Weld seam feature point extraction using laser and vision sensor

Vision sensors are used in welding seam applications for image capture and post-processing of image data. When utilized with welding robots, it is essential for establishing control quality of seam tracking that is up to par. The vision sensor works with a laser to provide the advantage of extractin...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohd Shah, Hairol Nizam, Mohammed Naji, Osamah Abdullah Ahmed, Sulaiman, Marizan, Johan, Nurul Fatiha
Format: Article
Language:English
Published: Springer Science and Business Media Deutschland GmbH 2023
Online Access:http://eprints.utem.edu.my/id/eprint/27349/2/0127522122023571.PDF
http://eprints.utem.edu.my/id/eprint/27349/
https://link.springer.com/article/10.1007/s00170-023-11776-5#:~:text=Feature%20extraction%20is%20used%20for,is%20for%20weld%20seam%20tracking.
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Teknikal Malaysia Melaka
Language: English
id my.utem.eprints.27349
record_format eprints
spelling my.utem.eprints.273492024-07-04T11:16:09Z http://eprints.utem.edu.my/id/eprint/27349/ Weld seam feature point extraction using laser and vision sensor Mohd Shah, Hairol Nizam Mohammed Naji, Osamah Abdullah Ahmed Sulaiman, Marizan Johan, Nurul Fatiha Vision sensors are used in welding seam applications for image capture and post-processing of image data. When utilized with welding robots, it is essential for establishing control quality of seam tracking that is up to par. The vision sensor works with a laser to provide the advantage of extracting the location of the weld seam. However, in terms of visual perspective, the challenges may come from the possible environment illumination, imperfections on the workpiece surface such as stain and scratches, error from the hardware setting, or laser reflection which produces a lot of image noises. The noise generated by the laser beam on the surface of the workpiece due to the specifications of the laser itself can cause the centerline of the laser to become uneven, usually making it difficult to extract the feature point of the weld seam. In this work, a method to improve the quality of the centerline by constructing a more stable centerline has been presented to obtain the pixel location of the welding seam point in the x–y coordinate by considering the effect of laser reflection on the workpiece. Three main phases have been employed to realize the objectives: laser extraction, broken-line fitting, and pixel location determination. To locate a pixel coordinate, a technique of the qualitative description based on the V-groove of butt joint had been developed. Two metals of butt joint, each of which has two different types of lines with several laser positions on the workpiece are tested in order to validate the accuracy of the proposed method. The approach has minimal error outcomes when compared to the actual value and has no noticeable impact on the system’s effectiveness. Springer Science and Business Media Deutschland GmbH 2023-07 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/27349/2/0127522122023571.PDF Mohd Shah, Hairol Nizam and Mohammed Naji, Osamah Abdullah Ahmed and Sulaiman, Marizan and Johan, Nurul Fatiha (2023) Weld seam feature point extraction using laser and vision sensor. International Journal of Advanced Manufacturing Technology, 127. pp. 5155-5170. ISSN 0268-3768 https://link.springer.com/article/10.1007/s00170-023-11776-5#:~:text=Feature%20extraction%20is%20used%20for,is%20for%20weld%20seam%20tracking. 10.1007/s00170-023-11776-5
institution Universiti Teknikal Malaysia Melaka
building UTEM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknikal Malaysia Melaka
content_source UTEM Institutional Repository
url_provider http://eprints.utem.edu.my/
language English
description Vision sensors are used in welding seam applications for image capture and post-processing of image data. When utilized with welding robots, it is essential for establishing control quality of seam tracking that is up to par. The vision sensor works with a laser to provide the advantage of extracting the location of the weld seam. However, in terms of visual perspective, the challenges may come from the possible environment illumination, imperfections on the workpiece surface such as stain and scratches, error from the hardware setting, or laser reflection which produces a lot of image noises. The noise generated by the laser beam on the surface of the workpiece due to the specifications of the laser itself can cause the centerline of the laser to become uneven, usually making it difficult to extract the feature point of the weld seam. In this work, a method to improve the quality of the centerline by constructing a more stable centerline has been presented to obtain the pixel location of the welding seam point in the x–y coordinate by considering the effect of laser reflection on the workpiece. Three main phases have been employed to realize the objectives: laser extraction, broken-line fitting, and pixel location determination. To locate a pixel coordinate, a technique of the qualitative description based on the V-groove of butt joint had been developed. Two metals of butt joint, each of which has two different types of lines with several laser positions on the workpiece are tested in order to validate the accuracy of the proposed method. The approach has minimal error outcomes when compared to the actual value and has no noticeable impact on the system’s effectiveness.
format Article
author Mohd Shah, Hairol Nizam
Mohammed Naji, Osamah Abdullah Ahmed
Sulaiman, Marizan
Johan, Nurul Fatiha
spellingShingle Mohd Shah, Hairol Nizam
Mohammed Naji, Osamah Abdullah Ahmed
Sulaiman, Marizan
Johan, Nurul Fatiha
Weld seam feature point extraction using laser and vision sensor
author_facet Mohd Shah, Hairol Nizam
Mohammed Naji, Osamah Abdullah Ahmed
Sulaiman, Marizan
Johan, Nurul Fatiha
author_sort Mohd Shah, Hairol Nizam
title Weld seam feature point extraction using laser and vision sensor
title_short Weld seam feature point extraction using laser and vision sensor
title_full Weld seam feature point extraction using laser and vision sensor
title_fullStr Weld seam feature point extraction using laser and vision sensor
title_full_unstemmed Weld seam feature point extraction using laser and vision sensor
title_sort weld seam feature point extraction using laser and vision sensor
publisher Springer Science and Business Media Deutschland GmbH
publishDate 2023
url http://eprints.utem.edu.my/id/eprint/27349/2/0127522122023571.PDF
http://eprints.utem.edu.my/id/eprint/27349/
https://link.springer.com/article/10.1007/s00170-023-11776-5#:~:text=Feature%20extraction%20is%20used%20for,is%20for%20weld%20seam%20tracking.
_version_ 1804070314240376832