Multi-Type Weld Defect Detection in Galvanized Sheet MIG Welding Using an Improved YOLOv10 Model.
Saved in:
| Title: | Multi-Type Weld Defect Detection in Galvanized Sheet MIG Welding Using an Improved YOLOv10 Model. |
|---|---|
| Authors: | Xiao, Bangzhi1 (AUTHOR), Yang, Yadong2 (AUTHOR), He, Yinshui3 (AUTHOR), Ma, Guohong1,2 (AUTHOR) mgh@ncu.edu.cn |
| Source: | Materials (1996-1944). Mar2026, Vol. 19 Issue 6, p1178. 19p. |
| Subjects: | Welding defects, Deep learning, Computer vision, Engineering inspection, Edge computing, Sheet steel, Gas metal arc welding, Object recognition (Computer vision) |
| Abstract: | Shop-floor weld inspection may appear to be a solved problem until a camera is deployed near a galvanized-sheet MIG welding line. The seam reflects light, the texture changes from frame to frame, and the defects of interest are often small and visually subtle. Additionally, the hardware near the line is rarely a data-center GPU. With those constraints in mind, this paper presents YOLO-MIG, a compact detector built on YOLOv10n for weld-seam inspection in practical production conditions. We make three focused changes to the baseline: a C2f-EMSCP backbone block to better preserve weak defect cues with modest parameter growth, a BiFPN neck to keep small-target information alive during feature fusion, and a C2fCIB head to clean up predictions that otherwise get distracted by seam edges and illumination artifacts. On a workshop-collected dataset containing 326 original images, with the training subset expanded through augmentation to 2608 labeled samples in total, YOLO-MIG achieves 98.4% mAP@0.5 and 56.29% mAP@0.5:0.95 on the test set while remaining lightweight (1.83 M parameters, 3.87 MB FP16 weights). Compared with YOLOv10n, the proposed model improves mAP@0.5 by 9.36 points and mAP@0.5:0.95 by 4.89 points, while reducing parameters, GFLOPs, and model size by 43.4%, 19.9%, and 29.9%, respectively. The results suggest that YOLO-MIG is not only accurate but also realistic to deploy at the edge for intelligent weld quality control. [ABSTRACT FROM AUTHOR] |
| Copyright of Materials (1996-1944) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 192591611 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Multi-Type Weld Defect Detection in Galvanized Sheet MIG Welding Using an Improved YOLOv10 Model. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Xiao%2C+Bangzhi%22">Xiao, Bangzhi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yang%2C+Yadong%22">Yang, Yadong</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22He%2C+Yinshui%22">He, Yinshui</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ma%2C+Guohong%22">Ma, Guohong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> mgh@ncu.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Materials+%281996-1944%29%22">Materials (1996-1944)</searchLink>. Mar2026, Vol. 19 Issue 6, p1178. 19p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Welding+defects%22">Welding defects</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Engineering+inspection%22">Engineering inspection</searchLink><br /><searchLink fieldCode="DE" term="%22Edge+computing%22">Edge computing</searchLink><br /><searchLink fieldCode="DE" term="%22Sheet+steel%22">Sheet steel</searchLink><br /><searchLink fieldCode="DE" term="%22Gas+metal+arc+welding%22">Gas metal arc welding</searchLink><br /><searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Shop-floor weld inspection may appear to be a solved problem until a camera is deployed near a galvanized-sheet MIG welding line. The seam reflects light, the texture changes from frame to frame, and the defects of interest are often small and visually subtle. Additionally, the hardware near the line is rarely a data-center GPU. With those constraints in mind, this paper presents YOLO-MIG, a compact detector built on YOLOv10n for weld-seam inspection in practical production conditions. We make three focused changes to the baseline: a C2f-EMSCP backbone block to better preserve weak defect cues with modest parameter growth, a BiFPN neck to keep small-target information alive during feature fusion, and a C2fCIB head to clean up predictions that otherwise get distracted by seam edges and illumination artifacts. On a workshop-collected dataset containing 326 original images, with the training subset expanded through augmentation to 2608 labeled samples in total, YOLO-MIG achieves 98.4% mAP@0.5 and 56.29% mAP@0.5:0.95 on the test set while remaining lightweight (1.83 M parameters, 3.87 MB FP16 weights). Compared with YOLOv10n, the proposed model improves mAP@0.5 by 9.36 points and mAP@0.5:0.95 by 4.89 points, while reducing parameters, GFLOPs, and model size by 43.4%, 19.9%, and 29.9%, respectively. The results suggest that YOLO-MIG is not only accurate but also realistic to deploy at the edge for intelligent weld quality control. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Materials (1996-1944) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192591611 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/ma19061178 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 19 StartPage: 1178 Subjects: – SubjectFull: Welding defects Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Computer vision Type: general – SubjectFull: Engineering inspection Type: general – SubjectFull: Edge computing Type: general – SubjectFull: Sheet steel Type: general – SubjectFull: Gas metal arc welding Type: general – SubjectFull: Object recognition (Computer vision) Type: general Titles: – TitleFull: Multi-Type Weld Defect Detection in Galvanized Sheet MIG Welding Using an Improved YOLOv10 Model. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Xiao, Bangzhi – PersonEntity: Name: NameFull: Yang, Yadong – PersonEntity: Name: NameFull: He, Yinshui – PersonEntity: Name: NameFull: Ma, Guohong IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 03 Text: Mar2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 19961944 Numbering: – Type: volume Value: 19 – Type: issue Value: 6 Titles: – TitleFull: Materials (1996-1944) Type: main |
| ResultId | 1 |
