Scholarlink

<p>Gas metal arc welding (GMAW) is a widely utilised welding method that forms an electric arc between a consumable wire electrode and a metal workpiece, safeguarded from impurities by a shielding gas. Despite its reputation for being a dependable, fast, and efficient welding method, various defects may arise during welding, potentially compromising the strength of the weld bead. Of these defects, burn-through, porosity, and insufficient penetration are all critical defects that can severely impact the quality of the produced weld bead. Historically, skilled welders have been adept at recognising these flaws by relying on audible and visual cues. However, there is a noticeable lack of research in the available literature concerning the replication of this skill. This paper introduces an innovative automatic approach for detecting faults in GMAW by monitoring the changes in droplet transfer mode during the welding process. The proposed fault detection algorithm exhibits a strong capability to identify and pinpoint burn-through and porosity defects across various natural GMAW droplet transfer modes, accurately detecting 27 out of the 30 burn-through occurrences and all 22 porosity defects presented in this paper. Additionally, it enables the penetration depth to be estimated within <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="170_2024_14932_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="31" /> </InlineMediaObject> <EquationSource Format="TEX">\(15\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>15</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation> of the values measured from the etched cross-sections, demonstrating its potential as a promising solution for online monitoring in robotic or automated welding applications. These encouraging results highlight the potential of acoustic signal monitoring in automated welding processes to facilitate early detection of significant welding anomalies, thereby reducing dependence on costly non-destructive testing and minimising on-site rework.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Online defect detection and penetration estimation system for gas metal arc welding

  • 期刊论文

  • 发表日期：

    2025年1月2日

查看全文
  • Mitchell Cullen,
  • J. C. Ji

摘要

Gas metal arc welding (GMAW) is a widely utilised welding method that forms an electric arc between a consumable wire electrode and a metal workpiece, safeguarded from impurities by a shielding gas. Despite its reputation for being a dependable, fast, and efficient welding method, various defects may arise during welding, potentially compromising the strength of the weld bead. Of these defects, burn-through, porosity, and insufficient penetration are all critical defects that can severely impact the quality of the produced weld bead. Historically, skilled welders have been adept at recognising these flaws by relying on audible and visual cues. However, there is a noticeable lack of research in the available literature concerning the replication of this skill. This paper introduces an innovative automatic approach for detecting faults in GMAW by monitoring the changes in droplet transfer mode during the welding process. The proposed fault detection algorithm exhibits a strong capability to identify and pinpoint burn-through and porosity defects across various natural GMAW droplet transfer modes, accurately detecting 27 out of the 30 burn-through occurrences and all 22 porosity defects presented in this paper. Additionally, it enables the penetration depth to be estimated within \(15\%\) 15 % of the values measured from the etched cross-sections, demonstrating its potential as a promising solution for online monitoring in robotic or automated welding applications. These encouraging results highlight the potential of acoustic signal monitoring in automated welding processes to facilitate early detection of significant welding anomalies, thereby reducing dependence on costly non-destructive testing and minimising on-site rework.