Development of a Smart Gas Metal Arc Welding System Using Acoustic Sensing

Cullen, Mitchell C.

Development of a Smart Gas Metal Arc Welding System Using Acoustic Sensing

Cullen, Mitchell C.

Permalink

Publication Type:: Thesis
Issue Date:: 2023

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (4 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Cullen, Mitchell C.
dc.date.accessioned	2024-04-16T02:06:51Z
dc.date.available	2024-04-16T02:06:51Z
dc.date.issued	2023
dc.identifier.uri	http://hdl.handle.net/10453/177948
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	Gas Metal Arc Welding (GMAW) is a widely utilized welding process that involves the formation of an electric arc between a consumable wire electrode and a metal workpiece, protected from contaminants by a shielding gas. While GMAW is a reliable, fast, and effective welding method, controlling it can be challenging, especially in automated processes where skilled operators are absent. Skilled welders traditionally rely on audible and visual cues to control the arc, ensuring proper penetration and minimizing the occurrence of defects. Automated robotic welding processes currently lack an adequate quality control system that can replicate the abilities of experienced welders. This deficiency leads to expensive quality control checks after production, increased labour time for reworks, and extended downtime while rectifying issues. However, the implementation of an effective real-time quality control system enables the immediate detection of defects during production, allowing prompt resolution and avoiding costly post-production checks. This research aims to replicate the abilities of manual welders by utilizing acoustic signals to monitor the droplet transfer process. Signal processing and machine learning techniques are employed to analyse the acoustic signals and monitor the formation of the weld bead. By monitoring the droplet transfer process, it becomes possible to assess the physical properties of the weld bead as it forms, thereby detecting defects like porosity and burn-through. Additionally, a digital twin of the weld bead formation was created to provide real-time visualization of penetration depth and cross-sectional profile growth. This new system is able to accurately detect the droplet transfer mode, defects, and plot the penetration profile with 96%, 90%, and 90% accuracy respectively. The acoustic monitoring system developed in this study offers simplicity, easy installation, and non-intrusiveness, making it an ideal plug-and-play solution for modern automated industrial GMAW welding applications. Its implementation minimizes costs and downtime associated with troubleshooting, non-destructive testing, and on-site reworks.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/177948/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2023 Mitchell C. Cullen
dc.rights	au.edu.uts.lib/cph
dc.title	Development of a Smart Gas Metal Arc Welding System Using Acoustic Sensing	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

Gas Metal Arc Welding (GMAW) is a widely utilized welding process that involves the formation of an electric arc between a consumable wire electrode and a metal workpiece, protected from contaminants by a shielding gas. While GMAW is a reliable, fast, and effective welding method, controlling it can be challenging, especially in automated processes where skilled operators are absent. Skilled welders traditionally rely on audible and visual cues to control the arc, ensuring proper penetration and minimizing the occurrence of defects. Automated robotic welding processes currently lack an adequate quality control system that can replicate the abilities of experienced welders. This deficiency leads to expensive quality control checks after production, increased labour time for reworks, and extended downtime while rectifying issues. However, the implementation of an effective real-time quality control system enables the immediate detection of defects during production, allowing prompt resolution and avoiding costly post-production checks. This research aims to replicate the abilities of manual welders by utilizing acoustic signals to monitor the droplet transfer process. Signal processing and machine learning techniques are employed to analyse the acoustic signals and monitor the formation of the weld bead. By monitoring the droplet transfer process, it becomes possible to assess the physical properties of the weld bead as it forms, thereby detecting defects like porosity and burn-through. Additionally, a digital twin of the weld bead formation was created to provide real-time visualization of penetration depth and cross-sectional profile growth. This new system is able to accurately detect the droplet transfer mode, defects, and plot the penetration profile with 96%, 90%, and 90% accuracy respectively. The acoustic monitoring system developed in this study offers simplicity, easy installation, and non-intrusiveness, making it an ideal plug-and-play solution for modern automated industrial GMAW welding applications. Its implementation minimizes costs and downtime associated with troubleshooting, non-destructive testing, and on-site reworks.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/177948