EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TIG welding defect detection using ResNet and Random Forest

Vu Quang Huy, Vu Minh Thuan, Hoang Van Huong, Tran Minh The Uyen, Van-Thuc Nguyen, Pham Son Minh iD

PLOS One · 30.07.2026 · 21 (7) · e0353276

DOI: 10.1371/journal.pone.0353276 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 30.07.2026. Verfasst von Vu Quang Huy und 5 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Advanced Education, Ho Chi Minh City University of Technology and Engineering, HCM City, Vietnam. Hauptthemen laut MEDLINE: Welding, Image Processing, Computer-Assisted. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ho Chi Minh City University of Technology and Engineering.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Orbital TIG welding is critical in precision manufacturing, where weld defects can affect structural reliability. Manual inspection, analysis, and evaluation of welding defect images are complex because defect characteristics vary in shape, position, and size, making the process time-consuming. This study proposes a method that combines ResNet50 feature extraction with Random Forest classification to improve classification accuracy. A total of 3,219 weld image samples collected from controlled orbital TIG experiments were used for model training and evaluation and divided into four classes: normal weld, lack of fusion, overheating, and uneven weld. Using five-fold cross-validation, the method achieved an overall accuracy of 98% and demonstrated improved performance compared with CNN architectures (VGG16, VGG19, ResNet18, ResNet50) and traditional machine learning approaches such as SVM and Random Forest. ResNet50 extracts hierarchical visual representations through deep residual connections, enabling automatic feature learning, while Random Forest performs the final classification with robustness against overfitting on high-dimensional features.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WeldingImage Processing, Computer-AssistedRandom ForestConvolutional Neural NetworksMachine LearningClassification Algorithms

Autor:innen und Institutionen

  • Faculty of Advanced Education, Ho Chi Minh City University of Technology and Engineering, HCM City, Vietnam.
  • Faculty of Mechanical Engineering, Ho Chi Minh City University of Technology and Engineering, HCM City, Vietnam.

ORCID-Profile: Pham Son Minh

Förderung

  • Ho Chi Minh City University of Technology and Engineering

Zitieren

APA

Quang Huy, V., Minh Thuan, V., Van Huong, H., The Uyen, T. M., Nguyen, V. T., & Son Minh, P. (2026). TIG welding defect detection using ResNet and Random Forest. PLOS One, 21(7), e0353276. https://doi.org/10.1371/journal.pone.0353276

Vancouver

Quang Huy V, Minh Thuan V, Van Huong H, The Uyen TM, Nguyen VT, Son Minh P. TIG welding defect detection using ResNet and Random Forest. PLOS One. 2026;21(7):e0353276. doi:10.1371/journal.pone.0353276

BibTeX
@article{QuangHuy2026,
  author = {Quang Huy, Vu and Minh Thuan, Vu and Van Huong, Hoang and The Uyen, Tran Minh and Nguyen, Van-Thuc and Son Minh, Pham},
  title = {TIG welding defect detection using ResNet and Random Forest},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {7},
  pages = {e0353276},
  doi = {10.1371/journal.pone.0353276}
}
Kostenlos starten →