment, and it is performed in a controlled environment, making it suitable for automation. This study designs a system for assessing the tungsten inert gas welding quality with the potential of application in real-time. The system uses images in the visible spectrum paired with the state-of-the-art approach for image classification. The welding images represent the weld pool in visible spectra balanced using high dynamic range technology to offset the powerful arc light. The study trains models on a new tungsten inert gas welding dataset, leveraging the state-of-the-art machine learning research, establishing a correlation between the aspect of the weld pool and surrounding area and the weld quality, similar to an operator's assessment.

KW - Weld monitoring

KW - High dynamic range camera

KW - Machine learning

KW - Vision

KW - Automation

U2 - 10.1016/j.ndteint.2019.102139

DO - 10.1016/j.ndteint.2019.102139

M3 - Article

VL - 107

JO - NDT & E International

JF - NDT & E International

SN - 0963-8695

M1 - 102139

ER -