Advanced search
1 file | 1.53 MB Add to list

Automatic detection of welding defects using the convolutional neural network

Author
Organization
Abstract
Quality control of welded joints is an important step before commissioning of various types of metal structures. The main obstacles to the commissioning of such facilities are the areas where the welded joint deviates from acceptable defective standards. The defects of welded joints include non-welded, foreign inclusions, cracks, pores, etc. The article describes an approach to the detection of the main types of defects of welded joints using a combination of convolutional neural networks and support vector machine methods. Convolutional neural networks are used for primary classification. The support vector machine is used to accurately define defect boundaries. As a preprocessing in our work, we use the methods of morphological filtration. A series of experiments confirms the high efficiency of the proposed method in comparison with pure CNN method for detecting defects.
Keywords
elding defect detection, convolutional neural network (CNN), support vector machine (SVM), morphological filtering, histogram equalization

Downloads

  • main.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.53 MB

Citation

Please use this url to cite or link to this publication:

MLA
Sizyakin, Roman, et al. “Automatic Detection of Welding Defects Using the Convolutional Neural Network.” AUTOMATED VISUAL INSPECTION AND MACHINE VISION III, edited by Jürgen Beyerer and Fernando Puente León, vol. 11061, SPIE, 2019.
APA
Sizyakin, R., Voronin, V. V., Gapon, N., Zelensky, A., & Pizurica, A. (2019). Automatic detection of welding defects using the convolutional neural network. In J. Beyerer & F. Puente León (Eds.), AUTOMATED VISUAL INSPECTION AND MACHINE VISION III (Vol. 11061). Munich, Germany: SPIE.
Chicago author-date
Sizyakin, Roman, Viacheslav V. Voronin, Nikolay Gapon, Aleksandr Zelensky, and Aleksandra Pizurica. 2019. “Automatic Detection of Welding Defects Using the Convolutional Neural Network.” In AUTOMATED VISUAL INSPECTION AND MACHINE VISION III, edited by Jürgen Beyerer and Fernando Puente León. Vol. 11061. SPIE.
Chicago author-date (all authors)
Sizyakin, Roman, Viacheslav V. Voronin, Nikolay Gapon, Aleksandr Zelensky, and Aleksandra Pizurica. 2019. “Automatic Detection of Welding Defects Using the Convolutional Neural Network.” In AUTOMATED VISUAL INSPECTION AND MACHINE VISION III, ed by. Jürgen Beyerer and Fernando Puente León. Vol. 11061. SPIE.
Vancouver
1.
Sizyakin R, Voronin VV, Gapon N, Zelensky A, Pizurica A. Automatic detection of welding defects using the convolutional neural network. In: Beyerer J, Puente León F, editors. AUTOMATED VISUAL INSPECTION AND MACHINE VISION III. SPIE; 2019.
IEEE
[1]
R. Sizyakin, V. V. Voronin, N. Gapon, A. Zelensky, and A. Pizurica, “Automatic detection of welding defects using the convolutional neural network,” in AUTOMATED VISUAL INSPECTION AND MACHINE VISION III, Munich, Germany, 2019, vol. 11061.
@inproceedings{8620982,
  abstract     = {Quality control of welded joints is an important step before commissioning of various types of metal structures. The main obstacles to the commissioning of such facilities are the areas where the welded joint deviates from acceptable defective standards. The defects of welded joints include non-welded, foreign inclusions, cracks, pores, etc. The article describes an approach to the detection of the main types of defects of welded joints using a combination of convolutional neural networks and support vector machine methods. Convolutional neural networks are used for primary classification. The support vector machine is used to accurately define defect boundaries. As a preprocessing in our work, we use the methods of morphological filtration. A series of experiments confirms the high efficiency of the proposed method in comparison with pure CNN method for detecting defects.},
  articleno    = {11061OE},
  author       = {Sizyakin, Roman and Voronin, Viacheslav V. and Gapon, Nikolay and Zelensky, Aleksandr and Pizurica, Aleksandra},
  booktitle    = {AUTOMATED VISUAL INSPECTION AND MACHINE VISION III},
  editor       = {Beyerer, Jürgen and Puente León, Fernando},
  isbn         = {9781510628014},
  issn         = {0277-786X},
  keywords     = {elding defect detection,convolutional neural network (CNN),support vector machine (SVM),morphological filtering,histogram equalization},
  language     = {eng},
  location     = {Munich, Germany},
  pages        = {9},
  publisher    = {SPIE},
  title        = {Automatic detection of welding defects using the convolutional neural network},
  url          = {http://dx.doi.org/10.1117/12.2525643},
  volume       = {11061},
  year         = {2019},
}

Altmetric
View in Altmetric
Web of Science
Times cited: