Semi-Supervised Training for Positioning of Welding Seams

Robotic welding often uses vision-based measurement to find the correct placement of the welding seam. Traditional machine vision methods work well in many cases but lack robustness when faced with variations in the manufacturing process or in the imaging conditions. While supervised deep neural net...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Wenbin Zhang, Jochen Lang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	welding seam semi-supervised learning localization Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/8e110c9f998142fd94a346a7bb346a65
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8e110c9f998142fd94a346a7bb346a65
record_format	dspace
spelling	oai:doaj.org-article:8e110c9f998142fd94a346a7bb346a652021-11-11T19:15:38ZSemi-Supervised Training for Positioning of Welding Seams10.3390/s212173091424-8220https://doaj.org/article/8e110c9f998142fd94a346a7bb346a652021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7309https://doaj.org/toc/1424-8220Robotic welding often uses vision-based measurement to find the correct placement of the welding seam. Traditional machine vision methods work well in many cases but lack robustness when faced with variations in the manufacturing process or in the imaging conditions. While supervised deep neural networks have been successful in increasing accuracy and robustness in many real-world measurement applications, their success relies on labeled data. In this paper, we employ semi-supervised learning to simultaneously increase accuracy and robustness while avoiding expensive and time-consuming labeling efforts by a domain expert. While semi-supervised learning approaches for various image classification tasks exist, we purpose a novel algorithm for semi-supervised key-point detection for seam placement by a welding robot. We demonstrate that our approach can work robustly with as few as fifteen labeled images. In addition, our method utilizes full image resolution to enhance the accuracy of the key-point detection in seam placement.Wenbin ZhangJochen LangMDPI AGarticlewelding seamsemi-supervised learninglocalizationChemical technologyTP1-1185ENSensors, Vol 21, Iss 7309, p 7309 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	welding seam semi-supervised learning localization Chemical technology TP1-1185
spellingShingle	welding seam semi-supervised learning localization Chemical technology TP1-1185 Wenbin Zhang Jochen Lang Semi-Supervised Training for Positioning of Welding Seams
description	Robotic welding often uses vision-based measurement to find the correct placement of the welding seam. Traditional machine vision methods work well in many cases but lack robustness when faced with variations in the manufacturing process or in the imaging conditions. While supervised deep neural networks have been successful in increasing accuracy and robustness in many real-world measurement applications, their success relies on labeled data. In this paper, we employ semi-supervised learning to simultaneously increase accuracy and robustness while avoiding expensive and time-consuming labeling efforts by a domain expert. While semi-supervised learning approaches for various image classification tasks exist, we purpose a novel algorithm for semi-supervised key-point detection for seam placement by a welding robot. We demonstrate that our approach can work robustly with as few as fifteen labeled images. In addition, our method utilizes full image resolution to enhance the accuracy of the key-point detection in seam placement.
format	article
author	Wenbin Zhang Jochen Lang
author_facet	Wenbin Zhang Jochen Lang
author_sort	Wenbin Zhang
title	Semi-Supervised Training for Positioning of Welding Seams
title_short	Semi-Supervised Training for Positioning of Welding Seams
title_full	Semi-Supervised Training for Positioning of Welding Seams
title_fullStr	Semi-Supervised Training for Positioning of Welding Seams
title_full_unstemmed	Semi-Supervised Training for Positioning of Welding Seams
title_sort	semi-supervised training for positioning of welding seams
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8e110c9f998142fd94a346a7bb346a65
work_keys_str_mv	AT wenbinzhang semisupervisedtrainingforpositioningofweldingseams AT jochenlang semisupervisedtrainingforpositioningofweldingseams
_version_	1718431597834797056

Semi-Supervised Training for Positioning of Welding Seams

Ejemplares similares