Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Surface casting defects inspection using vision system and neural network techniques

Treść / Zawartość
Warianty tytułu
Języki publikacji
The paper presents a vision based approach and neural network techniques in surface defects inspection and categorization. Depending on part design and processing techniques, castings may develop surface discontinuities such as cracks and pores that greatly influence the material’s properties Since the human visual inspection for the surface is slow and expensive, a computer vision system is an alternative solution for the online inspection. The authors present the developed vision system uses an advanced image processing algorithm based on modified Laplacian of Gaussian edge detection method and advanced lighting system. The defect inspection algorithm consists of several parameters that allow the user to specify the sensitivity level at which he can accept the defects in the casting. In addition to the developed image processing algorithm and vision system apparatus, an advanced learning process has been developed, based on neural network techniques. Finally, as an example three groups of defects were investigated demonstrates automatic selection and categorization of the measured defects, such as blowholes, shrinkage porosity and shrinkage cavity.
Opis fizyczny
Bibliogr. 15 poz., rys., tab., wykr.
  • Institute of Manufacturing Technologies, Warsaw University of Technology, Narbutta 85, 02-524 Warsaw, Poland
  • Institute of Manufacturing Technologies, Warsaw University of Technology, Narbutta 85, 02-524 Warsaw, Poland
  • [1] Świłło, S. & Myszka, D. (2011). Computerized system for aluminum alloy defects control. Experts NEMU. 2(10), 10-12.
  • [2] Świłło, S. & Myszka, D. (2011). Advanced metrology of surface defects measurement for aluminum die casting. Archives of Foundry Engineering. 11(spec. 3), 227-230.
  • [3] Perzyk, M. & Kozlowski, J. (2006). Comparison of statistical and neural networks based methods in analysis of significance and interaction of manufacturing process parameter. Computer Methods in Materials Science. 6(2), 81-93.
  • [4] Perzyk, M. & Biernacki, R. (2004). Diagnosis of causes of casting defects with use of statistical methods and neural networks. Archives of Foundry Engineering. 4(11), 71-76.
  • [5] Shanmugaraja, M., Nataraj, M. & Gunasekaran, N. (2011). Defect control analysis for improving quality and productivity: an innovative Six Sigma case study. Int. J. of Quality and Innovation. 1(3), 259-282.
  • [6] Mery, D., Jaeger, Th. & Filbert, D. (2002). A review of methods for automated recognition of casting defects. INSIGHT, Journal of The British Institute of Non-Destructive Testing. 44(7), 428-436.
  • [7] Świłło, S. & Perzyk, M. (2011). Automatic inspection of surface defects in die castings after machining. Archives of Foundry Engineering. 11(3), 231-236.
  • [8] Marr, D. & Hildreth, E. (1980). Theory of edge detection. Proceedings The Royal Society London. 207, 187-217.
  • [9] Dobrzański, L.A., Krupiński, M. & Sokolowski, J.H. (2006). Application of artificial intelligence methods for classification of defects of Al-Si-Cu alloys castings. Archives of Foundry Engineering. 6(22), 598-605.
  • [10] Perzyk, M., Krawiec, K. & Kozłowski, J. (2009). Application of time-series analysis in foundry production. Archives of Foundry Engineering. 9(3), 109-114.
  • [11] Dobrzański, L.A., Krupiński, M. & Sokolowski, J.H. (2007). Methodology of automatic quality control of aluminum castings. Journal of Achievements in Materials and Manufacturing Engineering. 20(1-2), 69-78.
  • [12] Xu, Z., Pietikainen, M., and Ojala, T., (1997). Defect classification by texture in steel surface inspection, Proc. QCAV 97 International Conference on Quality Control by Artificial Vision, Le Creusot, Burgundy, France, (pp. 179-184).
  • [13] Kyllonen, J. & Pietikainen, M. (2000). Visual inspection of parquet slabs by combining color and texture. Proc. IAPR Workshop on Machine Vision Applications. (MVA’00), Tokyo, Japan, 187-192.
  • [14] Wasserman, P.D. (1993). Advanced Methods in Neural Computing. New York, Van Nostrand Reinhold. 155-61.
  • [15] Hagan, M.T., Demuth, H.B. & Beale, M.H. (2002). Neural Network Design, Campus Pub. Service, University of Colorado Bookstore, 1284.
Typ dokumentu
Identyfikator YADDA
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.